feat(sdd): evidence-locked gate claims in the implementer report

Responds to maintainer review asking for better implementer
self-reflection. The report format already demands command+output for
TDD evidence and fix-round covering tests, but the full-suite claim
asked only for prose — and that is the claim that rotted in the field:
three consecutive fix rounds shipped a "full suite passes" claim the
fix reviewer found unreproducible, each time because the suite had run
before later edits made the result stale.

Two changes, both at the moment the report is written: every claimed
gate needs its exact command and the tail of fresh output — fresh
meaning after the final edit, otherwise rerun or report the gate as
unverified — and a missing pasted output is itself a defect for the
reviewer to flag, which puts enforcement at the consumption side the
same way the dispatch hints do. Fix reports claiming a full-suite pass
need a fresh run, not the pre-findings one.

This is verification-before-completion's gate function relocated into
the one prompt subagents actually receive.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.md

@@ -3,6 +3,12 @@
 Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
 
 
+## We're Hiring!
+
+We're hiring someone to help out full time with Superpowers community and code work. 
+You can read about the job at https://primeradiant.com/jobs/superpowers-community-engineer/
+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), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).

docs/superpowers/specs/2026-07-30-codex-efficiency-fixes-design.md

@@ -1,252 +0,0 @@
-# Codex Efficiency Fixes — Design
-
-Date: 2026-07-30
-Status: approved by Jesse (in-session)
-Branch: `codex-efficiency-fixes` off `dev`
-
-## Sources
-
-- Eval campaign closeout: `superpowers-autoresearch/reports/2026-07-codex-efficiency-campaign.md`
-  (treatment table §4; every treatment below has a scorer and a measured
-  `dev` baseline).
-- Codex source recon: `superpowers-autoresearch/docs/2026-07-29-codex-multiagent-v2-capabilities.md`
-  (file:line citations against the Codex CLI source; grounds T2, T3, T5).
-- Published experiment write-ups: `superpowers-evals/docs/experiments/`.
-- Drew's spinout stack (PRs #2036, #2035) is **evidence, not adopted text**:
-  Jesse wants to dig into those fixes in more detail before adopting any
-  of them; they inform the problem statements only.
-
-## Goal
-
-Ship the five evidence-strong treatments from the codex-efficiency eval
-campaign as superpowers skill/doc changes, each graded against its
-pre-registered criterion by the campaign's scorers before its PR is cut.
-Phase 2 (everything else in the closeout treatment table) follows, each
-item gated on new baseline work first.
-
-## Scope decisions (settled with Jesse)
-
-- **Phase 1 = the evidence-strong five** (T1–T5 below). Phase 2 items
-  each need a failing baseline before any fix ships (discrimination
-  rule: inconclusive-by-zero is a stop).
-- **One branch, PR per treatment.** Development and batteries happen on
-  `codex-efficiency-fixes`; when a treatment beats its criterion, it is
-  cut into its own PR against `dev` with its eval evidence. No merge
-  without Jesse's per-PR approval.
-- **T4 ships cross-harness with a global regression battery** (Claude
-  Code, Codex, Gemini), variant C shape: ceremony scales, approval never
-  does.
-
-## The five treatments
-
-### T1. SDD worker-review prohibition
-
-**Evidence:** 9/9 depth-2 spawns across 4 corpora were implementer-issued
-reviewers; all 9 were same-task duplicates of the review the controller
-dispatches anyway. The dispatch contract never says review is not the
-worker's job; "self-review" in the implementer prompt gets reified into a
-reviewer subagent on harnesses where children can spawn (Codex).
-
-**Changes:**
-- `skills/subagent-driven-development/implementer-prompt.md`: an explicit
-  "You do not dispatch subagents" clause — self-review means reading your
-  own diff; the controller owns all review dispatch; a reviewer you spawn
-  duplicates a review the process already provides.
-- `skills/subagent-driven-development/SKILL.md`: one dispatch-contract
-  line in the task loop, plus a Red Flags row: "An independent review
-  would strengthen my report" → review is the controller's next step;
-  your reviewer is a duplicate seat.
-- Harness-agnostic wording (no-op where children cannot spawn).
-
-**Graded by:** `score_e6.py` (depth-2 spawns by spawner role, duplicate
-review families); `score_e5.py` for the same-scope variant.
-**Baseline:** 9/9 worker-issued, 0 counter-examples.
-**Criterion:** 0 worker-issued depth-2 spawns AND review coverage
-preserved (every task still gets exactly one controller-dispatched task
-review).
-
-### T2. Event-driven waiting
