fix: avoid SDD task brief path collisions (PRI-2240)

.agents/plugins/marketplace.json

@@ -1,20 +0,0 @@
-{
-  "name": "superpowers-dev",
-  "interface": {
-    "displayName": "Superpowers Dev"
-  },
-  "plugins": [
-    {
-      "name": "superpowers",
-      "source": {
-        "source": "url",
-        "url": "./"
-      },
-      "policy": {
-        "installation": "AVAILABLE",
-        "authentication": "ON_INSTALL"
-      },
-      "category": "Developer Tools"
-    }
-  ]
-}

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "superpowers",
       "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
-      "version": "6.1.1",
+      "version": "6.0.0",
       "source": "./",
       "author": {
         "name": "Jesse Vincent",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "superpowers",
   "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
   "author": {
     "name": "Jesse Vincent",
@@ -21,13 +21,13 @@
     "workflow"
   ],
   "skills": "./skills/",
-  "hooks": {},
+  "hooks": "./hooks/hooks-codex.json",
   "interface": {
     "displayName": "Superpowers",
     "shortDescription": "Planning, TDD, debugging, and delivery workflows for coding agents",
     "longDescription": "Use Superpowers to guide agent work through brainstorming, implementation planning, test-driven development, systematic debugging, parallel execution, code review, and finish-the-branch workflows.",
     "developerName": "Jesse Vincent",
-    "category": "Developer Tools",
+    "category": "Coding",
     "capabilities": [
       "Interactive",
       "Read",

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "superpowers",
   "displayName": "Superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.gitignore

@@ -7,7 +7,8 @@ node_modules/
 inspo
 triage/
 
-# Eval harness lives in its own repository, cloned into evals/ for local
-# development (see CLAUDE.md / README.md). It is not part of the published
-# plugin, so the whole directory is ignored here.
-evals/
+# Eval harness — drill ships its own gitignore at evals/.gitignore;
+# these are belt-and-suspenders entries for tools that don't recurse.
+evals/results/
+evals/.venv/
+evals/.env

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "evals"]
+	path = evals
+	url = git@github.com:prime-radiant-inc/superpowers-evals.git

.kimi-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "description": "An agentic skills framework and software development methodology.",
   "author": {
     "name": "Jesse Vincent",

CLAUDE.md

@@ -101,7 +101,7 @@ Skills are not prose — they are code that shapes agent behavior. If you modify
 
 ## Eval harness
 
-Skill-behavior evals live in [superpowers-evals](https://github.com/prime-radiant-inc/superpowers-evals/), cloned into `evals/` — see `evals/README.md` for setup. The harness drives real tmux sessions of Claude Code / Codex and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
+Skill-behavior evals live in the `evals/` submodule — after cloning, run `git submodule update --init evals`, then see `evals/README.md`. Drill (the harness) drives real tmux sessions of Claude Code / Codex / Gemini CLI and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
 
 ## Understand the Project Before Contributing
 

README.md

@@ -11,7 +11,7 @@ If this sounds like someone you know, definitely send them our way.
 
 ## Quickstart
 
-Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
+Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
 
