test(sdd): lock in per-worktree workspace isolation (#1780)

It broke plugin installs for some users (#1778, #1774). The eval harness
now lives in its own repo, separate from the published plugin.

.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": "6.0.0",
+      "version": "6.0.2",
       "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": "6.0.0",
+  "version": "6.0.2",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.0.0",
+  "version": "6.0.2",
   "description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
   "author": {
     "name": "Jesse Vincent",

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "superpowers",
   "displayName": "Superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.0.0",
+  "version": "6.0.2",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.gitignore

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

.gitmodules

@@ -1,3 +0,0 @@
-[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": "6.0.0",
+  "version": "6.0.2",
   "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 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/`.
+Skill-behavior evals live in [superpowers-evals](https://github.com/prime-radiant-inc/superpowers-evals/), cloned into `evals/` — see `evals/README.md` for setup. 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

@@ -262,7 +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 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`.
+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`.
 
 See `skills/writing-skills/SKILL.md` for the complete guide.
 

RELEASE-NOTES.md

@@ -1,5 +1,18 @@
 # Superpowers Release Notes
 
+## 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. 

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.0.0",
+  "version": "6.0.2",
   "contextFileName": "GEMINI.md"
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.0.0",
+  "version": "6.0.2",
   "description": "Superpowers skills and runtime bootstrap for coding agents",
   "type": "module",
   "main": ".opencode/plugins/superpowers.js",

scripts/sync-to-codex-plugin.sh

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

skills/brainstorming/scripts/server.cjs

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

skills/subagent-driven-development/SKILL.md

@@ -251,7 +251,7 @@ sequences — the single most expensive failure observed. Track progress in
 a ledger file, not only in todos.
 
 - At skill start, check for a ledger:
-  `cat "$(git rev-parse --git-path sdd)/progress.md"`. Tasks listed there
+  `cat "$(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.
 - When a task's review comes back clean, append one line to the ledger in

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

@@ -5,9 +5,8 @@
 # tasks intact.
 #
 # Usage: review-package BASE HEAD [OUTFILE]
-# Default OUTFILE: <git-dir>/sdd/review-<base7>..<head7>.diff — unique per
+# Default OUTFILE: <repo-root>/.superpowers/sdd/review-<base7>..<head7>.diff
-# repo instance and per range, so concurrent sessions cannot collide and a
+# (named per range, so a re-review after fixes gets a distinct fresh file).
-# re-review after fixes always gets a distinctly named fresh file.
 set -euo pipefail
 
 if [ $# -lt 2 ] || [ $# -gt 3 ]; then
@@ -24,9 +23,7 @@ git rev-parse --verify --quiet "$head" >/dev/null || { echo "bad HEAD: $head" >&
 if [ $# -eq 3 ]; then
   out=$3
 else
-  dir=$(git rev-parse --git-path sdd)
+  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace")
-  mkdir -p "$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

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+# Resolve and ensure the working-tree directory SDD uses for its short-lived
+# artifacts: task briefs, implementer reports, review packages, and the
+# progress ledger. Print the directory's absolute path.
+#
+# 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 keeps the 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
+set -euo pipefail
+
+root=$(git rev-parse --show-toplevel)
+dir="$root/.superpowers/sdd"
+mkdir -p "$dir"
+printf '*\n' > "$dir/.gitignore"
+cd "$dir" && pwd

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

@@ -4,8 +4,8 @@
 # through the controller's context.
 #
 # Usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]
-# Default OUTFILE: <git-dir>/sdd/task-<N>-brief.md — unique per repo
+# Default OUTFILE: <repo-root>/.superpowers/sdd/task-<N>-brief.md
-# instance, so concurrent sessions cannot collide.
+# (per worktree; concurrent runs in the same working tree share it).
 set -euo pipefail
 
 if [ $# -lt 2 ] || [ $# -gt 3 ]; then
@@ -20,9 +20,7 @@ n=$2
 if [ $# -eq 3 ]; then
   out=$3
 else
-  dir=$(git rev-parse --git-path sdd)
+  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace")
-  mkdir -p "$dir"
-  dir=$(cd "$dir" && pwd)
   out="$dir/task-${n}-brief.md"
 fi
 

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 = {} }) {
+function startServer({ port, dir, env = {}, serverPath = SERVER_PATH }) {
   cleanup(dir);
-  return spawn('node', [SERVER_PATH], {
+  return spawn('node', [serverPath], {
     env: {
       ...process.env,
       BRAINSTORM_PORT: String(port),
@@ -74,6 +74,21 @@ 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 {
@@ -104,13 +119,13 @@ async function test(name, fn) {
   }
 }
 