-
-**Evidence:** 60–78% of `wait_agent` calls time out in every corpus
-(dev 67.1%, spinout 60.2%). Source recon: V2 waits are event
-subscriptions, not polls — one long wait has the same wake latency as a
-10s poll at ~1/90th the calls; a completed child's FINAL_ANSWER is pushed
-into the parent's mailbox and drained into the next model request with no
-wait at all.
-
-**Changes** (`skills/using-superpowers/references/codex-tools.md`):
-- Never short-timeout poll.
-- While local work remains, do not wait — child results arrive with your
-  next turn via the mailbox.
-- When genuinely idle, issue ONE `wait_agent` with a long `timeout_ms`
-  (900000+; harness max 3600000).
-- V2 caveat stated: completion mail carries `trigger_turn=false` and will
-  not wake an idle controller — that is the one job `wait_agent` has.
-
-**Graded by:** `score_e7.py` (timeout rate, inter-poll cadence,
-cache-rebill estimate — the rebill figure stays labeled as an estimate).
-**Baseline:** dev 67.1% timeout rate.
-**Criterion:** timeout rate < 25% with no loss of task completion.
-
-### T3. codex-tools.md corrections
-
-**Evidence:** five claims in the current guidance are contradicted by the
-Codex source (all file:line-cited in the capabilities doc):
-1. `close_agent` does not exist in multi-agent V2 (V1-only). V2 LRU-evicts
-   finished children automatically; not closing costs nothing;
-   `followup_task` transparently reloads an evicted child.
-2. Fix rounds can always resume the implementer via `followup_task` —
-   dev's "if your harness cannot send another message to a spawned agent,
-   dispatch each fix round as a fresh implementer" branch is dead on V2.
-3. Role files (`~/.codex/agents/**.toml`) DO attach to spawns via
-   `agent_type` on isolated forks (0.145+).
-4. Full-history forks accept `model`/`reasoning_effort` overrides; only
-   `agent_type` is refused. (Isolated forks remain the SDD guidance for
-   context-hygiene reasons, stated accurately.)
-5. Dispatch guidance must never name non-V2 model presets — the V2 spawn
-   allowlist is v2 presets only; others hard-error.
-
-**Changes:** rewrite the multi-agent paragraph of
-`skills/using-superpowers/references/codex-tools.md` to be
-version-honest (V1 vs V2 behavior labeled where they differ).
-
-**Graded by:** source citation (already verified); no scorer regressions
-on the shared battery. `score_e8.py` is retained as a V1/V2 schema
-detector, not a hygiene grader — no `close_agent` checklist ships.
-
-### T4. Brainstorming three-path router (variant C: approval always)
-
-**Evidence:** micro — the current HARD-GATE text pushes a bounded task to
-FULL ceremony 5/5, while Z-null (no guidance) and a three-path router
-both differentiate 5/5: the absolute wording suppresses discrimination
-the model draws natively. FULL battery — ceremony volume scales
-moderately (16.7 vs 24.0 tool calls, bounded vs arch), but the
-two-document ritual (spec file → plan file) ran unconditionally in every
-rep. The measured waste is the unconditional artifact ritual, not the
-approval gate.
-
-**Design (variant C):** three paths scale the ARTIFACT; every path keeps
-human approval before implementation:
-- **Spike** (feasibility question, explicitly throwaway): present the
-  question and the intended probe in 2–3 sentences, get a nod, go. No
-  docs. Findings return as a recommendation; anything built stays labeled
-  throwaway.
-- **Bounded** (well-scoped change to an existing, understood flow):
-  present a short design in chat, get approval, implement. No spec file,
-  no writing-plans invocation.
-- **Architectural** (restructures components, new subsystem, public
-  interface change): the full current flow — spec doc, review,
-  writing-plans.
-
-**Guards (all ship with the router):**
-- Classification is said out loud ("this looks bounded, so I'll present a
-  short design here rather than write a spec") so the human can override.
-- When in doubt between two paths, take the heavier one.
-- One-way ratchet: hidden complexity discovered mid-path upgrades the
-  path; never downgrade mid-task.
-- New Red Flags rows targeting classification-as-escape-hatch ("I'll call
-  it bounded to skip the doc").
-
-**Changes** (`skills/brainstorming/SKILL.md`): HARD-GATE keeps "no
-implementation before approval" and drops "regardless of perceived
-simplicity" as the ceremony driver; anti-pattern section reframed (the
-sin is skipping approval, not skipping documents); checklist steps 6–9
-become the architectural path; process-flow graph gains the router; Red
-Flags rows added. This is carefully-tuned content — the edit follows
-writing-skills methodology and ships only with the full eval evidence
-below.
-
-**Graded by (three layers):**