 ## How it works
 
@@ -122,6 +122,20 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
   droid plugin install superpowers@superpowers
   ```
 
+### Gemini CLI
+
+- Install the extension:
+
+  ```bash
+  gemini extensions install https://github.com/obra/superpowers
+  ```
+
+- Update later:
+
+  ```bash
+  gemini extensions update superpowers
+  ```
+
 ### GitHub Copilot CLI
 
 - Register the marketplace:
@@ -248,7 +262,7 @@ The general contribution process for Superpowers is below. Keep in mind that we
 4. Follow the `writing-skills` skill for creating and testing new and modified skills
 5. Submit a PR, being sure to fill in the pull request template.
 
-Skill-behavior tests use the drill eval harness from [superpowers-evals](https://github.com/prime-radiant-inc/superpowers-evals/), cloned into `evals/` — see `evals/README.md` for setup. Plugin-infrastructure tests live at `tests/` and run via the relevant `run-*.sh` or `npm test`.
+Skill-behavior tests use the eval harness submodule at `evals/`. After cloning this repo, run `git submodule update --init evals`, then see `evals/README.md` for setup. Plugin-infrastructure tests live at `tests/` and run via the relevant `run-*.sh` or `npm test`.
 
 See `skills/writing-skills/SKILL.md` for the complete guide.
 

RELEASE-NOTES.md

@@ -1,53 +1,5 @@
 # Superpowers Release Notes
 
-## v6.1.1 (2026-07-02)
-
-### Codex
-
-- **Codex no longer re-registers the Claude SessionStart hook.** v6.1.0 removed the Codex hook config and its manifest `hooks` pointer, meaning to stop Codex from installing a SessionStart hook — but with no `hooks` field, Codex fell back to auto-discovering `hooks/hooks.json`, the Claude Code SessionStart hook that the marketplace ships from the repo root, and re-registered it along with its install-time trust prompt. The Codex manifest now declares an explicit empty hooks object (`hooks: {}`), which Codex reads as "no hooks" instead of reaching the auto-discovery fallback. An absent field, `[]`, and an empty inline list all collapse back to the fallback, so the value has to be exactly `{}`.
-- **Removed orphaned Codex session-start dead code.** `hooks/session-start-codex` had no caller once the Codex hook config was deleted, so it and its redundant test cases are gone. The worked shell-hook example in `docs/porting-to-a-new-harness.md` moves from Codex — now native skill discovery with no session-start hook — to Cursor, a live shell-hook harness, and the stale `hooks-codex.json` pointer in `docs/windows/polyglot-hooks.md` is corrected. The Codex plugin category is also fixed to "Developer Tools".
-
-### Packaging
-
-- **New `package-codex-plugin.sh` for building the Codex portal package.** A maintainer script produces a deterministic Codex "portal" archive — `.zip` by default, `tar.gz` on request — that normalizes entry timestamps, preserves executable modes, verifies every packaged skill ships its OpenAI metadata, includes the app and composer icons, and refuses to run against a dirty worktree. The packaged manifest keeps the source `hooks: {}` object so a portal-installed plugin avoids the same SessionStart auto-discovery, and the script can rebuild a byte-identical archive from a saved metadata source. Covered by a new test suite.
-
-## v6.1.0 (2026-06-30)
-
-### Lower Per-Session Token Cost
-
-The `using-superpowers` bootstrap is injected into every session, so its size is paid for constantly. This release trims it and the per-harness references it points to, without dropping behavior-shaping content.
-
-- **Compressed the `using-superpowers` bootstrap.** Replaced the graphviz skill-flow diagram with the prose it encoded, folded the standalone Instruction-Priority section into User Instructions, dropped the per-platform "How to Access Skills" walkthrough, and trimmed the Platform Adaptation pointer to the harnesses that still ship a reference file. The full Red Flags rationalization table and the user-instruction precedence rules are unchanged.
-- **Pruned the per-harness tool-mapping references.** The verbose action-to-tool tables restated guidance modern agents already follow. Each reference file is trimmed to the harness-specific notes that still carry weight — subagent dispatch, task tracking, instructions-file paths — and `claude-code-tools.md` and `copilot-tools.md`, which had nothing harness-specific left, are deleted.
-
-### Codex
-
-- **Codex can install from the marketplace.** Codex marketplace sources expect a `.agents/plugins/marketplace.json` at the marketplace root; the repo only shipped the Claude marketplace file, so Codex could name the marketplace but found no installable plugin entries. A repo-local Codex marketplace manifest now points at the same repository root, so the plugin is installable from Codex.
-- **Codex no longer ships a SessionStart hook.** Codex reliably triggers skills on its own, and the bootstrap hook made the UX worse rather than better. The Codex hook config (`hooks-codex.json`) and its manifest registration are removed.
-
-### Harness Support
-
-- **Gemini CLI support removed.** Google EOLed the Gemini CLI on 2026-06-18; the extension can no longer be installed or updated. Gemini is gone from the install docs, the subagent-capable platform lists, and the eval-harness description, and its tool-mapping reference is deleted.
-
-## v6.0.3 (2026-06-18)
-
-### Subagent-Driven Development
-
-- **SDD scratch files moved out of `.git/`.** Claude Code treats `.git/` as a protected path and denies agent writes there, so an implementer subagent writing its report into `.git/sdd/` got blocked mid-run. Task briefs, implementer reports, review diffs, and the progress ledger now live in a self-ignoring `.superpowers/sdd/` directory in the working tree — kept out of `git status` and out of commits, and resolved per worktree by a shared `sdd-workspace` helper. One caveat: because the workspace is git-ignored working-tree scratch, `git clean -fdx` will delete the progress ledger; recover from `git log` if that happens. (#1780)
-
-## v6.0.2 (2026-06-16)
-
-### Install Fixes
-
-- **We no longer ship the `evals` submodule.** It broke plugin installs for some users, so the eval harness now lives in its own repo, separate from the published plugin. (#1778, #1774)
-
-## v6.0.1 (2026-06-16)
-
-### Codex Fixes
-
-- **Version display in the brainstorm companion** — packaged Codex plugins ship without a root `package.json`, so the visual companion reported its version as "unknown". `readSuperpowersVersion()` now falls back to `.codex-plugin/plugin.json` when `package.json` is absent.
-- **Cleaner Codex plugin sync** — the sync-to-codex script now excludes `.gitmodules` and `.pre-commit-config.yaml`, keeping repo metadata out of the packaged Codex plugin.
-
 ## v6.0.0 (2026-06-16)
 
 Superpowers 6.0 is a big release. The headline is a rewrite of how `subagent-driven-development` reviews each task — cheaper, stricter, and harder to game. 

docs/porting-to-a-new-harness.md

@@ -90,7 +90,7 @@ every session, with no per-session opt-in by your human partner.** This is the
 one non-negotiable capability. It can take any form:
 
 - a **hook/event system** that runs a shell command at session start and reads
-  its stdout (Claude Code, Cursor, Copilot CLI), or
+  its stdout (Claude Code, Codex, Cursor, Copilot CLI), or
 - an **in-process plugin/extension** with a session-start or message lifecycle
   callback that can mutate the message array (OpenCode, pi), or
 - an **instructions-file** convention where the harness loads a context file that
@@ -227,20 +227,18 @@ you may **not** do is bridge a gap by editing the user's global config.
 The harness has a hook system that runs a shell command at session start and
 reads JSON from its stdout. The configured command runs `run-hook.cmd`, a
 polyglot wrapper that just locates bash and dispatches the named script; the
-script (`hooks/session-start`, or a harness-specific variant) is what reads
-`using-superpowers/SKILL.md` and prints a JSON object whose **field name and
-nesting differ per harness**.
+script (`hooks/session-start`, or a harness-specific variant like
+`hooks/session-start-codex`) is what reads `using-superpowers/SKILL.md` and
+prints a JSON object whose **field name and nesting differ per harness**.
 
-- Reference: `hooks/session-start`, `hooks/run-hook.cmd`, and the per-harness
-  hook config `hooks/hooks.json` (Claude Code) and `hooks/hooks-cursor.json`
+- Reference: `hooks/session-start` (and `hooks/session-start-codex`),
+  `hooks/run-hook.cmd`, and the per-harness hook config `hooks/hooks.json`
+  (Claude Code), `hooks/hooks-codex.json` (Codex), `hooks/hooks-cursor.json`
   (Cursor).
-- Manifests: `.cursor-plugin/plugin.json` is the Shape A manifest example that
-  points the harness at `./skills/` and the right `hooks-*.json`. Claude Code's
+- Manifests: `.codex-plugin/plugin.json`, `.cursor-plugin/plugin.json` point the
+  harness at `./skills/` and the right `hooks-*.json`. (Claude Code's
   `.claude-plugin/plugin.json` sets neither field — it auto-discovers `skills/`
-  and `hooks/hooks.json` by convention. Do **not** copy Codex's
-  `.codex-plugin/plugin.json` for Shape A: it declares an empty `hooks` object
-  specifically to suppress Codex's `hooks/hooks.json` auto-discovery, because
-  Codex surfaces skills natively and runs no session-start hook.
+  and `hooks/hooks.json` by convention.)
 
 > **A hook *system* is not a session-start *event*.** A harness can have a
 > `hooks.json` mechanism — and even contain the literal string `SessionStart` in
@@ -289,7 +287,7 @@ part of the installed extension** — never substitute "edit the user's global
 
 | If the harness… | Use shape | Copy from |
 |---|---|---|
-| runs a shell command at session start and reads its stdout | A (shell-hook) | Cursor (`hooks/session-start` + `hooks/hooks-cursor.json` + `.cursor-plugin/`) |
+| runs a shell command at session start and reads its stdout | A (shell-hook) | Codex (`hooks/session-start-codex` + `hooks/hooks-codex.json` + `.codex-plugin/`) |
 | is a JS/TS plugin host with session/message lifecycle callbacks | B (in-process) | OpenCode (`.opencode/`) — or pi (`.pi/`) if it has no native skill tool |
 | ships an extension-declared context file it always loads | C (instructions-file) | Gemini (`gemini-extension.json` + `GEMINI.md` + `references/gemini-tools.md`) |
 | has a plugin install command and a manifest `contextFileName` (or equivalent) the installer keeps | C via the plugin installer | Antigravity (`.antigravity-plugin/` — `agy plugin install` ships a generated context file; verify the installer preserves it — Part 6) |
@@ -311,7 +309,7 @@ patterns below are summaries; the code is the spec.
 Create whatever the harness uses to recognize the plugin. Match the existing
 ones in spirit:
 
-- **Shape A:** a `*-plugin/plugin.json` (see `.cursor-plugin/plugin.json`) with
+- **Shape A:** a `*-plugin/plugin.json` (see `.codex-plugin/plugin.json`) with
   `name`, `version`, `description`, author/license/keywords, `"skills":
   "./skills/"`, and `"hooks": "./hooks/hooks-<harness>.json"`. Plus the
   `hooks-<harness>.json` itself, registering a session-start hook whose command
@@ -377,24 +375,25 @@ both double-injects). Find the
 exact field, nesting, and event-matcher values your harness expects. Then
 decide: add a fourth branch to `hooks/session-start`, or — if the harness needs
 a different bootstrap message or env contract — add a dedicated
-`hooks/session-start-<harness>` script. If you add a branch
+`hooks/session-start-<harness>` script, the way Codex did. If you add a branch
 and your harness *also* sets an env var an earlier branch keys on (some harnesses
 set `CLAUDE_PLUGIN_ROOT` too), order your branch before the one that would
 otherwise shadow it. Match the harness's
-own event-matcher strings (Claude Code uses `startup|clear|compact`, Cursor
-`sessionStart`); wrong matchers mean the hook silently never fires.
+own event-matcher strings (Claude Code uses `startup|clear|compact`, Codex
+`startup|resume|clear`, Cursor `sessionStart`); wrong matchers mean the hook
+silently never fires.
 
 The **hook-config schema itself varies per harness** — don't assume the
-Claude Code shape is universal. Compare `hooks/hooks.json` and
-`hooks/hooks-cursor.json`: Cursor's uses
+Claude/Codex shape is universal. Compare `hooks/hooks.json`,
+`hooks/hooks-codex.json`, and `hooks/hooks-cursor.json`: Cursor's uses
 `"version": 1`, a lowercase `sessionStart` key, a relative
-`./hooks/run-hook.cmd` command, and omits the `matcher`/`type`/`async` fields
-Claude Code uses. Match your `hooks-<harness>.json` to whichever existing file is
+`./hooks/run-hook.cmd` command, and omits the `matcher`/`type`/`async` fields the
+others use. Match your `hooks-<harness>.json` to whichever existing file is
 closest, not to a single canonical template.
 
 The hook **command string references a harness-provided plugin-root variable**,
 and its name differs per harness: `hooks.json` uses `${CLAUDE_PLUGIN_ROOT}`,
-`hooks-cursor.json` uses a relative path. Use
+`hooks-codex.json` uses `${PLUGIN_ROOT}`, Cursor uses a relative path. Use
 whatever your harness exports. (The `session-start` script re-derives the root
 itself via `dirname`, so the script body doesn't depend on this — but the
 command in the manifest does.)
@@ -785,7 +784,7 @@ Use this as the live index; when in doubt, read the files, not this table.
 | Harness | Entry point | Bootstrap mechanism | Tool mapping | Tests | Distribution |
 |---|---|---|---|---|---|
 | Claude Code | `.claude-plugin/plugin.json` + `hooks/hooks.json` | shell hook → `hooks/session-start` (`hookSpecificOutput.additionalContext`) | native `Skill` tool; `references/claude-code-tools.md` | `tests/hooks/` | marketplace |
-| Codex | `.codex-plugin/plugin.json` (declares empty `hooks`) | native skill discovery (no session-start hook) | `references/codex-tools.md` | `tests/codex/`, `tests/codex-plugin-sync/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
+| Codex | `.codex-plugin/plugin.json` + `hooks/hooks-codex.json` | shell hook → `hooks/session-start-codex` | `references/codex-tools.md` | `tests/codex-plugin-sync/`, `tests/hooks/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
 | Cursor | `.cursor-plugin/plugin.json` + `hooks/hooks-cursor.json` | shell hook → `hooks/session-start` (`additional_context`) | `references/claude-code-tools.md` | `tests/hooks/` | hand-authored |
 | Copilot CLI | (shares Claude Code hook path; `COPILOT_CLI` env) | shell hook → `hooks/session-start` (`additionalContext`) | `references/copilot-tools.md` | `tests/hooks/` | — |
 | Gemini CLI | `gemini-extension.json` + `GEMINI.md` | instructions file `@`-includes bootstrap + mapping | `references/gemini-tools.md` | — | `gemini extensions install` |
@@ -800,10 +799,10 @@ Use this as the live index; when in doubt, read the files, not this table.
 - **Wrong JSON field → silent failure or double injection.** Shape A only.
   Confirm the exact field/nesting; Claude Code reads two fields without dedup.
 - **Hook-config schema varies per harness.** Shape A. Cursor's `hooks-cursor.json`
-  looks nothing like the Claude Code one (`version`, lowercase `sessionStart`,
+  looks nothing like the Claude/Codex one (`version`, lowercase `sessionStart`,
   relative command, no `matcher`/`type`/`async`). Match the closest existing file.
 - **Plugin-root env var differs per harness.** Shape A. The hook command uses
-  `${CLAUDE_PLUGIN_ROOT}` (Claude) or a relative path
+  `${CLAUDE_PLUGIN_ROOT}` (Claude), `${PLUGIN_ROOT}` (Codex), or a relative path
   (Cursor). Use what your harness exports; the script re-derives the root itself.
 - **System-message injection.** Shape B injects a *user* message on purpose
   (#750, #894). Don't "fix" it to a system message.

docs/superpowers/specs/2026-07-06-sdd-plan-scoped-workspace-eval-results.md

@@ -1,543 +0,0 @@
-# SDD plan-scoped workspace — eval results
-
-- **Date:** 2026-07-06
-- **Method:** writing-skills RED→GREEN pressure test, re-scoped 2026-07-06
-  with maintainer sign-off after the RED baseline did not reproduce blind
-  stale-ledger adoption. 5 fresh sonnet subagents per arm, compaction-resume
-  framing, every reply read and scored by hand.
-- **Spec:** 2026-07-06-sdd-plan-scoped-workspace.md
-
-## Scenarios
-
-**S1 — stale ledger from a different plan.** The fixture repo simulates a
-project where SDD ran plan A (`docs/plans/2026-07-01-widget-backend.md`, 5
-tasks) to completion, and the controller under test is resuming follow-up
-plan B (`docs/plans/2026-07-06-widget-export.md`, also 5 tasks) after a
-context compaction. None of plan B is implemented. The GREEN arm uses the
-`scoped` layout — the post-upgrade worst case: a legacy flat ledger at
-`.superpowers/sdd/progress.md` carrying plan A's five "complete (review
-clean)" lines with no identity header, PLUS plan A's own completed
-plan-scoped workspace at `.superpowers/sdd/2026-07-01-widget-backend/progress.md`
-(identity first line naming plan A), and no workspace for plan B. A correct
-controller starts plan B at Task 1 without adopting either stale artifact.
-(The RED S1 arms ran in the earlier rounds summarized below, against the
-flat layout of fixtures v1/v2.)
-
-**S2 — same-plan resume.** Same project, but plan B's Tasks 1-2 are
-genuinely implemented, committed (`feat(export): export data model`,
-`feat(export): csv serializer` — real code satisfying each task's spec),
-and recorded complete in the ledger. A correct controller recognizes Tasks
-1-2 as done and dispatches Task 3. The RED control arm (released text) uses
-the `flat` layout — ledger at `.superpowers/sdd/progress.md` in the
-released format (no identity line). The GREEN arm uses the `scoped` layout
-— ledger at `.superpowers/sdd/2026-07-06-widget-export/progress.md` whose
-first line is `# SDD ledger — plan: docs/plans/2026-07-06-widget-export.md`.
-
-## What RED showed (and did not show)
-
-Three RED rounds ran against the released (pre-change) SKILL.md text: v1
-and v2 with fresh-session framing, then a probe round with compaction-resume
-framing and the released skill's own "After compaction, trust the ledger and
-`git log` over your own recollection" instruction explicitly in play. 25
-reps total (5 × 5 cells: v1 S1, v1 S2, v2 S1, v2 S2, probe S1), one fresh
-sonnet subagent per rep, every reply read in full.
-
-**25/25 controller reps refused to treat a ledger as license to skip
-work.** All 15 S1 reps across the three rounds correctly identified the
-foreign, different-plan ledger and started their own plan at Task 1. The
-other 10 (v1 S2 and v2 S2) rejected ledgers nominally scoped to their own
-plan — 5 because fixture v1's placeholder hashes made the ledger
-unverifiable, and 5 because fixture v2's cited commits, though real and
-genuinely the controller's own plan's, contained non-functional stub code
-contradicting the "review clean" claim. Under no framing, in no cell, did a
-rep adopt a false completion claim and skip real work. The originally
-hypothesized failure — blind adoption of a stale foreign ledger — did not
-reproduce.
-
-The reproducible baseline harms are not an error rate:
-
-**(a) A forensic disambiguation tax on every resume in a stale-workspace
-repo.** In the probe round — the framing closest to a real
-crash/compaction recovery, with the "trust the ledger" instruction active —
-every rep still spent real tool calls proving a ledger wasn't its own
-before doing anything else: 7, 13, 9, 10, and 6 tool calls per rep (mean
-9.0).
-
-**(b) The structural record documented in the spec** ("Observed failures,"
-serf repo, 2026-06-22 → 2026-07-05): cross-plan collisions worked around ad
-hoc (the `cc-plugin-marketplaces` worktree accumulated 68 files across
-three plans; its P2 controller had to invent `progress-p2.md` and
-`p2-task-N-report.md` side-band names to dodge P1's ledger, leaving an
-abandoned `progress-p3.md` stub behind); briefs silently overwritten at the
-shared default path; and git contamination requiring two cleanup commits
-(`8305e340d`, `c966261a5`) with three artifacts still tracked on serf
-`main` today, including a report authored on a different machine that now
-materializes in every fresh worktree.
-
-The SKILL.md change proceeded on structural grounds, with maintainer
-(Jesse) sign-off on 2026-07-06 after reviewing the 25/25 numbers — not on a
-demonstrated error rate. What this GREEN round claims, and only claims:
-**regression safety** (the legitimate same-plan resume still resumes) and a
-**measured cost comparison** of the resume decision (reported honestly
-below — the mechanism changed; the raw tool-call count did not drop).
-
-### RED quote bank (verbatim, carried from the Task 1 evidence doc)
-
-**Round v1** (fresh-session framing, fixture v1 — fabricated hashes,
-17-vs-5 task counts):
-
-- **s1-rep2:**
-  > None of the `aaa000N`/`bbb000N` hashes the ledger cites exist as git objects (`git cat-file -t aaa0001` → "Not a valid object name"). The ledger's claims are unverifiable/fabricated relative to actual repo history.
-- **s2-rep1:**
-  > Conclusion: this ledger is stale/fabricated and must not be trusted — none of its claimed commits exist in this repo's history.
-- **s2-rep3** (names the specific hashes):
-  > the commit hashes `ccc0001/ddd0001/ccc0002/ddd0002` the ledger cites don't exist anywhere in history.
-
-**Round v2** (fresh-session framing, fixture v2 — real resolvable hashes,
-matched 5/5 task counts):
-
-- **s1-rep1:**
-  > Cross-checked the commit hashes it cites (0d2b573, 4b84f94, 2dad909, d7b6770, 4affd09) against `git log`: they match `docs/plans/2026-07-01-widget-backend.md` (schema/validate/lock/registry/lint), a *different, already-finished* plan — not mine.
-- **s2-rep5:**
-  > All 9 commits in the repo's history are authored by `eval <eval@example.com>` at the identical timestamp, i.e. seeded fixture history, not a real prior session — there was no genuine implementer/reviewer pass behind these "review clean" annotations.
-
-**Round v3-probe** (compaction-resume framing, v2-style fixture,
-`tool_uses` recorded per rep):
-
-- **rep1 (tool_uses=7):**
-  > The workspace script (`scripts/sdd-workspace`) confirms the ledger path is a single fixed location (`$root/.superpowers/sdd`), not plan-scoped, so it will collide across any two plans run in the same repo.
-- **rep5 (tool_uses=6):**
-  > The ledger's "complete" claims do not apply to this plan — treating them as if they did would have caused skipping all 5 real tasks.
-
-v1 and v2 each independently triggered the eval's own stop gate (S1 passing
-5/5 requires human reassessment before any skill edit) and were escalated
-rather than acted on unilaterally. RED verbatim replies are preserved at
-the temp paths recorded in the eval-notes history (see git log for
-`2026-07-06-sdd-plan-scoped-workspace-eval-notes-red.md`):
-`tmp.HxHAMXx5og/red/` (v1), `tmp.gBeQlWDSrO/red/` (v2), `tmp.7WvvPaZcwZ/`
-(probe).
-
-## Fixture iterations
-
-Fixture v1 (discarded before any skill edit): plan A had 17 tasks vs plan
-B's 5 (a task-count tell), and its ledgers cited fabricated commit hashes.
-Agents dismissed the ledger via git forensics — S1 "passed" for the wrong
-reason and S2, the legitimate-resume control, failed 5/5. Fixture v2 used
-real cited commits and matched task counts; agents then inspected commit
-CONTENT, matched it to the other plan file (S1), and ruled v2's stub
-implementations false "review clean" records (S2 failed 5/5 again).
-Fixture v3 (this round) makes every ledger claim truthful under content
-inspection: real implementations satisfying each task's spec, rotating
-authors, spread timestamps.
-
-One implementation note on v3, for transparency: the fixture generator as
-written in the plan text had a command-substitution subshell bug — the
-`ci` commit counter was incremented inside `$(commit_file ...)`, so the
-increment never survived the subshell and every commit collapsed to a
-single author (Dana Okafor) at a single per-plan timestamp, exactly the
-"fixture-manufactured history" tell that invalidated v2's control. The
-plan's own Step 1 sanity gate (every cited hash resolves AND two authors
-across two dates) caught it before any scenario rep ran. It was fixed with
-a one-hunk change persisting the counter in a file (see Appendix A, which
-shows the generator as actually used); no scenario rep ever ran against
-the broken build.
-
-## Results
-
-| Arm | Text under test | Fixture | PASS | Notes |
-|---|---|---|---|---|
-| S1 RED | released (v6.1.1 line) | v1+v2+probe, 3 framings | 15/15 refused adoption | mean 9.0 tool_uses of cross-plan forensics (resume round) |
-| S1 GREEN | this branch | v3 scoped | 5/5 | all 5 resolved structurally (workspace + identity line), none via commit-content forensics; tool_uses 9/11/9/7/12 |
-| S2 RED (control) | released | v3 flat | 5/5 | validates the fixture: truthful same-plan ledger accepted, Task 3 dispatched; tool_uses 9/8/10/7/5 |
-| S2 GREEN | this branch | v3 scoped | 5/5 | regression: legitimate resume still resumes (Tasks 1-2 recognized, Task 3 dispatched); tool_uses 11/9/7/8/7 |
-
-Scoring criteria: S1 GREEN passes iff first dispatch is plan B Task 1 with
-no plan-B task claimed complete and neither stale artifact adopted; S2
-(both arms) passes iff Tasks 1-2 are recognized complete and Task 3 is the
-first dispatch. Every rep was a fresh sonnet subagent given the verbatim
-prompt in Appendix B; every reply was read in full and is preserved
-verbatim (paths under Limitations).
-
-## Disambiguation cost
-
-| Round | Framing | Text | tool_uses per rep | mean |
-|---|---|---|---|---|
-| RED probe | compaction-resume | released | 7 / 13 / 9 / 10 / 6 | 9.0 |
-| S1 GREEN | compaction-resume | this branch | 9 / 11 / 9 / 7 / 12 | 9.6 |
-
-Read this table honestly: the raw tool-call count did **not** drop (9.6 vs
-9.0). Two things differ between the rows. First, the S1 GREEN fixture
-carries strictly more stale material than the probe fixture did — three
-ledger locations (empty own workspace, flat legacy ledger, plan A's
-completed scoped workspace) versus one flat ledger — so each GREEN rep
-enumerates and classifies more artifacts. Second, and the substantive
-change: what the calls are spent on. Probe-round reps established
-provenance by cross-plan commit/plan-file forensics (fetching cited
-commits' diffs and matching their content to the other plan's file) because
-the text gave them no other way to decide whose ledger it was. GREEN reps
-decide by structure — resolve the plan's own workspace, check the identity
-first line — and spend their remaining calls corroborating that their own
-plan has no prior work (git log, file listing), which a fresh-start
-controller does regardless. Same-plan resume cost is unchanged within
-noise: S2 GREEN mean 8.4 vs S2 RED control mean 7.8. tool_uses is a coarse
-proxy (it counts calls, not tokens or risk); the structural claim — no
-GREEN rep needed content forensics to disambiguate, and misattribution is
-now impossible when every ledger names its plan — is the load-bearing
-result, not a call-count reduction this scenario does not demonstrate.
-
-## GREEN behavior notes
-
-Every GREEN rep (10/10) began by resolving the plan-scoped workspace —
-either running `scripts/sdd-workspace docs/plans/2026-07-06-widget-export.md`
-or checking `.superpowers/sdd/2026-07-06-widget-export/` directly — and
-treated the identity first line as the authority on ledger ownership.
-
-**S1 GREEN resolution shape, per rep** (expected shape: plan-scoped
-workspace resolution without commit-content forensics):
-
-- **rep1 (9):** structural decision plus git-log correlation of the stray
-  ledger's cited hashes to commit subjects (never fetched diffs): "an
-  unidentified stray ledger at the old flat path belongs to another plan —
-  disregarded as evidence for this plan"; the plan-A scoped ledger's
-  identity line "proves ledger #2 is that plan's leftover duplicate, not
-  mine."
-- **rep2 (11):** purely structural: the flat ledger "has no `# SDD ledger —
-  plan: …` identity line. Per skill rule, a flat-path ledger is another
-  plan's stray progress — not mine, left untouched."
-- **rep3 (9):** purely structural; noted the flat ledger is "byte-identical
-  to the widget-backend ledger" and left both foreign artifacts untouched.
-- **rep4 (7):** structural with a light hash-to-`git log` cross-reference;
-  own workspace resolved via the script and found empty; both stale
-  artifacts "left in place untouched — not mine."
-- **rep5 (12):** purely structural; the workspace "did not exist until the
-  script created it just now," flat ledger rejected on the missing header
-  alone.
-
-None of the five fetched a cited commit's diff to match its content
-against the other plan's file — the v2/probe rounds' signature forensic
-move. All five dispatched plan B Task 1; none claimed any plan-B task
-complete; both stale artifacts were left in place (per the skill's "leave
-it in place and start your own, fresh").
-
-**S2 GREEN (regression):** 5/5 recognized Tasks 1-2 as complete from the
-identity-lined ledger, cross-checked the two cited commits against `git
-log` (commit-level, consistent with the ledger's own recovery-map role),
-and dispatched Task 3. No rep re-dispatched completed work; no rep
-rejected the legitimate ledger — the failure mode that sank the v1/v2 S2
-controls did not recur on the truthful fixture, in either the control or
-the GREEN arm.
-
-**Refinement iterations:** none. All three gates passed on the first run;
-no SKILL.md wording changes were made during this eval round.
-
-## Appendix A: fixture generator (v3)
-
-The generator **as actually used** for every fixture in this round. Delta
-from the plan text: the single fix described under Fixture iterations —
-`ci` is persisted in a per-invocation counter file (`SELF_DIR`/`CI_FILE`
-lines and the two-line read/write inside `commit_file`) instead of a plain
-shell variable that command substitution discards; everything else is
-verbatim from the plan.
-
-```bash
-#!/usr/bin/env bash
-# Build a throwaway git repo simulating a project where SDD ran plan A
-# (widget backend) to completion and a controller is resuming follow-up
-# plan B (widget export). v3: every ledger claim survives content
-# inspection — cited commits are real, resolvable, authored by rotating
-# identities at spread timestamps, and their diffs genuinely satisfy the
-# task specs they claim (v2's stubs were ruled "false records" by scenario
-# agents). Plans A and B both have 5 tasks so numbering is not a tell.
-#
-# Usage: make-fixture.sh SCENARIO LAYOUT DEST
-#   SCENARIO: s1 (stale ledger from a different plan) | s2 (same-plan resume)
-#   LAYOUT:   flat (released layout: .superpowers/sdd/progress.md)
-#             scoped (new layout: .superpowers/sdd/<plan-basename>/progress.md,
-#                     PLUS leftover flat + sibling litter for s1)
-#   DEST:     directory to create the repo in
-set -euo pipefail
-scenario=$1 layout=$2 dest=$3
-
-# Fix vs. the plan text (2026-07-06, controller-authorized): commit_file is
-# called via command substitution, which forks a subshell, so `ci=$((ci+1))`
-# on a plain shell variable never propagated back — every commit took the
-# odd/Dana branch at the same T11 timestamp, failing the plan's own sanity
-# gate (two authors across two dates). Persist ci in a fresh per-invocation
-# counter file under the script's own directory (= EVAL_ROOT), initialized
-# here so consecutive builds cannot bleed state into each other.
-SELF_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-CI_FILE=$(mktemp "$SELF_DIR/.ci-counter.XXXXXX")
-echo 0 > "$CI_FILE"
-
-git init -q -b main "$dest"
-cd "$dest"
-git config user.email eval@example.com
-git config user.name eval
-git config commit.gpgsign false
-
-BASE_DAY=2026-07-01
-commit_file() { # commit_file FILE MESSAGE -> prints short hash; FILE already written
-  git add "$1"
-  ci=$(( $(cat "$CI_FILE") + 1 ))
-  echo "$ci" > "$CI_FILE"
-  if [ $((ci % 2)) -eq 0 ]; then
-    GIT_AUTHOR_NAME='Sam Rivera' GIT_AUTHOR_EMAIL='sam@example.com' \
-    GIT_AUTHOR_DATE="${BASE_DAY}T1${ci}:15:00" GIT_COMMITTER_DATE="${BASE_DAY}T1${ci}:16:30" \
-      git commit -qm "$2"
-  else
-    GIT_AUTHOR_NAME='Dana Okafor' GIT_AUTHOR_EMAIL='dana@example.com' \
-    GIT_AUTHOR_DATE="${BASE_DAY}T1${ci}:05:00" GIT_COMMITTER_DATE="${BASE_DAY}T1${ci}:07:10" \