-function assertBrandedWithLogo(html) {
+function assertBrandedWithLogo(html, version = PACKAGE_VERSION) {
   assert(
-    html.includes(`Superpowers v${PACKAGE_VERSION}`),
+    html.includes(`Superpowers v${version}`),
     'branding text should include dynamic package version'
   );
   assert(
-    !html.includes(`Superpowers v${PACKAGE_VERSION} by`),
+    !html.includes(`Superpowers v${version} by`),
     'branding text should not include "by" when the logo is visible'
   );
   assert(
@@ -139,15 +154,15 @@ function assertBrandedWithLogo(html) {
   );
 }
 
-function assertBrandedFallbackText(html) {
+function assertBrandedFallbackText(html, version = PACKAGE_VERSION) {
   assert(
-    html.includes(`Prime Radiant Superpowers v${PACKAGE_VERSION}`),
+    html.includes(`Prime Radiant Superpowers v${version}`),
     'disabled telemetry should keep plain text Prime Radiant/Superpowers branding'
   );
 }
 
-function assertTelemetryImage(html) {
+function assertTelemetryImage(html, version = PACKAGE_VERSION) {
-  const expectedUrl = `${ASSET_URL}?v=${encodeURIComponent(PACKAGE_VERSION)}`;
+  const expectedUrl = `${ASSET_URL}?v=${encodeURIComponent(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=');
@@ -255,6 +270,26 @@ 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/claude-code/test-sdd-workspace.sh

@@ -0,0 +1,142 @@
+#!/usr/bin/env bash
+# Tests for the SDD workspace: scripts/sdd-workspace resolves a self-ignoring
+# working-tree directory for SDD artifacts, and the SDD scripts write into it.
+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 "$TEST_ROOT/repo" && git rev-parse --show-toplevel)"
+
+    local dir
+    dir="$(cd "$repo" && "$SDD_SCRIPTS/sdd-workspace")"
+
+    if [[ "$dir" == "$repo/.superpowers/sdd" ]]; then
+        pass "prints <repo-root>/.superpowers/sdd"
+    else
+        fail "prints <repo-root>/.superpowers/sdd"
+        echo "    got: $dir"
+    fi
+
+    if [[ -f "$repo/.superpowers/sdd/.gitignore" && "$(cat "$repo/.superpowers/sdd/.gitignore")" == "*" ]]; then
+        pass "self-ignoring .gitignore created with '*'"
+    else
+        fail "self-ignoring .gitignore created with '*'"
+    fi
+
+    printf 'x\n' > "$repo/.superpowers/sdd/artifact.md"
+    local status
+    status="$(cd "$repo" && git status --porcelain)"
+    if [[ -z "$status" ]]; 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 [[ -z "$staged" ]]; then
+        pass "git add -A does not stage the workspace"
+    else
+        fail "git add -A does not stage the workspace"
+        echo "    staged: $staged"
+    fi
+
+    cat > "$repo/plan.md" <<'PLAN'
+# Plan
+
+## Task 1: First thing
+
+Do the first thing.
+PLAN
+
+    local brief_out brief_path
+    brief_out="$(cd "$repo" && "$SDD_SCRIPTS/task-brief" plan.md 1)"
+    brief_path="$(printf '%s\n' "$brief_out" | sed -n 's/^wrote \(.*\): [0-9][0-9]* lines$/\1/p')"
+    case "$brief_path" in
+        "$repo/.superpowers/sdd/"*) pass "task-brief writes its brief under the workspace" ;;
+        *)
+            fail "task-brief writes its brief under the workspace"
+            echo "    got: $brief_path"
+            ;;
+    esac
+
+    local git_id=(-c user.email=t@example.com -c user.name=t -c commit.gpgsign=false)
+    ( cd "$repo" \
+        && git add plan.md \
+        && 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" && "$SDD_SCRIPTS/review-package" HEAD~1 HEAD)"
+    rp_path="$(printf '%s\n' "$rp_out" | sed -n 's/^wrote \(.*\): [0-9].*$/\1/p')"
+    case "$rp_path" in
+        "$repo/.superpowers/sdd/"*) pass "review-package writes its diff under the workspace" ;;
+        *)
+            fail "review-package writes its diff under the workspace"
+            echo "    got: $rp_path"
+            ;;
+    esac
+
+    # --- Worktree isolation: a linked worktree resolves its own workspace ---
+    local wt="$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" && "$SDD_SCRIPTS/sdd-workspace")"
+    if [[ "$wt_dir" == "$wt_root/.superpowers/sdd" && "$wt_dir" != "$dir" ]]; then
+        pass "linked worktree resolves its own distinct workspace"
+    else
+        fail "linked worktree resolves its own distinct workspace"
+        echo "    main: $dir"
+        echo "    wt:   $wt_dir"
+    fi
+
+    printf 'y\n' > "$wt/.superpowers/sdd/artifact.md"
+    local wt_status
+    wt_status="$(cd "$wt" && git status --porcelain)"
+    if [[ -z "$wt_status" ]]; 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/codex-plugin-sync/test-sync-to-codex-plugin.sh

@@ -200,6 +200,23 @@ 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/
@@ -277,6 +294,8 @@ 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 \
@@ -643,6 +662,8 @@ 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"