-1. **Micro** (`ceremony-path-micro.py`, adapted): variant C literal text,
-   plus adversarially ambiguous briefs the campaign never tested (a task
-   that pattern-matches bounded but hides a public interface change).
-   Criteria: spike/bounded/arch differentiate (≥4/5 per cell); ambiguous
-   briefs escalate to FULL (≥4/5); arch never downgrades (5/5).
-2. **Codex ceremony battery:** `cx-ceremony-{spike,bounded,arch}` on the
-   fix arm, 3 reps each, `score_e4.py` census. Criteria: bounded reps
-   show an approval turn but zero committed spec files and zero
-   writing-plans ritual; arch reps keep the full two-doc flow; spike reps
-   stay minimal.
-3. **Global regression battery:** the same three ceremony scenarios on
-   Claude Code and Gemini (rig work: those scenarios are currently
-   codex-gated), 3 reps each; plus the triggering acceptance check
-   ("Let's make a react todo list" auto-triggers brainstorming into the
-   full/architectural path) on all three harnesses.
-
-### T5. Explicit model on child-issued spawns
-
-**Evidence:** root spawns are 100% explicit-model at CLI 0.146 (dev
-14/14); the live gap is depth-2 — 2/2 child-issued spawns omitted
-`model`. Source recon: `model` without `reasoning_effort` resets effort
-to the MODEL's default, not the parent's.
-
-**Changes** (`skills/using-superpowers/references/codex-tools.md`):
-- Every spawn you issue — including as a child — sets `model` AND
-  `reasoning_effort`; the effort-reset trap is named.
-- Advise `[agents].default_subagent_model` and
-  `[agents].default_subagent_reasoning_effort` in `~/.codex/config.toml`
-  as the machine-level backstop for anything that slips through.
-
-**Graded by:** `score_e1.py` (per-spawn explicit-model rate, by depth) on
-the shared battery.
-**Baseline:** depth-2: 0/2 explicit.
-**Criterion:** every spawn at every depth carries explicit model +
-effort. Pre-registered caveat: if T1 eliminates depth-2 spawns entirely,
-T5 grades as root-spawn regression (hold 100%) plus doc correctness and
-is recorded inconclusive-by-zero at depth-2 — the config backstop is then
-the operative mechanism.
-
-## Grading plan
-
-- **Shared SDD battery** carries T1, T2, T5: `cx-sdd-small`, fix-branch
-  arm (`/tmp/sp-arm-fix`), 8 reps across both container lanes. Dev
-  baselines are already measured; no baseline re-runs.
-- **T4 batteries** as listed above (micro + codex ceremony + global
-  regression).
-- **Pre-registration:** every battery gets a hypothesis-log entry
-  (prediction, scorer, criterion) in
-  `superpowers-autoresearch/logs/2026-07-30-codex-efficiency-fixes.md`
-  BEFORE it runs. Standing rules carry over: append-only log, manual
-  inspection of scorer matches on fix-arm runs (non-circular
-  verification), no raw rollouts committed, correctness rides beside
-  cost in every verdict.
-- **Attribution:** orthogonal scorers on one combined branch; unexpected
-  regressions bisect by treatment commit.
-- **Budget:** shared battery ~$40, codex ceremony ~$40, global
-  regression ~$40–80, micros ~$5 → phase 1 ≈ $150–200 of the ~$850
-  remaining from the campaign's $1000.
-
-## Process
-
-- Work happens in the `codex-efficiency-fixes` worktree (branched off
-  `dev`); execution via subagent-driven-development from a written plan.
-- Skill-text changes follow writing-skills methodology.
-- Scenario/rig changes (un-gating ceremony scenarios for Claude
-  Code/Gemini, adversarial micro briefs) land in `superpowers-evals`
-  main, as authorized.
-- PR-per-treatment against `dev`, each with its eval evidence and the
-  standard identification block; merges only on Jesse's per-PR approval.
-
-## Phase 2 queue (baseline-first; not in this plan's tasks)
-
-Each item requires a failing baseline before any fix ships:
-1. **Dispatch routing / long-session drift** — needs a long-session
-   elicitation rig (fresh sessions don't reproduce the pathology at CLI
-   0.146). Drew's stack informs the treatment shape.
-2. **Verification leases / evidence receipts** — needs the
-   substring-aware duplicate counter added to `score_e3.py` first
-   (current baseline 1/23 exact-string pairs is too weak).
-3. **Remediation cap** — small-n baseline (2/3 reps) needs more reps.
-4. **Cross-task-race probe redesign** — `score_e5.py`'s probe is
-   inconclusive-by-zero by design tradeoff; needs a stronger probe.
-5. **E5 D4 shell-command parser** — fix-review-scope classifier cannot
-   parse compound commands; scorer work, not skill work.
-
-## Out of scope
-
-- Adopting Drew's spinout stack (#2036/#2035) or its text.
-- RoboRev, Codex token telemetry (separate codebases).
-- A `close_agent` hygiene checklist (V2 has no such tool — closed as
-  do-not-ship in the campaign).
-- Claude Code/Gemini-specific efficiency treatments beyond the T4
-  regression battery.