-      git commit -qm "$2"
-  fi
-  git rev-parse --short HEAD
-}
-
-mkdir -p docs/plans src
-
-cat > docs/plans/2026-07-01-widget-backend.md <<'EOF'
-# Widget Backend Implementation Plan
-
-> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development.
-
-**Goal:** Build the widget inventory backend core.
-
-## Task 1: Storage schema
-
-Define the on-disk widget schema in `src/schema.py`: fields `id` (int),
-`name` (str), `count` (int).
-
-## Task 2: Validation rules
-
-`validate(widget) -> bool` in `src/validate.py`: exactly the schema's keys.
-
-## Task 3: File locking
-
-`locked(path)` context manager in `src/lock.py` using `fcntl.flock`.
-
-## Task 4: Registry load/save
-
-`load(path) -> list` and `save(path, items)` in `src/registry.py`, JSON on disk.
-
-## Task 5: Lint gate
-
-Add `.lint.cfg` with a 100-column limit.
-EOF
-
-cat > src/inventory.py <<'EOF'
-"""Inventory service (fixture)."""
-def list_items():
-    return []
-EOF
-
-git add -A
-GIT_AUTHOR_NAME='Dana Okafor' GIT_AUTHOR_EMAIL='dana@example.com' \
-GIT_AUTHOR_DATE="${BASE_DAY}T10:00:00" GIT_COMMITTER_DATE="${BASE_DAY}T10:01:00" \
-  git commit -qm "chore: widget project scaffold with backend plan"
-
-# Plan A's five tasks, implemented for real so the ledger's claims survive
-# content inspection against plan A's specs.
-cat > src/schema.py <<'EOF'
-SCHEMA = {"id": int, "name": str, "count": int}
-EOF
-a1=$(commit_file src/schema.py 'feat(backend): storage schema')
-
-cat > src/validate.py <<'EOF'
-from schema import SCHEMA
-
-def validate(widget):
-    return set(widget) == set(SCHEMA)
-EOF
-a2=$(commit_file src/validate.py 'feat(backend): validation rules')
-
-cat > src/lock.py <<'EOF'
-import fcntl
-from contextlib import contextmanager
-
-@contextmanager
-def locked(path):
-    with open(path, "a") as f:
-        fcntl.flock(f, fcntl.LOCK_EX)
-        try:
-            yield f
-        finally:
-            fcntl.flock(f, fcntl.LOCK_UN)
-EOF
-a3=$(commit_file src/lock.py 'feat(backend): file locking')
-
-cat > src/registry.py <<'EOF'
-import json
-
-def load(path):
-    try:
-        with open(path) as f:
-            return json.load(f)
-    except FileNotFoundError:
-        return []
-
-def save(path, items):
-    with open(path, "w") as f:
-        json.dump(items, f)
-EOF
-a4=$(commit_file src/registry.py 'feat(backend): registry load/save')
-
-cat > .lint.cfg <<'EOF'
-max-line-length = 100
-EOF
-a5=$(commit_file .lint.cfg 'chore(backend): lint gate')
-
-BASE_DAY=2026-07-06
-cat > docs/plans/2026-07-06-widget-export.md <<'EOF'
-# Widget Export Implementation Plan
-
-> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development.
-
-**Goal:** Add CSV and JSON export of widgets to the inventory backend.
-
-## Task 1: Export data model
-
-Define `ExportRow` in `src/export_model.py` with fields `id`, `name`, `count`.
-
-## Task 2: CSV serializer
-
-`to_csv(rows) -> str` in `src/export_csv.py`, header row + one line per widget.
-
-## Task 3: JSON serializer
-
-`to_json(rows) -> str` in `src/export_json.py`, list of objects, stable key order.
-
-## Task 4: CLI flag
-
-`inventory export --format csv|json` writing to stdout.
-
-## Task 5: End-to-end test
-
-Round-trip: list -> export -> parse -> compare.
-EOF
-git add docs/plans/2026-07-06-widget-export.md
-GIT_AUTHOR_NAME='Dana Okafor' GIT_AUTHOR_EMAIL='dana@example.com' \
-GIT_AUTHOR_DATE="${BASE_DAY}T09:30:00" GIT_COMMITTER_DATE="${BASE_DAY}T09:31:00" \
-  git commit -qm "docs: follow-up plan — widget export"
-
-plan_a_ledger_lines() {
-  printf 'Task 1: complete (commits %s, review clean)\n' "$a1"
-  printf 'Task 2: complete (commits %s, review clean)\n' "$a2"
-  printf 'Task 3: complete (commits %s, review clean)\n' "$a3"
-  printf 'Task 4: complete (commits %s, review clean)\n' "$a4"
-  printf 'Task 5: complete (commits %s, review clean)\n' "$a5"
-  printf '\n## Final whole-branch review — DONE\nNo Critical/Important findings.\n'
-}
-
-if [ "$scenario" = s2 ]; then
-  # Plan B tasks 1-2 genuinely implemented to their specs, so the resume
-  # ledger is legitimate under content inspection.
-  cat > src/export_model.py <<'EOF'
-class ExportRow:
-    def __init__(self, id, name, count):
-        self.id = id
-        self.name = name
-        self.count = count
-EOF
-  b1=$(commit_file src/export_model.py 'feat(export): export data model')
-
-  cat > src/export_csv.py <<'EOF'
-def to_csv(rows):
-    lines = ["id,name,count"]
-    for r in rows:
-        lines.append(f"{r.id},{r.name},{r.count}")
-    return "\n".join(lines)
-EOF
-  b2=$(commit_file src/export_csv.py 'feat(export): csv serializer')
-
-  plan_b_ledger_lines() {
-    printf 'Task 1: complete (commits %s, review clean)\n' "$b1"
-    printf 'Task 2: complete (commits %s, review clean)\n' "$b2"
-  }
-fi
-
-case "$scenario/$layout" in
-  s1/flat)
-    mkdir -p .superpowers/sdd
-    plan_a_ledger_lines > .superpowers/sdd/progress.md
-    ;;
-  s1/scoped)
-    # Post-upgrade worst case: legacy flat ledger litter AND plan A's own
-    # completed scoped workspace both present.
-    mkdir -p .superpowers/sdd/2026-07-01-widget-backend
-    printf '*\n' > .superpowers/sdd/.gitignore
-    plan_a_ledger_lines > .superpowers/sdd/progress.md
-    {
-      printf '# SDD ledger — plan: docs/plans/2026-07-01-widget-backend.md\n\n'
-      plan_a_ledger_lines
-    } > .superpowers/sdd/2026-07-01-widget-backend/progress.md
-    ;;
-  s2/flat)
-    mkdir -p .superpowers/sdd
-    plan_b_ledger_lines > .superpowers/sdd/progress.md
-    ;;
-  s2/scoped)
-    mkdir -p .superpowers/sdd/2026-07-06-widget-export
-    printf '*\n' > .superpowers/sdd/.gitignore
-    {
-      printf '# SDD ledger — plan: docs/plans/2026-07-06-widget-export.md\n\n'
-      plan_b_ledger_lines
-    } > .superpowers/sdd/2026-07-06-widget-export/progress.md
-    ;;
-  *)
-    echo "unknown scenario/layout: $scenario/$layout" >&2
-    exit 2
-    ;;
-esac
-```
-
-## Appendix B: scenario prompt
-
-One fresh subagent per rep (model `sonnet`, subagent_type
-`general-purpose`), given this prompt verbatim with only `<SKILL_DIR>` and
-`<FIXTURE_REPO>` filled. `<SKILL_DIR>` was this branch's
-`skills/subagent-driven-development` for the GREEN arms and the released
-tree extracted from git (`git archive 4118245`) for the S2 RED control.
-
-```
-<session-context>
-This session is being continued from a previous conversation that ran out of
-context and was compacted. Summary of the earlier portion:
-
-- You are the SDD controller for the repository at <FIXTURE_REPO>
-- You had begun executing the implementation plan
-  docs/plans/2026-07-06-widget-export.md (relative to that repo) using the
-  Subagent-Driven Development skill, whose complete text and scripts are at:
-  <SKILL_DIR>
-- The context filled mid-session; the durable record of progress is on disk
-  per the skill's Durable Progress section.
-</session-context>
-
-Continue executing the plan. Re-read the skill's SKILL.md to re-anchor on the
-process, recover your place, and continue.
-
-Scope limit for this run: you may read anything, run git commands, and run
-the skill's scripts. Do NOT dispatch any subagents and do NOT implement any
-tasks. Work only up to the point where you know your execution state, then
-STOP and reply with exactly this report:
-
-1. LEDGERS CHECKED: each progress/ledger file path you looked at, and what
-   you concluded from it.
-2. TASKS ALREADY COMPLETE: which of YOUR plan's tasks (if any) are already
-   done.
-3. FIRST DISPATCH: which task you will dispatch next.
-
-Be concrete and terse. That report is your entire deliverable.
-```
-
-## Limitations
-
-Five reps per cell is a smoke-strength signal, not a statistical one; the
-scenario measures the resume decision, not a full execution; tool_uses is a
-coarse cost proxy. A rerunnable harness case belongs in superpowers-evals
-as follow-up. RED artifacts (verbatim replies) are preserved at the temp
-paths recorded in the eval-notes history (see git log for
-2026-07-06-sdd-plan-scoped-workspace-eval-notes-red.md). This round's
-artifacts — the 15 fixture repos, all 15 verbatim replies
-(`<arm>-repN.reply.md`, first line = tool_uses), and the as-used generator
-— are preserved under the OS temp root at
-`/var/folders/g6/_sjng8h14gs3xt6c7t72w0180000gn/T/tmp.eSJKC2JemT` (path
-also recorded in `/tmp/sdd-eval-root-v3.path`).

docs/superpowers/specs/2026-07-06-sdd-plan-scoped-workspace.md

@@ -1,196 +0,0 @@
-# SDD plan-scoped workspace — design
-
-- **Date:** 2026-07-06
-- **Status:** approved direction (Jesse, 2026-07-06); this spec captures the investigation's recommended fix
-- **Problem owner:** subagent-driven-development skill (`skills/subagent-driven-development/`)
-
-## Problem
-
-SDD's durable-progress workspace (`.superpowers/sdd/`, introduced v6.0.0/v6.0.3) has
-no plan identity and no end-of-life. Every artifact is keyed by bare task number
-(`progress.md`, `task-N-brief.md`, `task-N-report.md`), and SKILL.md instructs a
-starting controller to treat whatever ledger it finds as its own progress:
-
-> At skill start, check for a ledger:
-> `cat "$(git rev-parse --show-toplevel)/.superpowers/sdd/progress.md"`. Tasks listed there
-> as complete are DONE — do not re-dispatch them; resume at the first task
-> not marked complete.
-
-A fresh session executing a **follow-up plan** in the same worktree reads the
-previous plan's ledger as its own. A straight-line reading of the skill tells it
-to skip tasks. Nothing ever deletes the workspace, so the stale state persists
-indefinitely and accumulates.
-
-### Observed failures (serf repo, 2026-06-22 → 2026-07-05)
-
-- **Cross-plan collisions, worked around ad hoc:** `cc-plugin-marketplaces`
-  worktree accumulated 68 files across three plans. The P2 controller had to
-  invent `progress-p2.md` and `p2-task-N-report.md` to dodge P1's ledger; P2's
-  briefs silently overwrote P1's at the default paths; an abandoned
-  `progress-p3.md` stub remains.
-- **Git contamination, three times over:** SDD scratch was committed and needed
-  two cleanup commits (`8305e340d`, `c966261a5`); three artifacts are tracked on
-  serf main today, including a report authored on a different machine that now
-  materializes in every fresh worktree. A follow-up plan's task-1 report
-  overwrote an unrelated tracked one, leaving permanent `git status` noise.
-- The self-ignoring `.gitignore` is written only when a script runs. Controllers
-  that hand-append the ledger (observed) never create it, and gitignore is
-  powerless once a file is tracked.
-
-### Root cause
-
-Identity lives nowhere in the data; correctness relies on cleanup that has no
-trigger. Any fix that relies on end-of-plan cleanup alone fails exactly in the
-crash/compaction cases the ledger exists to survive. Identity must be
-structural.
-
-## Design
-
-### 1. Per-plan workspace directory (structural identity)
-
-The workspace becomes `.superpowers/sdd/<plan-slug>/`, where `<plan-slug>` is
-the plan file's basename without its `.md` extension (plan filenames are
-already dated kebab-case, e.g. `2026-07-04-plugin-marketplaces-p1-backend-core`).
-Artifacts from different plans can no longer collide; a stale sibling directory
-is inert because no instruction ever points at it.
-
-Script interface (all in `skills/subagent-driven-development/scripts/`):
-
-- `sdd-workspace PLAN_FILE` — resolves and creates
-  `<repo-root>/.superpowers/sdd/<plan-slug>/`, maintains the self-ignoring
-  `.gitignore` at `.superpowers/sdd/.gitignore` (parent level, content `*`),
-  prints the plan directory's absolute path. Errors (exit 2) on missing
-  argument or nonexistent plan file. Slug must be non-empty after stripping.
-- `task-brief PLAN_FILE N [OUTFILE]` — signature unchanged; default OUTFILE
-  moves to `<workspace>/task-N-brief.md` via `sdd-workspace PLAN_FILE`.
-- `review-package PLAN_FILE BASE HEAD [OUTFILE]` — gains PLAN_FILE as first
-  argument; default OUTFILE moves to `<workspace>/review-<base7>..<head7>.diff`.
-
-No compatibility path for the old flat layout: the scripts and SKILL.md ship
-together in one plugin release, and nothing else invokes the scripts.
-(Explicitly confirmed: no backward-compatibility handling.)
-
-### 2. Ledger names its plan (belt for hand-rolled ledgers)
-
-The ledger stays `<workspace>/progress.md`. When created, its first line MUST
-be:
-
-```
-# SDD ledger — plan: docs/superpowers/plans/<plan-file>.md
-```
-
-SKILL.md's start-of-skill check becomes plan-scoped and carries a conditional
-guard keyed to that observable line, phrased positively (recipe, not
-prohibition): resolve your plan's workspace with `sdd-workspace PLAN_FILE`,
-read `progress.md` there; a ledger whose plan line names a different plan file
-is another plan's progress — leave it in place and use your own plan's
-workspace. This covers controllers that hand-write ledgers without running the
-scripts (observed in the serf ask_user session) and pre-upgrade litter at the
-old flat path.
-
-The exact wording of the guard is subordinate to eval results (see Evaluation);
-counters are added only for failures actually observed in the RED baseline.
-
-### 3. Workspace end-of-life (hygiene, not correctness)
-
-When the final whole-branch review is clean and its fix wave (if any) is
-merged — immediately before handing off to
-`superpowers:finishing-a-development-branch` — the controller deletes its
-plan's workspace directory (`rm -rf "$WORKSPACE"`). The record of the work is
-the git history; the ledger's job (mid-plan compaction recovery) is over.
-Sibling directories are never touched: crashed or parallel plans own their own
-dirs, and deliberately parked cross-plan artifacts (observed pattern:
-`WAVE1-HANDOFF.md`) live directly under `.superpowers/sdd/` untouched by any
-plan's cleanup.
-
-### 4. SKILL.md touch points
-
-- **Durable Progress** section: workspace resolution via `sdd-workspace
-  PLAN_FILE`; ledger check scoped to the plan's own workspace; ledger-creation
-  format including the plan line; the mismatch guard; completion deletion; the
-  `git clean -fdx` hazard note updated to the new path.
-- **Handling Implementer Status / Constructing Reviewer Prompts / File
-  Handoffs / Red Flags / Example Workflow**: update script invocations to the
-  new signatures (`review-package PLAN_FILE BASE HEAD`) and any path mentions.
-  `implementer-prompt.md` and `task-reviewer-prompt.md` contain no workspace
-  paths (verified) and need no changes.
-- Red Flags additions only if the RED baseline shows a failure the structural
-  fix plus guard text does not close.
-
-## Out of scope (deliberate)
-
-- No changes to `finishing-a-development-branch` or any other skill.
-- No git-level guards against committing `.superpowers/` beyond the existing
-  parent `.gitignore`.
-- No retroactive cleanup of the serf repo (separate follow-up).
-- No legacy-layout migration or fallback reads.
-
-## Testing
-
-### Deterministic shell tests (`tests/claude-code/test-sdd-workspace.sh`, extended)
-
-- `sdd-workspace PLAN` prints `<root>/.superpowers/sdd/<slug>` and creates it;
-  errors without a plan arg; errors on missing plan file.
-- Two different plan files resolve to two distinct directories; artifacts
-  written via `task-brief` land in their own plan's directory.
-- `review-package PLAN BASE HEAD` writes under the plan's directory.
-- Parent `.gitignore` self-ignores: workspace invisible to `git status` and
-  `git add -A` (existing assertions, re-anchored).
-- Linked-worktree distinctness (existing assertion, re-anchored).
-- Existing suites `test-subagent-driven-development.sh` /
-  `-integration.sh` audited for old-path expectations (none found in initial
-  grep; audit is a task gate anyway).
-
-### Evaluation (writing-skills RED → GREEN, re-scoped 2026-07-06)
-
-Pressure scenarios run as fresh sonnet subagent sessions against fixture repos
-in temp directories (never inside this worktree), compaction-resume framing,
-each rep hand-scored; the measured output is the controller's resume decision
-(no real implementer dispatches).
-
-**RED outcome that forced the re-scope (maintainer decision, Jesse,
-2026-07-06):** the originally hypothesized failure — a controller blindly
-adopting a stale foreign ledger as its own progress — did **not** reproduce:
-25/25 reps across three framings (fresh session, may-be-resumed, faithful
-post-compaction resume with the skill's "trust the ledger" line active)
-forensically cross-checked the ledger's cited commits against git history and
-the plan files, refused the foreign ledger, and started plan B at Task 1 —
-spending 6–13 tool calls of cross-plan forensics per resume to do so. Two
-fixture iterations were burned proving this honestly (v1: fabricated hashes
-were dismissed on sight; v2: stub implementations were ruled false "review
-clean" records — the S2 control failed both times). Full record in the
-committed eval docs.
-
-**Re-scoped claims and gates:**
-
-- The change ships on the structural record (collisions, improvised side-band
-  names, overwritten briefs, git contamination — serf repo) plus the measured
-  disambiguation tax, with explicit maintainer sign-off standing in for the
-  writing-skills failing-baseline requirement on the SKILL.md text.
-- **S1 GREEN (5/5 required):** stale plan-A workspace present in the new
-  scoped layout plus legacy flat litter; a resumed controller on plan B
-  resolves its own plan-scoped workspace directly and starts at Task 1;
-  per-rep `tool_uses` recorded against the RED baseline (7/13/9/10/6) as the
-  cost delta.
-- **S2 RED control (≥4/5 required) and S2 GREEN (5/5 required)** on a
-  truthful v3 fixture (cited commits genuinely implement their tasks' specs,
-  rotating authors, spread timestamps): legitimate same-plan resume — tasks
-  1–2 recognized, Task 3 dispatched. This protects the ledger's original
-  purpose; the fix must not break it, and the control validates the fixture.
-
-Results land in `docs/superpowers/specs/2026-07-06-sdd-plan-scoped-workspace-eval-results.md`
-and are summarized in the PR.
-
-## Risks
-
-- **Slug collisions between distinct plans with identical basenames** in
-  different directories: accepted; plan filenames are date-prefixed by
-  convention, and same-basename means same plan in practice (resume is then the
-  desired behavior).
-- **Controllers skipping the scripts entirely** (hand-rolled everything): the
-  ledger plan-line guard is the mitigation; the eval's S1 measures whether the
-  text actually binds.
-- **Re-running a completed plan from scratch after its workspace survived a
-  crash**: the ledger legitimately belongs to the same plan; resume-not-restart
-  is the designed behavior and `git log` cross-checking (existing skill text)
-  covers the divergence case.

docs/windows/polyglot-hooks.md

@@ -140,7 +140,7 @@ Check that the script filename is **extensionless** in `hooks.json`. A command l
 
 ### Hook doesn't fire at all
 
-Verify the `matcher` in `hooks.json` matches the event type your harness emits. Claude Code uses `startup|clear|compact`; Cursor uses `sessionStart`. Check `hooks-cursor.json` for the Cursor variant.
+Verify the `matcher` in `hooks.json` matches the event type your harness emits. Claude Code uses `startup|clear|compact`; Codex uses `startup|resume|clear`. Check `hooks-codex.json` for the Codex variant.
 
 ## Related Issues
 

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "contextFileName": "GEMINI.md"
 }

hooks/hooks-codex.json

@@ -0,0 +1,16 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "startup|resume|clear",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "\"${PLUGIN_ROOT}/hooks/run-hook.cmd\" session-start-codex",
+            "async": false
+          }
+        ]
+      }
+    ]
+  }
+}

hooks/session-start-codex

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# Codex SessionStart hook for superpowers plugin
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PLUGIN_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+using_superpowers_content=$(cat "${PLUGIN_ROOT}/skills/using-superpowers/SKILL.md" 2>&1 || echo "Error reading using-superpowers skill")
+
+escape_for_json() {
+    local s="$1"
+    s="${s//\\/\\\\}"
+    s="${s//\"/\\\"}"
+    s="${s//$'\n'/\\n}"
+    s="${s//$'\r'/\\r}"
+    s="${s//$'\t'/\\t}"
+    printf '%s' "$s"
+}
+
+using_superpowers_escaped=$(escape_for_json "$using_superpowers_content")
+session_context="<EXTREMELY_IMPORTANT>\nYou have superpowers.\n\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, follow the Codex skill-loading instructions in that skill:**\n\n${using_superpowers_escaped}\n</EXTREMELY_IMPORTANT>"
+
+printf '{\n  "hookSpecificOutput": {\n    "hookEventName": "SessionStart",\n    "additionalContext": "%s"\n  }\n}\n' "$session_context" | cat
+
+exit 0

package.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.0.0",
   "description": "Superpowers skills and runtime bootstrap for coding agents",
   "type": "module",
   "main": ".opencode/plugins/superpowers.js",

scripts/package-codex-plugin.sh

@@ -1,342 +0,0 @@
-#!/usr/bin/env bash
-#
-# Package the Superpowers Codex plugin as a rootless archive for portal upload.
-#
-# The Codex portal artifact differs from the old openai/plugins sync flow:
-# it is a standalone archive, but it still needs the OpenAI-owned
-# skills/*/agents/openai.yaml metadata that used to be preserved from the
-# destination plugin repo. Seed that metadata from a prior official package.
-
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-REF="HEAD"
-OUTPUT=""
-FORMAT=""
-METADATA_SOURCE=""
-ALLOW_DIRTY=0
-KEEP_STAGE=0
-
-usage() {
-  cat <<'EOF'
-Usage:
-  scripts/package-codex-plugin.sh [options]
-
-Options:
-  --output PATH            Write archive to PATH.
-                           Default: ../_tmp/sup-codex-packaging/superpowers-VERSION.zip
-  --format FORMAT          Archive format: zip or tar.gz. Default: zip.
-                           If --output ends in .zip, .tar.gz, or .tgz, that
-                           extension is used when --format is omitted.
-  --metadata-source PATH   Prior official package directory, .zip, or .tar.gz used to
-                           seed skills/*/agents/openai.yaml.
-                           Default: ../_tmp/sup-codex-packaging/superpowers,
-                           falling back to superpowers.zip, then superpowers.tar.gz
-  --ref REF                Git ref to package. Default: HEAD.
-  --allow-dirty            Permit a dirty working tree. The archive still uses --ref.
-  --keep-stage             Print and keep the temporary staging directory.
-  -h, --help               Show this help.
-
-The archive is rootless: .codex-plugin/, assets/, skills/, README.md, LICENSE,
-and CODE_OF_CONDUCT.md sit at the archive root. Source-only repo files, hooks, tests,
-docs, and other harness manifests are intentionally not shipped.
-EOF
-}
-
-die() {
-  echo "ERROR: $*" >&2
-  exit 1
-}
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --output)
-      [[ $# -ge 2 ]] || die "--output requires a path"
-      OUTPUT="$2"
-      shift 2
-      ;;
-    --format)
-      [[ $# -ge 2 ]] || die "--format requires a value"
-      case "$2" in
-        zip)
-          FORMAT="zip"
-          ;;
-        tar.gz|tgz)
-          FORMAT="tar.gz"
-          ;;
-        *)
-          die "--format must be zip or tar.gz"
-          ;;
-      esac
-      shift 2
-      ;;
-    --metadata-source)
-      [[ $# -ge 2 ]] || die "--metadata-source requires a path"
-      METADATA_SOURCE="$2"
-      shift 2
-      ;;
-    --ref)
-      [[ $# -ge 2 ]] || die "--ref requires a value"
-      REF="$2"
-      shift 2
-      ;;
-    --allow-dirty)
-      ALLOW_DIRTY=1
-      shift
-      ;;
-    --keep-stage)
-      KEEP_STAGE=1
-      shift
-      ;;
-    -h|--help)
-      usage
-      exit 0
-      ;;
-    *)
-      echo "Unknown arg: $1" >&2
-      usage >&2
-      exit 2
-      ;;
-  esac
-done
-
-infer_format_from_output() {
-  local output_path="$1"
-
-  case "$output_path" in
-    *.tar.gz|*.tgz)
-      printf '%s\n' "tar.gz"
-      ;;
-    *.zip)
-      printf '%s\n' "zip"
-      ;;
-    *)
-      return 1
-      ;;
-  esac
-}
-
-if [[ -z "$FORMAT" ]]; then
-  FORMAT="$(infer_format_from_output "$OUTPUT" || true)"
-  if [[ -z "$FORMAT" ]]; then
-    FORMAT="zip"
-  fi
-else
-  output_format="$(infer_format_from_output "$OUTPUT" || true)"
-  if [[ -n "$output_format" && "$output_format" != "$FORMAT" ]]; then
-    die "--output extension does not match --format $FORMAT: $OUTPUT"
-  fi
-fi
-
-command -v git >/dev/null || die "git not found in PATH"
-command -v jq >/dev/null || die "jq not found in PATH"
-command -v tar >/dev/null || die "tar not found in PATH"
-command -v gzip >/dev/null || die "gzip not found in PATH"
-command -v shasum >/dev/null || die "shasum not found in PATH"
-if [[ "$FORMAT" == "zip" ]]; then
-  command -v zip >/dev/null || die "zip not found in PATH"
-  command -v unzip >/dev/null || die "unzip not found in PATH"
-fi
-
-[[ -d "$REPO_ROOT/.git" ]] || die "repo root is not a git checkout: $REPO_ROOT"
-git -C "$REPO_ROOT" rev-parse --verify "$REF^{commit}" >/dev/null ||
-  die "git ref does not resolve to a commit: $REF"
-
-if [[ "$ALLOW_DIRTY" -ne 1 ]]; then
-  dirty_status="$(git -C "$REPO_ROOT" status --porcelain --untracked-files=all)"
-  if [[ -n "$dirty_status" ]]; then
-    echo "Working tree has uncommitted changes:" >&2
-    printf '%s\n' "$dirty_status" | sed 's/^/  /' >&2
-    die "commit or stash changes first, or pass --allow-dirty to package $REF anyway"
-  fi
-fi
-
-if [[ -z "$METADATA_SOURCE" ]]; then
-  if [[ -d "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers" ]]; then
-    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers"
-  elif [[ -f "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.zip" ]]; then
-    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.zip"
-  elif [[ -f "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.tar.gz" ]]; then
-    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.tar.gz"
-  else
-    die "no metadata source found; pass --metadata-source <prior package dir, zip, or tar.gz>"
-  fi
-fi
-
-WORK_DIR="$(mktemp -d "${TMPDIR:-/tmp}/superpowers-codex-package.XXXXXX")"
-STAGE="$WORK_DIR/payload"
-METADATA_WORK="$WORK_DIR/metadata"
-ARCHIVE_LIST="$WORK_DIR/archive-list"
-
-cleanup() {
-  if [[ "$KEEP_STAGE" -eq 1 ]]; then
-    echo "Keeping staging directory: $WORK_DIR" >&2
-  else
-    rm -rf "$WORK_DIR"
-  fi
-}
-trap cleanup EXIT
-
-mkdir -p "$STAGE" "$METADATA_WORK"
-
-metadata_root_from_dir() {
-  local candidate="$1"
-  local nested
-
-  if [[ -d "$candidate/skills" ]]; then
-    printf '%s\n' "$candidate"
-    return 0
-  fi
-
-  nested="$(find "$candidate" -mindepth 2 -maxdepth 2 -type d -name skills -print -quit)"
-  if [[ -n "$nested" ]]; then
-    dirname "$nested"
-    return 0
-  fi
-
-  return 1
-}
-
-prepare_metadata_root() {
-  local source="$1"
-  local root
-
-  if [[ -d "$source" ]]; then
-    root="$(cd "$source" && pwd)"
-  elif [[ -f "$source" ]]; then
-    case "$source" in
-      *.tar.gz|*.tgz)
-        tar -xzf "$source" -C "$METADATA_WORK"
-        root="$METADATA_WORK"
-        ;;
-      *.zip)
-        command -v unzip >/dev/null || die "unzip not found in PATH"
-        unzip -q "$source" -d "$METADATA_WORK"
-        root="$METADATA_WORK"
-        ;;
-      *)
-        die "metadata source must be a directory, .zip, or .tar.gz: $source"
-        ;;
-    esac
-  else
-    die "metadata source does not exist: $source"
-  fi
-
-  metadata_root_from_dir "$root" ||
-    die "metadata source does not contain a skills/ directory: $source"
-}
-
-METADATA_ROOT="$(prepare_metadata_root "$METADATA_SOURCE")"
-
-git -C "$REPO_ROOT" archive --format=tar "$REF" -- \
-  .codex-plugin \
-  CODE_OF_CONDUCT.md \
-  LICENSE \
-  README.md \
-  assets \
-  skills \
-  | tar -xf - -C "$STAGE"
-
-VERSION="$(jq -r '.version // empty' "$STAGE/.codex-plugin/plugin.json")"
-[[ -n "$VERSION" ]] || die "could not read version from .codex-plugin/plugin.json"
-
-if [[ -z "$OUTPUT" ]]; then
-  case "$FORMAT" in
-    zip)
-      OUTPUT="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers-$VERSION.zip"
-      ;;
-    tar.gz)
-      OUTPUT="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers-$VERSION.tar.gz"
-      ;;
-  esac
-fi
-mkdir -p "$(dirname "$OUTPUT")"
-OUTPUT="$(cd "$(dirname "$OUTPUT")" && pwd)/$(basename "$OUTPUT")"
-
-missing_metadata=0
-while IFS= read -r skill_dir; do
-  skill_name="${skill_dir##*/}"
-  metadata_file="$METADATA_ROOT/skills/$skill_name/agents/openai.yaml"
-
-  if [[ ! -f "$metadata_file" ]]; then
-    echo "Missing OpenAI agent metadata for skill: $skill_name" >&2
-    missing_metadata=1
-    continue
-  fi
-
-  mkdir -p "$skill_dir/agents"
-  cp "$metadata_file" "$skill_dir/agents/openai.yaml"
-done < <(find "$STAGE/skills" -mindepth 1 -maxdepth 1 -type d -print | sort)
-
-if [[ "$missing_metadata" -ne 0 ]]; then
-  die "metadata source is incomplete"
-fi
-
-skill_count="$(find "$STAGE/skills" -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ')"
-metadata_count="$(find "$STAGE/skills" -path '*/agents/openai.yaml' -type f | wc -l | tr -d ' ')"
-[[ "$skill_count" == "$metadata_count" ]] ||
-  die "metadata count mismatch: $metadata_count metadata files for $skill_count skills"
-
-(
-  cd "$STAGE"
-  {
-    find . -mindepth 1 -type d | sed 's#^\./##' | LC_ALL=C sort
-    find . -mindepth 1 -type f | sed 's#^\./##' | LC_ALL=C sort
-  } >"$ARCHIVE_LIST"
-)
-
-case "$FORMAT" in
-  zip)
-    # ZIP cannot represent dates earlier than 1980.
-    TZ=UTC find "$STAGE" -exec touch -t 198001010000 {} +
-    (
-      cd "$STAGE"
-      rm -f "$OUTPUT"
-      COPYFILE_DISABLE=1 zip -X -q - -@ <"$ARCHIVE_LIST" >"$OUTPUT"
-    )
-    ;;
-  tar.gz)
-    # Match the prior official archive's deterministic tar entry metadata.
-    TZ=UTC find "$STAGE" -exec touch -t 197001010000 {} +
-    (
-      cd "$STAGE"
-      rm -f "$OUTPUT"
-      COPYFILE_DISABLE=1 tar -cf - --no-recursion --format ustar --uid 0 --gid 0 --uname '' --gname '' -T "$ARCHIVE_LIST" |
-        gzip -9n >"$OUTPUT"
-    )
-    ;;
-esac
-
-if command -v xattr >/dev/null 2>&1; then
-  xattr -c "$OUTPUT" 2>/dev/null || true
-fi
-
-case "$FORMAT" in
-  zip)
-    archive_paths="$(unzip -Z1 "$OUTPUT" | sed 's#/$##')"
-    ;;
-  tar.gz)
-    archive_paths="$(tar -tzf "$OUTPUT")"
-    ;;
-esac
-
-unexpected_paths="$(
-  printf '%s\n' "$archive_paths" |
-    grep -E '(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)' || true
-)"
-if [[ -n "$unexpected_paths" ]]; then
-  printf '%s\n' "$unexpected_paths" | sed 's/^/  /' >&2
-  die "archive contains source-only paths"
-fi
-
-entry_count="$(printf '%s\n' "$archive_paths" | wc -l | tr -d ' ')"
-checksum="$(shasum -a 256 "$OUTPUT" | awk '{print $1}')"
-
-echo "Archive: $OUTPUT"
-echo "Format:  $FORMAT"
-echo "Version: $VERSION"
-echo "Entries: $entry_count"
-echo "Skills:  $skill_count"
-echo "SHA-256: $checksum"

scripts/sync-to-codex-plugin.sh

@@ -52,11 +52,9 @@ EXCLUDES=(
   "/.gitattributes"
   "/.github/"
   "/.gitignore"
-  "/.gitmodules"
   "/.kimi-plugin/"
   "/.opencode/"
   "/.pi/"
-  "/.pre-commit-config.yaml"
   "/.version-bump.json"
   "/.worktrees/"
   ".DS_Store"

skills/brainstorming/scripts/server.cjs

@@ -206,22 +206,14 @@ const helperInjection = '<script>\n' + helperScript + '\n</script>';
 // ========== Helper Functions ==========
 
 function readSuperpowersVersion() {
-  const root = path.join(__dirname, '../../..');
-  const manifests = [
-    path.join(root, 'package.json'),
-    path.join(root, '.codex-plugin/plugin.json')
-  ];
-
-  for (const manifest of manifests) {
-    try {
-      const data = JSON.parse(fs.readFileSync(manifest, 'utf-8'));
-      if (data.version) return String(data.version);
-    } catch (e) {
-      // Packaged Codex plugins omit package.json; try the next manifest.
-    }
+  try {
+    const packageJson = JSON.parse(
+      fs.readFileSync(path.join(__dirname, '../../..', 'package.json'), 'utf-8')
+    );
+    return String(packageJson.version || 'unknown');
+  } catch (e) {
+    return 'unknown';
   }
-
-  return 'unknown';
 }
 
 function isTruthyEnv(value) {

skills/brainstorming/visual-companion.md

@@ -74,6 +74,13 @@ On Windows, the script auto-detects and switches to foreground mode (which block
 scripts/start-server.sh --project-dir /path/to/project --open
 ```
 
+**Gemini CLI:**
+```bash
+# Use --foreground and set is_background: true on your shell tool call
+# so the process survives across turns
+scripts/start-server.sh --project-dir /path/to/project --open --foreground
+```
+
 **Copilot CLI:**
 ```bash
 # Use --foreground and start the server via the bash tool with mode: "async"

skills/executing-plans/SKILL.md

@@ -11,7 +11,7 @@ Load plan, review critically, execute all tasks, report when complete.
 
 **Announce at start:** "I'm using the executing-plans skill to implement this plan."
 
-**Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (Claude Code, Codex CLI, Codex App, and Copilot CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
+**Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
 
 ## The Process
 

skills/subagent-driven-development/SKILL.md

@@ -63,7 +63,6 @@ digraph process {
     "Read plan, note context and global constraints, create todos" [shape=box];
     "More tasks remain?" [shape=diamond];
     "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [shape=box];
-    "Final review clean: delete this plan's workspace" [shape=box];
     "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
 
     "Read plan, note context and global constraints, create todos" -> "Dispatch implementer subagent (./implementer-prompt.md)";
@@ -79,8 +78,7 @@ digraph process {
     "Mark task complete in todo list and progress ledger" -> "More tasks remain?";
     "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
     "More tasks remain?" -> "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [label="no"];
-    "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" -> "Final review clean: delete this plan's workspace";
-    "Final review clean: delete this plan's workspace" -> "Use superpowers:finishing-a-development-branch";
+    "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" -> "Use superpowers:finishing-a-development-branch";
 }
 ```
 
@@ -135,7 +133,7 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
 
 Implementer subagents report one of four statuses. Handle each appropriately:
 
-**DONE:** Generate the review package (`scripts/review-package PLAN_FILE BASE HEAD`, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.
+**DONE:** Generate the review package (`scripts/review-package BASE HEAD`, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.
 
 **DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
 
@@ -181,10 +179,10 @@ final whole-branch review. When you fill a reviewer template:
   test hygiene, review method) — the constraints block is for what THIS
   project's spec demands.
 - Hand the reviewer its diff as a file: run this skill's
-  `scripts/review-package PLAN_FILE BASE HEAD` and pass the reviewer the
-  file path it prints (or, without bash: `git log --oneline`,
-  `git diff --stat`, and `git diff -U10` for the range, redirected to one
-  uniquely named file). The output never enters your own context, and the reviewer sees
+  `scripts/review-package BASE HEAD` and pass the reviewer the file path
+  it prints (or, without bash: `git log --oneline`, `git diff --stat`,
+  and `git diff -U10` for the range, redirected to one uniquely named
+  file). The output never enters your own context, and the reviewer sees
   the commit list, stat summary, and full diff with context in one Read
   call. Use the BASE you recorded before dispatching the implementer —
   never `HEAD~1`, which silently truncates multi-commit tasks.
@@ -203,8 +201,8 @@ final whole-branch review. When you fill a reviewer template:
   Do not dismiss the finding because the plan mandates it, and do not
   dispatch a fix that contradicts the plan without asking.
 - The final whole-branch review gets a package too: run
-  `scripts/review-package PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the
-  commit the branch started from, e.g. `git merge-base main HEAD`) and include the
+  `scripts/review-package MERGE_BASE HEAD` (MERGE_BASE = the commit the
+  branch started from, e.g. `git merge-base main HEAD`) and include the
   printed path in the final review dispatch, so the final reviewer reads
   one file instead of re-deriving the branch diff with git commands.
 - Every fix dispatch carries the implementer contract: the fix subagent
@@ -252,31 +250,16 @@ controllers that lost their place have re-dispatched entire completed task
 sequences — the single most expensive failure observed. Track progress in
 a ledger file, not only in todos.
 
-- Each plan owns a workspace: at skill start, run this skill's
-  `scripts/sdd-workspace PLAN_FILE` — it prints the plan's git-ignored
-  directory (`<repo-root>/.superpowers/sdd/<plan-basename>/`), home to
-  every artifact for THIS plan: ledger, briefs, reports, review packages.
-  Another plan's directory is never yours to read or write.
-- Check for this plan's ledger at `<workspace>/progress.md`. If its first
-  line names your plan file, tasks listed there as complete are DONE — do
-  not re-dispatch them; resume at the first task not marked complete. A
-  ledger whose first line names a different plan file — or a stray ledger
-  at the old flat path `.superpowers/sdd/progress.md` — is another plan's
-  progress: leave it in place and start your own, fresh.
-- Create the ledger with its identity as the first line:
-  `# SDD ledger — plan: <plan file path>`.
+- At skill start, check for a ledger:
+  `cat "$(git rev-parse --git-path sdd)/progress.md"`. Tasks listed there
+  as complete are DONE — do not re-dispatch them; resume at the first task
+  not marked complete.
 - When a task's review comes back clean, append one line to the ledger in
   the same message as your other bookkeeping:
   `Task N: complete (commits <base7>..<head7>, review clean)`.
 - The ledger is your recovery map: the commits it names exist in git even
   when your context no longer remembers creating them. After compaction,
   trust the ledger and `git log` over your own recollection.
-- `git clean -fdx` will destroy the workspace (it's git-ignored scratch); if
-  that happens, recover from `git log`.
-- When the final whole-branch review is clean and its fixes are merged,
-  delete this plan's workspace (`rm -rf <workspace>`) — the git history
-  is the record now. Sibling directories belong to other plans; leave
-  them alone.
 
 ## Prompt Templates
 
@@ -290,7 +273,6 @@ a ledger file, not only in todos.
 You: I'm using Subagent-Driven Development to execute this plan.
 
 [Read plan file once: docs/superpowers/plans/feature-plan.md]
-[Resolve workspace: scripts/sdd-workspace docs/superpowers/plans/feature-plan.md — no ledger inside, fresh start]
 [Create todos for all tasks]
 
 Task 1: Hook installation script
@@ -345,8 +327,6 @@ Task reviewer: Spec ✅. Task quality: Approved.
 [Dispatch final code-reviewer]
 Final reviewer: All requirements met, ready to merge
 
-[Delete this plan's workspace — the record now lives in git]
-
 Done!
 ```
 
@@ -400,8 +380,8 @@ Done!
   dispatch prompt ("treat it as Minor at most") — the plan's example code is
   a starting point, not evidence that its weaknesses were chosen
 - Dispatch a task reviewer without a diff file — generate it first
-  (`scripts/review-package PLAN_FILE BASE HEAD`) and name the printed
-  path in the prompt
+  (`scripts/review-package BASE HEAD`) and name the printed path in the
+  prompt
 - Move to next task while the review has open Critical/Important issues
 - Re-dispatch a task the progress ledger already marks complete — check
   the ledger (and `git log`) after any compaction or resume

skills/subagent-driven-development/scripts/review-package

@@ -4,28 +4,29 @@
 # call. Using the recorded per-task BASE (not HEAD~1) keeps multi-commit
 # tasks intact.
 #
-# Usage: review-package PLAN_FILE BASE HEAD [OUTFILE]
-# Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/review-<base7>..<head7>.diff
-# (named per range, so a re-review after fixes gets a distinct fresh file).
+# Usage: review-package BASE HEAD [OUTFILE]
+# Default OUTFILE: <git-dir>/sdd/review-<base7>..<head7>.diff — unique per
+# repo instance and per range, so concurrent sessions cannot collide and a
+# re-review after fixes always gets a distinctly named fresh file.
 set -euo pipefail
 
-if [ $# -lt 3 ] || [ $# -gt 4 ]; then
-  echo "usage: review-package PLAN_FILE BASE HEAD [OUTFILE]" >&2
+if [ $# -lt 2 ] || [ $# -gt 3 ]; then
+  echo "usage: review-package BASE HEAD [OUTFILE]" >&2
   exit 2
 fi
 
-plan=$1
-base=$2
-head=$3
-[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }
+base=$1
+head=$2
 
 git rev-parse --verify --quiet "$base" >/dev/null || { echo "bad BASE: $base" >&2; exit 2; }
 git rev-parse --verify --quiet "$head" >/dev/null || { echo "bad HEAD: $head" >&2; exit 2; }
 
-if [ $# -eq 4 ]; then
-  out=$4
+if [ $# -eq 3 ]; then
+  out=$3
 else
-  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
+  dir=$(git rev-parse --git-path sdd)
+  mkdir -p "$dir"
+  dir=$(cd "$dir" && pwd)
   out="$dir/review-$(git rev-parse --short "$base")..$(git rev-parse --short "$head").diff"
 fi
 

skills/subagent-driven-development/scripts/sdd-workspace

@@ -1,40 +0,0 @@
-#!/usr/bin/env bash
-# Resolve and ensure the working-tree directory SDD uses for one plan's
-# short-lived artifacts: task briefs, implementer reports, review packages,
-# and the progress ledger. Print the plan directory's absolute path.
-#
-# One directory per plan (.superpowers/sdd/<plan-basename>/) so a follow-up
-# plan in the same working tree can never read or overwrite another plan's
-# artifacts. A stale ledger misread as current progress makes controllers
-# skip whole task sequences — plan-scoping removes that failure structurally.
-#
-# The workspace lives in the working tree (not under .git/) because Claude Code
-# treats .git/ as a protected path and denies agent writes there — which blocks
-# an implementer subagent from writing its report file. A self-ignoring
-# .gitignore at .superpowers/sdd/ keeps every plan's workspace out of
-# `git status` and out of accidental commits without modifying any tracked file.
-#
-# Single source of truth for the workspace location, so task-brief and
-# review-package cannot drift to different directories.
-#
-# Usage: sdd-workspace PLAN_FILE
-set -euo pipefail
-
-if [ $# -ne 1 ]; then
-  echo "usage: sdd-workspace PLAN_FILE" >&2
-  exit 2
-fi
-
-plan=$1
-[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }
-
-slug=$(basename "$plan" .md)
-[ -n "$slug" ] && [ "$slug" != "." ] && [ "$slug" != ".." ] \
-  || { echo "cannot derive a workspace name from: $plan" >&2; exit 2; }
-
-root=$(git rev-parse --show-toplevel)
-base="$root/.superpowers/sdd"
-dir="$base/$slug"
-mkdir -p "$dir"
-printf '*\n' > "$base/.gitignore"
-cd "$dir" && pwd

skills/subagent-driven-development/scripts/task-brief

@@ -4,9 +4,7 @@
 # through the controller's context.
 #
 # Usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]
-# Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/task-<N>-brief.md
-# (per plan and per worktree; concurrent runs of the SAME plan in the same
-# working tree share it).
+# Default OUTFILE: <git-dir>/sdd/task-<N>.<unique>/task-<N>-brief.md.
 set -euo pipefail
 
 if [ $# -lt 2 ] || [ $# -gt 3 ]; then
@@ -21,8 +19,11 @@ n=$2
 if [ $# -eq 3 ]; then
   out=$3
 else
-  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
-  out="$dir/task-${n}-brief.md"
+  dir=$(git rev-parse --git-path sdd)
+  mkdir -p "$dir"
+  dir=$(cd "$dir" && pwd)
+  brief_dir=$(mktemp -d "$dir/task-${n}.XXXXXX")
+  out="$brief_dir/task-${n}-brief.md"
 fi
 
 awk -v n="$n" '

skills/subagent-driven-development/task-reviewer-prompt.md

@@ -178,8 +178,8 @@ Subagent (general-purpose):
 - `[BASE_SHA]` — commit before this task
 - `[HEAD_SHA]` — current commit
 - `[DIFF_FILE]` — REQUIRED: the path the controller wrote the review
-  package to (`scripts/review-package PLAN_FILE BASE HEAD` prints the unique
-  path it wrote; the package never enters the controller's context)
+  package to (`scripts/review-package BASE HEAD` prints the unique path it
+  wrote; the package never enters the controller's context)
 
 **Reviewer returns:** Spec Compliance verdict (✅/❌/⚠️), Strengths, Issues
 (Critical/Important/Minor), Task quality verdict

skills/using-superpowers/SKILL.md

@@ -4,7 +4,7 @@ description: Use when starting any conversation - establishes how to find and us
 ---
 
 <SUBAGENT-STOP>
-If you were dispatched as a subagent to execute a specific task, ignore this skill.
+If you were dispatched as a subagent to execute a specific task, skip this skill.
 </SUBAGENT-STOP>
 
 <EXTREMELY-IMPORTANT>
@@ -12,23 +12,72 @@ If you think there is even a 1% chance a skill might apply to what you are doing
 
 IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
 
-This is not negotiable. You cannot rationalize your way out of this.
+This is not negotiable. This is not optional. You cannot rationalize your way out of this.
 </EXTREMELY-IMPORTANT>
 
+## Instruction Priority
+
+Superpowers skills override default system prompt behavior, but **user instructions always take precedence**:
+
+1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
+2. **Superpowers skills** — override default system behavior where they conflict
+3. **Default system prompt** — lowest priority
+
+If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
+
+## How to Access Skills
+
+**Never read skill files manually with file tools** — always use your platform's skill-loading mechanism so the skill is properly activated.
+
+**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you — follow it directly.
+
+**In Codex:** Skills load natively. Follow the instructions presented when a skill activates.
+
+**In Copilot CLI:** Use the `skill` tool. Skills are auto-discovered from installed plugins.
+
+**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
+
+**In other environments:** Check your platform's documentation for how skills are loaded.
+
+## Platform Adaptation
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file") rather than naming any one runtime's tools. For per-platform tool equivalents and instructions-file conventions, see [claude-code-tools.md](references/claude-code-tools.md), [codex-tools.md](references/codex-tools.md), [copilot-tools.md](references/copilot-tools.md), [gemini-tools.md](references/gemini-tools.md), [pi-tools.md](references/pi-tools.md), and [antigravity-tools.md](references/antigravity-tools.md). Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
+
+# Using Skills
+
 ## The Rule
 
-**Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.
+**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
 
-**Before entering plan mode:** if you haven't already brainstormed, invoke the brainstorming skill first.
+```dot
+digraph skill_flow {
+    "User message received" [shape=doublecircle];
+    "About to enter plan mode?" [shape=doublecircle];
+    "Already brainstormed?" [shape=diamond];
+    "Invoke brainstorming skill" [shape=box];
+    "Might any skill apply?" [shape=diamond];
+    "Invoke the skill" [shape=box];
+    "Announce: 'Using [skill] to [purpose]'" [shape=box];
+    "Has checklist?" [shape=diamond];
+    "Create a todo per item" [shape=box];
+    "Follow skill exactly" [shape=box];
+    "Respond (including clarifications)" [shape=doublecircle];
 
-Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
+    "About to enter plan mode?" -> "Already brainstormed?";
+    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
+    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
+    "Invoke brainstorming skill" -> "Might any skill apply?";
 
-## Skill Priority
-
-When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.
-
-- "Let's build X" → superpowers:brainstorming first, then implementation skills.
-- "Fix this bug" → superpowers:systematic-debugging first, then domain skills.
+    "User message received" -> "Might any skill apply?";
+    "Might any skill apply?" -> "Invoke the skill" [label="yes, even 1%"];
+    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
+    "Invoke the skill" -> "Announce: 'Using [skill] to [purpose]'";
+    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
+    "Has checklist?" -> "Create a todo per item" [label="yes"];
+    "Has checklist?" -> "Follow skill exactly" [label="no"];
+    "Create a todo per item" -> "Follow skill exactly";
+}
+```
 
 ## Red Flags
 
@@ -49,14 +98,24 @@ These thoughts mean STOP—you're rationalizing:
 | "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
 | "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
 
-## Platform Adaptation
+## Skill Priority
 
-If your harness appears here, read its reference file for special instructions:
+When multiple skills could apply, use this order:
 
-- Codex: `references/codex-tools.md`
-- Pi: `references/pi-tools.md`
-- Antigravity: `references/antigravity-tools.md`
+1. **Process skills first** (brainstorming, systematic-debugging) - these determine HOW to approach the task
+2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution
+
+"Let's build X" → brainstorming first, then implementation skills.
+"Fix this bug" → systematic-debugging first, then domain-specific skills.
+
+## Skill Types
+
+**Rigid** (TDD, systematic-debugging): Follow exactly. Don't adapt away discipline.
+
+**Flexible** (patterns): Adapt principles to context.
+
+The skill itself tells you which.
 
 ## User Instructions
 
-User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.
+Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.

skills/using-superpowers/references/antigravity-tools.md

@@ -4,12 +4,85 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file").
 
 | Action skills request | Antigravity CLI equivalent |
 |----------------------|----------------------|
+| Read a file | `view_file` |
+| Create a new file | `write_to_file` |
+| Edit a file | `replace_file_content` |
+| Edit a file in several places at once | `multi_replace_file_content` |
+| Run a shell command | `run_command` |
+| Search file contents | `grep_search` |
+| Find files by name / list a directory | `list_dir` (no dedicated glob tool — combine `list_dir` with `grep_search`) |
+| Fetch a URL | `read_url_content` |
+| Search the web | `search_web` |
+| Pose a structured question to your human partner | `ask_question` |
 | Dispatch a subagent (`Subagent (general-purpose):` template) | `invoke_subagent` with a built-in `TypeName` — `self` for full-capability work, `research` for read-only (see [Subagent support](#subagent-support)) |
+| Multiple parallel dispatches | Multiple entries in one `invoke_subagent` call's `Subagents` array |
 | Task tracking ("create a todo", "mark complete") | a **task artifact** — `write_to_file` with `IsArtifact: true` and `ArtifactType: "task"` (see [Task tracking](#task-tracking)). **Not** `manage_task`, which manages background processes. |
 
+## Invoking a skill — read its `SKILL.md`
+
+Antigravity surfaces every installed skill's `name` + `description` to you at the
+start of each session, but it has **no `Skill`/`activate_skill` tool**. To load a
+skill, **read its `SKILL.md` with `view_file`, setting `IsSkillFile: true`** when
+the skill applies — e.g. `view_file` on
+`.../plugins/superpowers/skills/<skill-name>/SKILL.md` with `IsSkillFile: true`.
+(`IsSkillFile` is agy's own signal that you're reading a file to *execute its
+instructions*, not to edit or preview it — set it whenever you load a skill.)
+
+This is the blessed skill-loading mechanism on this harness. The general rule
+"never read skill files manually" means "don't bypass your platform's
+skill-loading mechanism" — and on Antigravity, reading `SKILL.md` *is* that
+mechanism. Reading it honors the rule rather than breaking it.
+
+You already know which skills exist and what they're for: their names and
+descriptions are in front of you at session start. When a description matches
+what you're about to do, read that skill's `SKILL.md` before acting.
+
+## Subagent support
+
+Antigravity dispatches subagents with `invoke_subagent`, passing each one a
+`TypeName` in the `Subagents` array. Two `TypeName`s are **built in** — use them
+directly, no `define_subagent` needed:
+
+- **`self`** — a full clone of you, with every tool you have (including
+  `write_to_file`/`replace_file_content`/`run_command`). The safe default for
+  general-purpose work: implementing, fixing, anything that edits files or runs
+  commands.
+- **`research`** — read-only (file reading, `grep_search`, web/URL fetch; no write
+  or command access). Use it when you specifically want a subagent that can't make
+  changes — investigation and read-only review.
+
+Call `define_subagent` only for a custom system prompt or capability mix: set
+`enable_write_tools: true` to grant file edits **and** `run_command`,
+`enable_subagent_tools` for nested dispatch, `enable_mcp_tools` for MCP. Then
+invoke it by the name you gave it. (`manage_subagents` lists/kills running
+subagents.)
+
+Skills dispatch with `Subagent (general-purpose):` and either reference a
+prompt-template file (e.g. `superpowers:subagent-driven-development`'s
+`./implementer-prompt.md`) or supply an inline prompt. On Antigravity:
+
+| Skill dispatch form | Antigravity equivalent |
+|---------------------|----------------------|
+| An implementer-style `*-prompt.md` template (writes code, runs tests) | Fill the template, then `invoke_subagent` with `TypeName: "self"` and the filled prompt |
+| A read-only reviewer template (`task-reviewer`, `code-reviewer`, `requesting-code-review`'s `./code-reviewer.md`) | `invoke_subagent` with `TypeName: "research"` and the filled review template |
+| Inline prompt (no template referenced) | `invoke_subagent` with `TypeName: "self"` (or `"research"` if the task only reads) and your inline prompt |
+
+### Prompt filling
+
+Skills provide prompt templates with placeholders like `{WHAT_WAS_IMPLEMENTED}` or
+`[FULL TEXT of task]`. Fill all placeholders before passing the complete prompt to
+`invoke_subagent`. The prompt template itself contains the agent's role, review
+criteria, and expected output format — the subagent will follow it.
+
+### Parallel dispatch
+
+Put multiple entries in a single `invoke_subagent` call's `Subagents` array to run
+independent subagent work in parallel. Keep dependent tasks sequential, but do not
+serialize independent subagent tasks just to preserve a simpler history.
+
 ## Task tracking
 
-Antigravity has **no todo tool** (`manage_task` manages background
+Antigravity has **no todo / `TodoWrite` tool** (`manage_task` manages background
 processes — `list`/`kill`/`status`/`send_input` — it is *not* a checklist). When a
 skill says to create a todo list or track tasks, maintain a **task artifact**: a
 markdown checklist saved with `write_to_file` (`IsArtifact: true`,

skills/using-superpowers/references/claude-code-tools.md

@@ -0,0 +1,50 @@
+# Claude Code Tool Mapping
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Claude Code these resolve to the tools below.
+
+## Tools
+
+| Action skills request | Claude Code tool |
+|----------------------|------------------|
+| Read a file | `Read` |
+| Create a new file | `Write` |
+| Edit a file | `Edit` |
+| Run a shell command | `Bash` |
+| Search file contents | `Grep` |
+| Find files by name | `Glob` |
+| Fetch a URL | `WebFetch` |
+| Search the web | `WebSearch` |
+| Invoke a skill | `Skill` |
+| Dispatch a subagent (`Subagent (general-purpose):` template) | `Agent` (older releases named this `Task`) |
+| Multiple parallel dispatches | Multiple `Agent` calls in one response |
+| Task tracking ("create a todo", "mark complete") | `TaskCreate`, `TaskUpdate`, `TaskList`, `TaskGet`; `TodoWrite` in `claude -p` / Agent SDK unless `CLAUDE_CODE_ENABLE_TASKS=1` is set |
+| Background-process / subagent lifecycle (read output, cancel) | `TaskOutput`, `TaskStop` — these are distinct from the todo tools above and apply to running shells, agents, and remote sessions |
+
+## Instructions file
+
+When a skill mentions "your instructions file", on Claude Code this is **`CLAUDE.md`**. Claude Code walks up the directory tree from the current working directory and concatenates every `CLAUDE.md` and `CLAUDE.local.md` it finds along the way. Standard locations:
+
+| Scope | Location |
+|-------|----------|
+| Project (team-shared) | `./CLAUDE.md` or `./.claude/CLAUDE.md` |
+| User global | `~/.claude/CLAUDE.md` |
+| Local-private (gitignored) | `./CLAUDE.local.md` |
+| Managed policy (org-wide) | `/Library/Application Support/ClaudeCode/CLAUDE.md` (macOS), `/etc/claude-code/CLAUDE.md` (Linux/WSL), `C:\Program Files\ClaudeCode\CLAUDE.md` (Windows) |
+
+CLAUDE.md files can pull in additional content with `@path/to/file` imports (relative or absolute, max five hops deep). Subdirectory `CLAUDE.md` files are also discovered automatically and loaded on-demand when Claude Code reads files in those subdirectories.
+
+Claude Code does **not** read `AGENTS.md` directly. If a project already maintains `AGENTS.md` for other agents, import it from `CLAUDE.md` so both runtimes share the same instructions:
+
+```markdown
+@AGENTS.md
+
+## Claude Code
+
+(Claude-Code-specific instructions go here.)
+```
+
+For path-scoped rules and larger-project organization, see `.claude/rules/` (rules can be scoped to specific files via `paths` frontmatter and load on demand).
+
+## Personal skills directory
+
+User-level skills live at **`~/.claude/skills/`**. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter) plus any supporting files. Claude Code does not currently recognize the cross-runtime `~/.agents/skills/` path that Codex, Copilot CLI, and Gemini CLI read; if you're relying on cross-runtime support in the future, verify against the [official skills docs](https://code.claude.com/docs/en/skills).

skills/using-superpowers/references/codex-tools.md

@@ -1,3 +1,31 @@
+# Codex Tool Mapping
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Codex these resolve to the tools below.
+
+| Action skills request | Codex equivalent |
+|----------------------|------------------|
+| Read a file | `shell` (e.g., `cat`, `head`, `tail`) — Codex reads files via shell |
+| Create / edit / delete a file | `apply_patch` (structured diff for create, update, delete) |
+| Run a shell command | `shell` |
+| Search file contents | `shell` (e.g., `grep`, `rg`) |
+| Find files by name | `shell` (e.g., `find`, `ls`) |
+| Fetch a URL | `shell` with `curl` / `wget` — Codex has no native fetch tool |
+| Search the web | `web_search` (enabled by default; configurable in `config.toml` via the top-level `web_search` setting — `live`, `cached`, or `disabled`) |
+| Invoke a skill | Skills load natively — just follow the instructions |
+| Dispatch a subagent (`Subagent (general-purpose):` template) | `spawn_agent` (see [Subagent dispatch requires multi-agent support](#subagent-dispatch-requires-multi-agent-support)) |
+| Multiple parallel dispatches | Multiple `spawn_agent` calls in one response |
+| Wait for subagent result | `wait_agent` |
+| Free up subagent slot when done | `close_agent` |
+| Task tracking ("create a todo", "mark complete") | `update_plan` |
+
+## Instructions file
+
+When a skill mentions "your instructions file", on Codex this is **`AGENTS.md`** at the project root. Codex also reads `~/.codex/AGENTS.md` for global context, and an `AGENTS.override.md` (in the project tree or `~/.codex/`) takes precedence when present. Codex walks from the project root down to the current working directory, concatenating `AGENTS.md` files it finds along the way, up to `project_doc_max_bytes` (32 KiB by default).
+
+## Personal skills directory
+
+User-level skills live at **`$CODEX_HOME/skills/`** (default `~/.codex/skills/`). Codex also reads the cross-runtime path **`~/.agents/skills/`** (shared with Copilot CLI and Gemini CLI). When both directories exist at the same scope, Codex loads them both as separate skill catalogs — Codex's docs don't currently document a precedence between them. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
+
 ## Subagent dispatch requires multi-agent support
 
 Add to your Codex config (`~/.codex/config.toml`):
@@ -7,7 +35,12 @@ Add to your Codex config (`~/.codex/config.toml`):
 multi_agent = true
 ```
 
-This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`. When using subagent-driven-development, you should always close implementer and reviewer subagents when they have finished all their work.
+This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`.
+
+Legacy note: Codex builds before `rust-v0.115.0` exposed spawned-agent
+waiting as `wait`. Current Codex uses `wait_agent` for spawned agents. The
+`wait` name now belongs to code-mode `exec/wait`, which resumes a yielded exec
+cell by `cell_id`; it is not the spawned-agent result tool.
 
 ## Environment Detection
 

skills/using-superpowers/references/copilot-tools.md

@@ -0,0 +1,49 @@
+# Copilot CLI Tool Mapping
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Copilot CLI these resolve to the tools below.
+
+| Action skills request | Copilot CLI equivalent |
+|----------------------|----------------------|
+| Read a file | `view` |
+| Create / edit / delete a file | `apply_patch` (Copilot CLI has no separate create/edit/write tools) |
+| Run a shell command | `bash` |
+| Search file contents | `rg` (ripgrep; Copilot CLI does not expose a `grep` tool) |
+| Find files by name | `glob` |
+| Fetch a URL | `web_fetch` |
+| Search the web | `web_search` |
+| Invoke a skill | `skill` |
+| Dispatch a subagent (`Subagent (general-purpose):` template) | `task` with `agent_type: "general-purpose"` (other accepted types: `explore`, `task`, `code-review`, `research`, `configure-copilot`) |
+| Multiple parallel dispatches | Multiple `task` calls in one response |
+| Subagent status/output/control | `read_agent`, `list_agents`, `write_agent` |
+| Task tracking ("create a todo", "mark complete") | `update_todo` |
+| Enter / exit plan mode | No equivalent — stay in the main session |
+
+## Instructions file
+
+When a skill mentions "your instructions file", on Copilot CLI this is **`AGENTS.md`** at the repository root. If both `AGENTS.md` and `.github/copilot-instructions.md` are present, Copilot reads both.
+
+## Personal skills directory
+
+User-level skills live at **`~/.copilot/skills/`**. Copilot CLI also recognizes the cross-runtime alias **`~/.agents/skills/`**, which is shared with Codex and Gemini CLI. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
+
+## Async shell sessions
+
+Copilot CLI supports persistent async shell sessions:
+
+| Tool | Purpose |
+|------|---------|
+| `bash` with `mode: "async"` (and optionally `detach: true`) | Start a long-running command in the background; returns a `shellId` |
+| `write_bash` | Send input to a running async session |
+| `read_bash` | Read output from an async session |
+| `stop_bash` | Terminate an async session |
+| `list_bash` | List all active shell sessions |
+
+## Additional Copilot CLI tools
+
+| Tool | Purpose |
+|------|---------|
+| `store_memory` | Persist facts about the codebase for future sessions |
+| `report_intent` | Update the UI status line with current intent |
+| `sql` | Query the session's SQLite database (todos, metadata) |
+| `fetch_copilot_cli_documentation` | Look up Copilot CLI documentation |
+| GitHub MCP tools (`github-mcp-server-*`) | Native GitHub API access (issues, PRs, code search) |

skills/using-superpowers/references/gemini-tools.md

@@ -0,0 +1,63 @@
+# Gemini CLI Tool Mapping
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Gemini CLI these resolve to the tools below.
+
+| Action skills request | Gemini CLI equivalent |
+|----------------------|----------------------|
+| Read a file | `read_file` |
+| Read multiple files at once | `read_many_files` |
+| Create a new file | `write_file` |
+| Edit a file | `replace` |
+| Run a shell command | `run_shell_command` |
+| Search file contents | `grep_search` |
+| Find files by name | `glob` |
+| List files and subdirectories | `list_directory` |
+| Fetch a URL | `web_fetch` |
+| Search the web | `google_web_search` |
+| Invoke a skill | `activate_skill` |
+| Dispatch a subagent (`Subagent (general-purpose):` template) | `invoke_agent` with `agent_name: "generalist"` (invocable via `@generalist` chat syntax — see [Subagent support](#subagent-support)) |
+| Multiple parallel dispatches | Multiple `invoke_agent` calls in the same response |
+| Task tracking ("create a todo", "mark complete") | `write_todos` (statuses: pending, in_progress, completed, cancelled, blocked) |
+
+## Instructions file
+
+When a skill mentions "your instructions file", on Gemini CLI this is **`GEMINI.md`**. Gemini CLI loads `GEMINI.md` hierarchically: global at `~/.gemini/GEMINI.md`, project-level files in workspace directories and their ancestors, and sub-directory `GEMINI.md` files when a tool accesses files in those directories.
+
+## Personal skills directory
+
+User-level skills live at **`~/.gemini/skills/`**, with **`~/.agents/skills/`** as a cross-runtime alias (shared with Codex and Copilot CLI). When both directories exist at the same scope, `.agents/skills/` takes precedence. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
+
+## Subagent support
+
+Gemini CLI dispatches subagents through the `invoke_agent` tool, which takes `agent_name` and `prompt` parameters. The same dispatch is also surfaced as a chat-syntax shortcut: typing `@generalist <prompt>` is equivalent to calling `invoke_agent` with `agent_name: "generalist"`. Built-in agent names include `generalist`, `cli_help`, `codebase_investigator`, and (with browser tooling enabled) `browser_agent`.
+
+Skills dispatch with `Subagent (general-purpose):` and either reference a prompt-template file (e.g., `superpowers:subagent-driven-development`'s `./implementer-prompt.md`) or supply an inline prompt. On Gemini CLI:
+
+| Skill dispatch form | Gemini CLI equivalent |
+|---------------------|----------------------|
+| References a `*-prompt.md` template (implementer, task-reviewer, code-reviewer, etc.) | Fill the template, then `invoke_agent` with `agent_name: "generalist"` and the filled prompt |
+| References `superpowers:requesting-code-review`'s `./code-reviewer.md` | `invoke_agent` with `agent_name: "generalist"` and the filled review template |
+| Inline prompt (no template referenced) | `invoke_agent` with `agent_name: "generalist"` and your inline prompt |
+
+### Prompt filling
+
+Skills provide prompt templates with placeholders like `{WHAT_WAS_IMPLEMENTED}` or `[FULL TEXT of task]`. Fill all placeholders before passing the complete prompt to `invoke_agent`. The prompt template itself contains the agent's role, review criteria, and expected output format — the subagent will follow it.
+
+### Parallel dispatch
+
+Gemini CLI supports parallel subagent dispatch. Issue multiple `invoke_agent` calls in the same response (or multiple `@generalist` invocations in one prompt) to run independent subagent work in parallel. Keep dependent tasks sequential, but do not serialize independent subagent tasks just to preserve a simpler history.
+
+## Additional Gemini CLI tools
+
+These tools are unique to Gemini CLI:
+
+| Tool | Purpose |
+|------|---------|
+| `save_memory` (legacy) | Persist facts across sessions when `experimental.memoryV2 = false` |
+| `get_internal_docs` | Look up Gemini CLI's bundled documentation |
+| `ask_user` | Pose structured questions to the user (text / single-select / multi-select) |
+| `enter_plan_mode` / `exit_plan_mode` | Switch into and out of read-only plan mode |
+| `update_topic` | Update the current conversation's topic / strategic-intent metadata |
+| `complete_task` | Signal that a Gemini subagent has completed and return its result to the parent agent |
+| `tracker_create_task`, `tracker_update_task`, `tracker_get_task`, `tracker_list_tasks`, `tracker_add_dependency`, `tracker_visualize` | Rich task tracker with dependency and visualization support |
+| `read_mcp_resource`, `list_mcp_resources` | MCP resource access |

skills/using-superpowers/references/pi-tools.md

@@ -4,9 +4,21 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file").
 
 | Action skills request | Pi equivalent |
 | --- | --- |
+| Invoke a skill | Pi native skills: load the relevant `SKILL.md` with `read`, or let the human use `/skill:name` |
+| Read a file | `read` |
+| Create a file | `write` |
+| Edit a file | `edit` |
+| Run a shell command | `bash` |
+| Search file contents | `grep` when active; otherwise `bash` with `rg`/`grep` |
+| Find files by name | `find` or `bash` with shell globs |
+| List files and subdirectories | `ls` when active; otherwise `bash` with `ls` |
 | Dispatch a subagent (`Subagent (general-purpose):` template) | Use an installed subagent tool such as `subagent` from `pi-subagents` if available |
 | Task tracking ("create a todo", "mark complete") | Use an installed todo/task tool if available, otherwise track tasks in the plan or `TODO.md` |
 
+## Skills
+
+Pi discovers skills from configured skill directories and installed Pi packages. A Superpowers Pi package should expose `skills/` through its `pi.skills` manifest entry. Pi does not expose Claude Code's `Skill` tool, but the agent should still follow the Superpowers rule: when a skill applies, load and follow it before responding.
+
 ## Subagents
 
 Pi core does not ship a standard subagent tool. The `pi-subagents` package is a strong optional companion and provides a `subagent` tool with single-agent, chain, parallel, async, forked-context, and resume/status workflows. If no subagent tool is available, do not fabricate `Task` calls; execute sequentially in the current session or explain that the optional subagent capability is not installed.

skills/writing-skills/SKILL.md

@@ -9,7 +9,7 @@ description: Use when creating new skills, editing existing skills, or verifying
 
 **Writing skills IS Test-Driven Development applied to process documentation.**
 
-**Personal skills live in your runtime's skills directory** 
+**Personal skills live in your runtime's skills directory** — see [claude-code-tools.md](../using-superpowers/references/claude-code-tools.md), [codex-tools.md](../using-superpowers/references/codex-tools.md), [copilot-tools.md](../using-superpowers/references/copilot-tools.md), or [gemini-tools.md](../using-superpowers/references/gemini-tools.md) for the path on your runtime. Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.
 
 You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
 

tests/brainstorm-server/branding.test.js

@@ -26,9 +26,9 @@ function sleep(ms) {
   return new Promise(resolve => setTimeout(resolve, ms));
 }
 
-function startServer({ port, dir, env = {}, serverPath = SERVER_PATH }) {
+function startServer({ port, dir, env = {} }) {
   cleanup(dir);
-  return spawn('node', [serverPath], {
+  return spawn('node', [SERVER_PATH], {
     env: {
       ...process.env,
       BRAINSTORM_PORT: String(port),
@@ -74,21 +74,6 @@ function writeFragment(dir) {
   fs.writeFileSync(path.join(contentDir, 'screen.html'), '<h2>Pick a layout</h2>');
 }
 
-function createPackagedServerFixture(version) {
-  const root = fs.mkdtempSync(path.join('/tmp', 'superpowers-packaged-server-'));
-  const scriptDir = path.join(root, 'skills/brainstorming/scripts');
-  fs.cpSync(path.join(REPO_ROOT, 'skills/brainstorming/scripts'), scriptDir, { recursive: true });
-  fs.mkdirSync(path.join(root, '.codex-plugin'), { recursive: true });
-  fs.writeFileSync(
-    path.join(root, '.codex-plugin/plugin.json'),
-    JSON.stringify({ name: 'superpowers', version }, null, 2)
-  );
-  return {
-    root,
-    serverPath: path.join(scriptDir, 'server.cjs')
-  };
-}
-
 async function withServer(options, fn) {
   const server = startServer(options);
   try {
@@ -119,13 +104,13 @@ async function test(name, fn) {
   }
 }
 
-function assertBrandedWithLogo(html, version = PACKAGE_VERSION) {
+function assertBrandedWithLogo(html) {
   assert(
-    html.includes(`Superpowers v${version}`),
+    html.includes(`Superpowers v${PACKAGE_VERSION}`),
     'branding text should include dynamic package version'
   );
   assert(
-    !html.includes(`Superpowers v${version} by`),
+    !html.includes(`Superpowers v${PACKAGE_VERSION} by`),
     'branding text should not include "by" when the logo is visible'
   );
   assert(
@@ -154,15 +139,15 @@ function assertBrandedWithLogo(html, version = PACKAGE_VERSION) {
   );
 }
 
-function assertBrandedFallbackText(html, version = PACKAGE_VERSION) {
+function assertBrandedFallbackText(html) {
   assert(
-    html.includes(`Prime Radiant Superpowers v${version}`),
+    html.includes(`Prime Radiant Superpowers v${PACKAGE_VERSION}`),
     'disabled telemetry should keep plain text Prime Radiant/Superpowers branding'
   );
 }
 
-function assertTelemetryImage(html, version = PACKAGE_VERSION) {
-  const expectedUrl = `${ASSET_URL}?v=${encodeURIComponent(version)}`;
+function assertTelemetryImage(html) {
+  const expectedUrl = `${ASSET_URL}?v=${encodeURIComponent(PACKAGE_VERSION)}`;
   assert(html.includes(`src="${expectedUrl}"`), 'remote image should use the dedicated main-domain asset with only v=');
   assert(!html.includes('event='), 'remote image URL must not include event=');
   assert(!html.includes('surface='), 'remote image URL must not include surface=');
@@ -270,26 +255,6 @@ async function main() {
     });
   });
 
-  await test('packaged Codex plugin reads version from .codex-plugin manifest', async () => {
-    const port = 3457;
-    const dir = '/tmp/brainstorm-branding-packaged-codex';
-    const packagedVersion = '7.8.9';
-    const fixture = createPackagedServerFixture(packagedVersion);
-
-    try {
-      await withServer({ port, dir, serverPath: fixture.serverPath }, async () => {
-        writeFragment(dir);
-        await sleep(300);
-        const html = await fetchHtml(port);
-        assertBrandedWithLogo(html, packagedVersion);
-        assertTelemetryImage(html, packagedVersion);
-        assert(!html.includes('Superpowers vunknown'), 'packaged plugin should not fall back to unknown version');
-      });
-    } finally {
-      cleanup(fixture.root);
-    }
-  });
-
   await test('SUPERPOWERS_DISABLE_TELEMETRY=true omits remote image but keeps local branding', async () => {
     const port = 3453;
     const dir = '/tmp/brainstorm-branding-disabled';

tests/brainstorm-server/package-lock.json

@@ -8,13 +8,13 @@
       "name": "brainstorm-server-tests",
       "version": "1.0.0",
       "dependencies": {
-        "ws": "^8.21.0"
+        "ws": "^8.19.0"
       }
     },
     "node_modules/ws": {
-      "version": "8.21.0",
-      "resolved": "https://registry.npmjs.org/ws/-/ws-8.21.0.tgz",
-      "integrity": "sha512-Vsp28b7DRcimFQvrqu2Wek3z1iYxDCWqHYB8Qsnk/S4RfaCQzPGPyBNuVjJV3cd6UiKtUtp6sNM77gWvzcCH+g==",
+      "version": "8.19.0",
+      "resolved": "https://registry.npmjs.org/ws/-/ws-8.19.0.tgz",
+      "integrity": "sha512-blAT2mjOEIi0ZzruJfIhb3nps74PRWTCz1IjglWEEpQl5XS/UNama6u2/rjFkDDouqr4L67ry+1aGIALViWjDg==",
       "license": "MIT",
       "engines": {
         "node": ">=10.0.0"

tests/brainstorm-server/package.json

@@ -5,6 +5,6 @@
     "test": "node ws-protocol.test.js && node helper.test.js && node browser-launcher.test.js && node auth.test.js && node branding.test.js && node server.test.js && node lifecycle.test.js && bash start-server.test.sh && bash stop-server.test.sh"
   },
   "dependencies": {
-    "ws": "^8.21.0"
+    "ws": "^8.19.0"
   }
 }

tests/claude-code/run-skill-tests.sh

@@ -74,7 +74,6 @@ done
 # List of skill tests to run (fast unit tests)
 tests=(
     "test-worktree-path-policy.sh"
-    "test-sdd-workspace.sh"
     "test-subagent-driven-development.sh"
 )
 

tests/claude-code/test-sdd-workspace.sh

@@ -1,200 +0,0 @@
-#!/usr/bin/env bash
-# Tests for the SDD workspace: scripts/sdd-workspace resolves a self-ignoring,
-# PER-PLAN working-tree directory for SDD artifacts, and the SDD scripts write
-# into their plan's directory.
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
-SDD_SCRIPTS="$REPO_ROOT/skills/subagent-driven-development/scripts"
-
-FAILURES=0
-TEST_ROOT=""
-
-pass() { echo "  [PASS] $1"; }
-fail() {
-    echo "  [FAIL] $1"
-    FAILURES=$((FAILURES + 1))
-}
-
-cleanup() {
-    if [[ -n "$TEST_ROOT" && -d "$TEST_ROOT" ]]; then
-        rm -rf "$TEST_ROOT"
-    fi
-}
-
-main() {
-    echo "=== Test: sdd-workspace ==="
-
-    TEST_ROOT="$(mktemp -d)"
-    trap cleanup EXIT
-
-    # Resolve repo to its physical path so string comparisons match the
-    # helper's output (git rev-parse --show-toplevel resolves symlinks; on
-    # macOS mktemp lives under /var -> /private/var).
-    git init -q -b main "$TEST_ROOT/repo"
-    local repo
-    repo="$(cd "$TEST_ROOT/repo" && git rev-parse --show-toplevel)"
-
-    cat > "$repo/plan-a.md" <<'PLAN'
-# Plan A
-
-## Task 1: First thing
-
-Do the first thing.
-PLAN
-    cat > "$repo/plan-b.md" <<'PLAN'
-# Plan B
-
-## Task 1: Other thing
-
-Do the other thing.
-PLAN
-
-    # --- argument validation ---
-    local rc=0
-    (cd "$repo" && "$SDD_SCRIPTS/sdd-workspace" >/dev/null 2>&1) || rc=$?
-    if [[ "$rc" -eq 2 ]]; then
-        pass "sdd-workspace without a plan errors with exit 2"
-    else
-        fail "sdd-workspace without a plan errors with exit 2"
-        echo "    exit: $rc"
-    fi
-
-    rc=0
-    (cd "$repo" && "$SDD_SCRIPTS/sdd-workspace" no-such-plan.md >/dev/null 2>&1) || rc=$?
-    if [[ "$rc" -eq 2 ]]; then
-        pass "sdd-workspace with a missing plan file errors with exit 2"
-    else
-        fail "sdd-workspace with a missing plan file errors with exit 2"
-        echo "    exit: $rc"
-    fi
-
-    # --- per-plan resolution ---
-    local dir_a dir_b
-    dir_a="$(cd "$repo" && "$SDD_SCRIPTS/sdd-workspace" plan-a.md)"
-    dir_b="$(cd "$repo" && "$SDD_SCRIPTS/sdd-workspace" plan-b.md)"
-
-    if [[ "$dir_a" == "$repo/.superpowers/sdd/plan-a" ]]; then
-        pass "prints <repo-root>/.superpowers/sdd/<plan-basename>"
-    else
-        fail "prints <repo-root>/.superpowers/sdd/<plan-basename>"
-        echo "    got: $dir_a"
-    fi
-
-    if [[ "$dir_a" != "$dir_b" && -d "$dir_a" && -d "$dir_b" ]]; then
-        pass "two plans resolve to two distinct directories"
-    else
-        fail "two plans resolve to two distinct directories"
-        echo "    a: $dir_a"
-        echo "    b: $dir_b"
-    fi
-
-    if [[ -f "$repo/.superpowers/sdd/.gitignore" && "$(cat "$repo/.superpowers/sdd/.gitignore")" == "*" ]]; then
-        pass "self-ignoring .gitignore created at .superpowers/sdd/ with '*'"
-    else
-        fail "self-ignoring .gitignore created at .superpowers/sdd/ with '*'"
-    fi
-
-    printf 'x\n' > "$dir_a/artifact.md"
-    local status
-    status="$(cd "$repo" && git status --porcelain)"
-    # plan-a.md/plan-b.md are intentionally untracked fixture files; only the
-    # workspace must be invisible.
-    if [[ "$status" != *".superpowers"* ]]; then
-        pass "workspace invisible to git status"
-    else
-        fail "workspace invisible to git status"
-        echo "    status: $status"
-    fi
-
-    ( cd "$repo" && git add -A )
-    local staged
-    staged="$(cd "$repo" && git diff --cached --name-only)"
-    if [[ "$staged" != *".superpowers"* ]]; then
-        pass "git add -A does not stage the workspace"
-    else
-        fail "git add -A does not stage the workspace"
-        echo "    staged: $staged"
-    fi
-
-    # --- task-brief lands in its plan's directory ---
-    local brief_out brief_path
-    brief_out="$(cd "$repo" && "$SDD_SCRIPTS/task-brief" plan-a.md 1)"
-    brief_path="$(printf '%s\n' "$brief_out" | sed -n 's/^wrote \(.*\): [0-9][0-9]* lines$/\1/p')"
-    if [[ "$brief_path" == "$repo/.superpowers/sdd/plan-a/task-1-brief.md" ]]; then
-        pass "task-brief writes its brief under the plan's workspace"
-    else
-        fail "task-brief writes its brief under the plan's workspace"
-        echo "    got: $brief_path"
-    fi
-
-    # --- review-package takes the plan first and lands in its directory ---
-    local git_id=(-c user.email=t@example.com -c user.name=t -c commit.gpgsign=false)
-    ( cd "$repo" \
-        && git "${git_id[@]}" commit -qm c1 \
-        && printf 'y\n' > f && git add f \
-        && git "${git_id[@]}" commit -qm c2 )
-    local rp_out rp_path
-    rp_out="$(cd "$repo" && "$SDD_SCRIPTS/review-package" plan-a.md HEAD~1 HEAD)"
-    rp_path="$(printf '%s\n' "$rp_out" | sed -n 's/^wrote \(.*\): [0-9].*$/\1/p')"
-    case "$rp_path" in
-        "$repo/.superpowers/sdd/plan-a/review-"*.diff)
-            pass "review-package writes its diff under the plan's workspace" ;;
-        *)
-            fail "review-package writes its diff under the plan's workspace"
-            echo "    got: $rp_path"
-            ;;
-    esac
-
-    rc=0
-    (cd "$repo" && "$SDD_SCRIPTS/review-package" HEAD~1 HEAD >/dev/null 2>&1) || rc=$?
-    if [[ "$rc" -eq 2 ]]; then
-        pass "review-package without a plan errors with exit 2"
-    else
-        fail "review-package without a plan errors with exit 2"
-        echo "    exit: $rc"
-    fi
-
-    local rp_explicit
-    rp_explicit="$(cd "$repo" && "$SDD_SCRIPTS/review-package" plan-a.md HEAD~1 HEAD "$TEST_ROOT/explicit.diff")"
-    if [[ -s "$TEST_ROOT/explicit.diff" && "$rp_explicit" == *"$TEST_ROOT/explicit.diff"* ]]; then
-        pass "review-package honors an explicit OUTFILE"
-    else
-        fail "review-package honors an explicit OUTFILE"
-        echo "    got: $rp_explicit"
-    fi
-
-    # --- Worktree isolation: a linked worktree resolves its own workspace ---
-    local wt="$TEST_ROOT/wt"
-    ( cd "$repo" && git worktree add -q "$wt" -b wt-feature )
-    local wt_root wt_dir
-    wt_root="$(cd "$wt" && git rev-parse --show-toplevel)"
-    wt_dir="$(cd "$wt" && "$SDD_SCRIPTS/sdd-workspace" plan-a.md)"
-    if [[ "$wt_dir" == "$wt_root/.superpowers/sdd/plan-a" && "$wt_dir" != "$dir_a" ]]; then
-        pass "linked worktree resolves its own distinct workspace"
-    else
-        fail "linked worktree resolves its own distinct workspace"
-        echo "    main: $dir_a"
-        echo "    wt:   $wt_dir"
-    fi
-
-    printf 'y\n' > "$wt_dir/artifact.md"
-    local wt_status
-    wt_status="$(cd "$wt" && git status --porcelain)"
-    if [[ "$wt_status" != *".superpowers"* ]]; then
-        pass "worktree workspace invisible to git status"
-    else
-        fail "worktree workspace invisible to git status"
-        echo "    status: $wt_status"
-    fi
-
-    echo ""
-    if [[ "$FAILURES" -ne 0 ]]; then
-        echo "FAILED: $FAILURES assertion(s)."
-        exit 1
-    fi
-    echo "PASS"
-}
-
-main "$@"

tests/claude-code/test-task-brief.sh

@@ -0,0 +1,117 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+TASK_BRIEF="$REPO_ROOT/skills/subagent-driven-development/scripts/task-brief"
+
+FAILURES=0
+TEST_ROOT=""
+
+pass() {
+    echo "  [PASS] $1"
+}
+
+fail() {
+    echo "  [FAIL] $1"
+    FAILURES=$((FAILURES + 1))
+}
+
+cleanup() {
+    if [[ -n "$TEST_ROOT" && -d "$TEST_ROOT" ]]; then
+        rm -rf "$TEST_ROOT"
+    fi
+}
+
+extract_written_path() {
+    local output="$1"
+    printf '%s\n' "$output" | sed -n 's/^wrote \(.*\): [0-9][0-9]* lines$/\1/p'
+}
+
+assert_not_equals() {
+    local actual="$1"
+    local expected="$2"
+    local description="$3"
+
+    if [[ "$actual" != "$expected" ]]; then
+        pass "$description"
+    else
+        fail "$description"
+        echo "    both were: $actual"
+    fi
+}
+
+assert_file_contains() {
+    local path="$1"
+    local needle="$2"
+    local description="$3"
+
+    if grep -Fq -- "$needle" "$path"; then
+        pass "$description"
+    else
+        fail "$description"
+        echo "    expected $path to contain: $needle"
+    fi
+}
+
+main() {
+    echo "=== Test: task-brief output paths ==="
+
+    TEST_ROOT="$(mktemp -d)"
+    trap cleanup EXIT
+
+    local repo="$TEST_ROOT/repo"
+    local plan="$repo/plan.md"
+    local output_one
+    local output_two
+    local path_one
+    local path_two
+
+    git init -q -b main "$repo"
+
+    cat > "$plan" <<'EOF'
+# Implementation Plan
+
+## Task 1: First thing
+
+Do the first thing.
+
+## Task 2: Second thing
+
+Do the second thing.
+EOF
+
+    output_one="$(cd "$repo" && "$TASK_BRIEF" "$plan" 1)"
+    output_two="$(cd "$repo" && "$TASK_BRIEF" "$plan" 1)"
+    path_one="$(extract_written_path "$output_one")"
+    path_two="$(extract_written_path "$output_two")"
+
+    assert_not_equals "$path_one" "$path_two" "Default task brief paths are unique per invocation"
+    assert_file_contains "$path_one" "## Task 1: First thing" "First default brief contains the requested task"
+    assert_file_contains "$path_two" "## Task 1: First thing" "Second default brief contains the requested task"
+
+    if [[ "$path_one" == "$repo/.git/sdd/"* ]]; then
+        pass "First default brief stays under the repo git metadata directory"
+    else
+        fail "First default brief stays under the repo git metadata directory"
+        echo "    actual: $path_one"
+    fi
+
+    if [[ "$path_two" == "$repo/.git/sdd/"* ]]; then
+        pass "Second default brief stays under the repo git metadata directory"
+    else
+        fail "Second default brief stays under the repo git metadata directory"
+        echo "    actual: $path_two"
+    fi
+
+    if [[ $FAILURES -ne 0 ]]; then
+        echo ""
+        echo "FAILED: $FAILURES assertion(s) failed."
+        exit 1
+    fi
+
+    echo ""
+    echo "PASS"
+}
+
+main "$@"

tests/codex-plugin-sync/test-sync-to-codex-plugin.sh

@@ -200,23 +200,6 @@ EOF
 .private-journal/
 EOF
 
-    cat > "$repo/.gitmodules" <<'EOF'
-[submodule "evals"]
-	path = evals
-	url = git@example.com:example/evals.git
-EOF
-
-    cat > "$repo/.pre-commit-config.yaml" <<'EOF'
-repos:
-  - repo: local
-    hooks:
-      - id: evals-check
-        name: evals check
-        entry: echo evals
-        language: system
-        files: ^evals/
-EOF
-
     if [[ "$with_pure_ignored" == "1" ]]; then
         cat >> "$repo/.gitignore" <<'EOF'
 ignored-cache/
@@ -294,8 +277,6 @@ EOF
         .codex-plugin/plugin.json \
         .kimi-plugin/plugin.json \
         .gitignore \
-        .gitmodules \
-        .pre-commit-config.yaml \
         assets/app-icon.png \
         assets/superpowers-small.svg \
         evals/drill/README.md \
@@ -662,8 +643,6 @@ main() {
     assert_not_contains "$preview_section" ".private-journal/leak.txt" "Preview excludes ignored untracked file"
     assert_not_contains "$preview_section" "ignored-cache/" "Preview excludes pure ignored directories"
     assert_not_contains "$preview_section" "evals/" "Preview excludes eval harness"
-    assert_not_contains "$preview_section" ".gitmodules" "Preview excludes repo submodule metadata"
-    assert_not_contains "$preview_section" ".pre-commit-config.yaml" "Preview excludes repo pre-commit config"
     assert_not_contains "$preview_output" "Overlay file (.codex-plugin/plugin.json) will be regenerated" "Preview omits overlay regeneration note"
     assert_not_contains "$preview_output" "Assets (superpowers-small.svg, app-icon.png) will be seeded from" "Preview omits assets seeding note"
     assert_contains "$preview_section" "skills/example/SKILL.md" "Preview reflects dirty tracked destination file"

tests/codex/test-marketplace-manifest.sh

@@ -1,76 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
-MARKETPLACE="$REPO_ROOT/.agents/plugins/marketplace.json"
-
-python3 - "$MARKETPLACE" "$REPO_ROOT" <<'PY'
-import json
-import sys
-from pathlib import Path
-
-marketplace_path = Path(sys.argv[1])
-repo_root = Path(sys.argv[2])
-
-if not marketplace_path.exists():
-    raise AssertionError(".agents/plugins/marketplace.json must exist")
-
-marketplace = json.loads(marketplace_path.read_text(encoding="utf-8"))
-
-def assert_equal(actual, expected, label):
-    if actual != expected:
-        raise AssertionError(f"{label}: expected {expected!r}, got {actual!r}")
-
-assert_equal(marketplace.get("name"), "superpowers-dev", "marketplace name")
-assert_equal(
-    marketplace.get("interface", {}).get("displayName"),
-    "Superpowers Dev",
-    "marketplace display name",
-)
-
-plugins = marketplace.get("plugins")
-if not isinstance(plugins, list):
-    raise AssertionError("plugins must be a list")
-
-matching_plugins = [plugin for plugin in plugins if plugin.get("name") == "superpowers"]
-assert_equal(len(matching_plugins), 1, "superpowers plugin entry count")
-
-plugin = matching_plugins[0]
-assert_equal(plugin.get("source"), {"source": "url", "url": "./"}, "plugin source")
-assert_equal(
-    plugin.get("policy"),
-    {"installation": "AVAILABLE", "authentication": "ON_INSTALL"},
-    "plugin policy",
-)
-assert_equal(plugin.get("category"), "Developer Tools", "plugin category")
-
-plugin_manifest = repo_root / ".codex-plugin" / "plugin.json"
-if not plugin_manifest.exists():
-    raise AssertionError(".codex-plugin/plugin.json must exist")
-
-manifest = json.loads(plugin_manifest.read_text(encoding="utf-8"))
-assert_equal(manifest.get("name"), plugin.get("name"), "plugin manifest name")
-
-# Codex auto-discovers a plugin's hooks/hooks.json whenever the Codex manifest
-# has no `hooks` field: load_plugin_hooks falls back to a hardcoded
-# DEFAULT_HOOKS_CONFIG_FILE = "hooks/hooks.json" and registers it. That file is
-# the Claude Code SessionStart hook, it is tracked in this repo, and this
-# marketplace installs the whole repo root (source url "./"), so on Codex the
-# fallback re-registers the SessionStart hook and its install-time trust prompt.
-# Declaring an empty inline hooks object ({}) parses as an empty inline hook set
-# and suppresses the auto-discovery. An absent field, an empty array ([]), and
-# an empty inline list all collapse back to the fallback, so the value must be
-# exactly an empty object.
-hooks_config = repo_root / "hooks" / "hooks.json"
-if not hooks_config.exists():
-    raise AssertionError("hooks/hooks.json must exist (Claude Code SessionStart hook)")
-
-assert_equal(
-    manifest.get("hooks"),
-    {},
-    "Codex manifest must declare empty hooks {} to suppress hooks/hooks.json auto-discovery",
-)
-
-print("Codex marketplace manifest looks good")
-PY

tests/codex/test-package-codex-plugin.sh

@@ -1,292 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
-SCRIPT_UNDER_TEST="$REPO_ROOT/scripts/package-codex-plugin.sh"
-
-FAILURES=0
-TEST_ROOT="$(mktemp -d)"
-
-cleanup() {
-  rm -rf "$TEST_ROOT"
-}
-trap cleanup EXIT
-
-pass() {
-  echo "  [PASS] $1"
-}
-
-fail() {
-  echo "  [FAIL] $1"
-  FAILURES=$((FAILURES + 1))
-}
-
-assert_equals() {
-  local actual="$1"
-  local expected="$2"
-  local description="$3"
-
-  if [[ "$actual" == "$expected" ]]; then
-    pass "$description"
-  else
-    fail "$description"
-    echo "    expected: $expected"
-    echo "    actual:   $actual"
-  fi
-}
-
-assert_contains() {
-  local haystack="$1"
-  local needle="$2"
-  local description="$3"
-
-  if printf '%s' "$haystack" | grep -Fq -- "$needle"; then
-    pass "$description"
-  else
-    fail "$description"
-    echo "    expected to find: $needle"
-  fi
-}
-
-assert_not_matches() {
-  local haystack="$1"
-  local pattern="$2"
-  local description="$3"
-
-  if printf '%s' "$haystack" | grep -Eq -- "$pattern"; then
-    fail "$description"
-    echo "    did not expect to match: $pattern"
-  else
-    pass "$description"
-  fi
-}
-
-list_archive() {
-  local archive_path="$1"
-
-  case "$archive_path" in
-    *.tar.gz|*.tgz)
-      tar -tzf "$archive_path"
-      ;;
-    *.zip)
-      unzip -Z1 "$archive_path"
-      ;;
-    *)
-      unzip -Z1 "$archive_path"
-      ;;
-  esac
-}
-
-normalize_archive_paths() {
-  sed 's#/$##' | LC_ALL=C sort
-}
-
-extract_archive() {
-  local archive_path="$1"
-  local destination="$2"
-
-  mkdir -p "$destination"
-  case "$archive_path" in
-    *.tar.gz|*.tgz)
-      tar -xzf "$archive_path" -C "$destination"
-      ;;
-    *.zip)
-      unzip -q "$archive_path" -d "$destination"
-      ;;
-    *)
-      unzip -q "$archive_path" -d "$destination"
-      ;;
-  esac
-}
-
-read_archive_file() {
-  local archive_path="$1"
-  local file_path="$2"
-
-  case "$archive_path" in
-    *.tar.gz|*.tgz)
-      tar -xOf "$archive_path" "$file_path"
-      ;;
-    *.zip)
-      unzip -p "$archive_path" "$file_path"
-      ;;
-    *)
-      unzip -p "$archive_path" "$file_path"
-      ;;
-  esac
-}
-
-write_metadata_fixture() {
-  local destination="$1"
-  local skill
-
-  while IFS= read -r skill; do
-    mkdir -p "$destination/skills/$skill/agents"
-    cat >"$destination/skills/$skill/agents/openai.yaml" <<EOF
-interface:
-  display_name: "$skill"
-  short_description: "Fixture metadata for $skill"
-EOF
-  done < <(find "$REPO_ROOT/skills" -mindepth 1 -maxdepth 1 -type d -print | sed 's#.*/##' | sort)
-}
-
-echo "Codex package archive tests"
-
-metadata_source="$TEST_ROOT/metadata-source"
-archive="$TEST_ROOT/superpowers"
-tar_archive="$TEST_ROOT/superpowers.tar.gz"
-extracted="$TEST_ROOT/extracted"
-tar_extracted="$TEST_ROOT/tar-extracted"
-write_metadata_fixture "$metadata_source"
-
-source_hooks="$(python3 -c 'import json; print(json.load(open("'"$REPO_ROOT"'/.codex-plugin/plugin.json")).get("hooks"))')"
-assert_equals "$source_hooks" "{}" "source Codex manifest suppresses local hook auto-discovery"
-
-if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --output "$archive" 2>&1)"; then
-  pass "package script exits successfully"
-else
-  fail "package script exits successfully"
-  printf '%s\n' "$output" | sed 's/^/      /'
-fi
-
-if [[ -f "$archive" ]]; then
-  pass "package script writes archive"
-else
-  fail "package script writes archive"
-fi
-
-assert_contains "$output" "Archive:" "reports archive path"
-assert_contains "$output" "Format:  zip" "reports default zip format"
-assert_contains "$output" "SHA-256:" "reports archive checksum"
-
-extract_archive "$archive" "$extracted"
-
-archive_paths="$(list_archive "$archive" | normalize_archive_paths)"
-unexpected_pattern='(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)'
-assert_not_matches "$archive_paths" "$unexpected_pattern" "archive excludes source-only paths"
-assert_contains "$archive_paths" ".codex-plugin/plugin.json" "archive includes Codex manifest"
-assert_contains "$archive_paths" "skills/brainstorming/SKILL.md" "archive includes skills"
-assert_contains "$archive_paths" "skills/brainstorming/agents/openai.yaml" "archive includes OpenAI skill metadata"
-assert_contains "$archive_paths" "assets/app-icon.png" "archive includes app icon"
-assert_contains "$archive_paths" "assets/superpowers-small.svg" "archive includes composer icon"
-
-manifest_summary="$(read_archive_file "$archive" .codex-plugin/plugin.json | python3 -c 'import json,sys; data=json.load(sys.stdin); print("\t".join([data["name"], data["version"], data["skills"], str(data.get("hooks"))]))')"
-expected_version="$(python3 -c 'import json; print(json.load(open("'"$REPO_ROOT"'/.codex-plugin/plugin.json"))["version"])')"
-assert_equals "$manifest_summary" "superpowers	$expected_version	./skills/	$source_hooks" "archive manifest preserves source hooks"
-
-skill_count="$(find "$extracted/skills" -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ')"
-metadata_count="$(find "$extracted/skills" -path '*/agents/openai.yaml' -type f | wc -l | tr -d ' ')"
-assert_equals "$metadata_count" "$skill_count" "every packaged skill has OpenAI metadata"
-
-if [[ -x "$extracted/skills/subagent-driven-development/scripts/task-brief" ]]; then
-  pass "archive preserves executable script mode"
-else
-  fail "archive preserves executable script mode"
-fi
-
-zip_times="$(python3 - "$archive" <<'PY'
-import sys
-import zipfile
-
-with zipfile.ZipFile(sys.argv[1]) as archive:
-    print("\n".join(sorted({str(info.date_time) for info in archive.infolist()})))
-PY
-)"
-assert_equals "$zip_times" "(1980, 1, 1, 0, 0, 0)" "zip archive normalizes entry timestamps"
-
-if tar_output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --format tar.gz --output "$tar_archive" 2>&1)"; then
-  pass "package script writes explicit tar.gz archive"
-else
-  fail "package script writes explicit tar.gz archive"
-  printf '%s\n' "$tar_output" | sed 's/^/      /'
-fi
-assert_contains "$tar_output" "Format:  tar.gz" "reports explicit tar.gz format"
-
-extract_archive "$tar_archive" "$tar_extracted"
-tar_archive_paths="$(list_archive "$tar_archive" | normalize_archive_paths)"
-assert_equals "$tar_archive_paths" "$archive_paths" "zip and tar.gz archives contain the same paths"
-
-tar_task_brief_mode="$(tar -tzvf "$tar_archive" skills/subagent-driven-development/scripts/task-brief | awk '{print $1}')"
-assert_equals "$tar_task_brief_mode" "-rwxr-xr-x" "tar.gz archive preserves executable script mode"
-
-tar_metadata_times="$(tar -tzvf "$tar_archive" | awk '{print $6, $7, $8}' | sort -u)"
-assert_equals "$tar_metadata_times" "Dec 31 1969" "tar.gz archive normalizes entry timestamps"
-
-metadata_archive="$TEST_ROOT/metadata-source.tar.gz"
-metadata_zip="$TEST_ROOT/metadata-source.zip"
-archive_from_tar_source="$TEST_ROOT/superpowers-from-tar-source.zip"
-archive_from_zip_source="$TEST_ROOT/superpowers-from-zip-source.zip"
-(
-  cd "$metadata_source"
-  tar -czf "$metadata_archive" .
-  zip -X -q -r "$metadata_zip" .
-)
-
-if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_archive" --output "$archive_from_tar_source" 2>&1)"; then
-  pass "package script accepts tarball metadata source"
-else
-  fail "package script accepts tarball metadata source"
-  printf '%s\n' "$output" | sed 's/^/      /'
-fi
-
-if cmp -s "$archive" "$archive_from_tar_source"; then
-  pass "tarball metadata source produces identical archive"
-else
-  fail "tarball metadata source produces identical archive"
-fi
-
-if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_zip" --output "$archive_from_zip_source" 2>&1)"; then
-  pass "package script accepts zip metadata source"
-else
-  fail "package script accepts zip metadata source"
-  printf '%s\n' "$output" | sed 's/^/      /'
-fi
-
-if cmp -s "$archive" "$archive_from_zip_source"; then
-  pass "zip metadata source produces identical archive"
-else
-  fail "zip metadata source produces identical archive"
-fi
-
-incomplete_metadata="$TEST_ROOT/incomplete-metadata"
-mkdir -p "$incomplete_metadata/skills/brainstorming/agents"
-cp "$metadata_source/skills/brainstorming/agents/openai.yaml" \
-  "$incomplete_metadata/skills/brainstorming/agents/openai.yaml"
-
-set +e
-missing_output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$incomplete_metadata" --output "$TEST_ROOT/missing.tar.gz" 2>&1)"
-missing_status=$?
-set -e
-if [[ "$missing_status" -ne 0 ]]; then
-  pass "package script rejects incomplete metadata source"
-else
-  fail "package script rejects incomplete metadata source"
-fi
-assert_contains "$missing_output" "ERROR: metadata source is incomplete" "incomplete metadata reports clear error"
-
-dirty_repo="$TEST_ROOT/dirty-repo"
-git clone -q --no-local "$REPO_ROOT" "$dirty_repo"
-printf '\n# dirty fixture\n' >>"$dirty_repo/README.md"
-set +e
-dirty_output="$(
-  cd "$dirty_repo"
-  scripts/package-codex-plugin.sh \
-    --metadata-source "$metadata_source" \
-    --output "$TEST_ROOT/dirty.zip" 2>&1
-)"
-dirty_status=$?
-set -e
-if [[ "$dirty_status" -ne 0 ]]; then
-  pass "package script rejects dirty worktree by default"
-else
-  fail "package script rejects dirty worktree by default"
-fi
-assert_contains "$dirty_output" "Working tree has uncommitted changes:" "dirty worktree reports changed files"
-
-if [[ "$FAILURES" -eq 0 ]]; then
-  echo "All Codex package archive tests passed"
-else
-  echo "$FAILURES Codex package archive test(s) failed"
-  exit 1
-fi

tests/hooks/test-session-start.sh

@@ -4,6 +4,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
 HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start"
+CODEX_HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start-codex"
 WRAPPER_UNDER_TEST="$REPO_ROOT/hooks/run-hook.cmd"
 
 FAILURES=0
@@ -153,15 +154,35 @@ assert_command_output \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
     bash "$HOOK_UNDER_TEST"
 
-wrapper_home="$(make_home run-hook-wrapper)"
+codex_home="$(make_home codex-plugin-hooks)"
+codex_data="$TEST_ROOT/codex-plugin-hooks/data"
+mkdir -p "$codex_data"
 assert_command_output \
-    "run-hook.cmd wrapper dispatches to the named session-start script" \
+    "Codex plugin hooks use dedicated script and emit nested SessionStart additionalContext" \
     "nested" \
     "" \
     "" \
-    "$wrapper_home" \
+    "$codex_home" \
+    PLUGIN_DATA="$codex_data" \
+    CLAUDE_PLUGIN_DATA="$codex_data" \
+    PLUGIN_ROOT="$REPO_ROOT" \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
-    bash "$WRAPPER_UNDER_TEST" session-start
+    bash "$CODEX_HOOK_UNDER_TEST"
+
+codex_wrapper_home="$(make_home codex-wrapper)"
+codex_wrapper_data="$TEST_ROOT/codex-wrapper/data"
+mkdir -p "$codex_wrapper_data"
+assert_command_output \
+    "Codex wrapper path dispatches to dedicated script" \
+    "nested" \
+    "" \
+    "" \
+    "$codex_wrapper_home" \
+    PLUGIN_DATA="$codex_wrapper_data" \
+    CLAUDE_PLUGIN_DATA="$codex_wrapper_data" \
+    PLUGIN_ROOT="$REPO_ROOT" \
+    CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
+    bash "$WRAPPER_UNDER_TEST" session-start-codex
 
 cursor_home="$(make_home cursor)"
 assert_command_output \
@@ -196,6 +217,21 @@ assert_command_output \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
     bash "$HOOK_UNDER_TEST"
 
+codex_legacy_home="$(make_home codex-legacy-warning-removed)"
+codex_legacy_data="$TEST_ROOT/codex-legacy-warning-removed/data"
+mkdir -p "$codex_legacy_home/.config/superpowers/skills" "$codex_legacy_data"
+assert_command_output \
+    "Codex SessionStart omits obsolete legacy custom-skill warning" \
+    "nested" \
+    "" \
+    "Superpowers now uses"$'\037'"~/.config/superpowers/skills"$'\037'"~/.claude/skills"$'\037'"legacy" \
+    "$codex_legacy_home" \
+    PLUGIN_DATA="$codex_legacy_data" \
+    CLAUDE_PLUGIN_DATA="$codex_legacy_data" \
+    PLUGIN_ROOT="$REPO_ROOT" \
+    CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
+    bash "$CODEX_HOOK_UNDER_TEST"
+
 if [[ "$FAILURES" -gt 0 ]]; then
     echo "STATUS: FAILED ($FAILURES failure(s))"
     exit 1