skills/subagent-driven-development/SKILL.md

@@ -59,7 +59,7 @@ digraph process {
         "Finding conflicts with plan text?" [shape=diamond];
         "Ask human partner which governs" [shape=box];
         "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [shape=box];
-        "Dispatch scoped re-review (./re-review-prompt.md)" [shape=box];
+        "Dispatch scoped fix review (./fix-review-prompt.md)" [shape=box];
         "All findings addressed?" [shape=diamond];
         "R = 5?" [shape=diamond];
         "Adjudicate each open finding" [shape=box];
@@ -72,7 +72,7 @@ digraph process {
     "Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
     "More tasks remain?" [shape=diamond];
     "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [shape=box];
-    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" [shape=box];
+    "Final findings? ONE fix dispatch, one scoped fix review, adjudicate residuals" [shape=box];
     "Final review clean: delete this plan's workspace" [shape=box];
     "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
 
@@ -88,8 +88,8 @@ digraph process {
     "Finding conflicts with plan text?" -> "Ask human partner which governs" [label="yes"];
     "Ask human partner which governs" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model";
     "Finding conflicts with plan text?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no"];
-    "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" -> "Dispatch scoped re-review (./re-review-prompt.md)";
+    "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" -> "Dispatch scoped fix review (./fix-review-prompt.md)";
-    "Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?";
+    "Dispatch scoped fix review (./fix-review-prompt.md)" -> "All findings addressed?";
     "All findings addressed?" -> "Append completion to ledger, mark todo complete" [label="yes"];
     "All findings addressed?" -> "R = 5?" [label="no"];
     "R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no - next round"];
@@ -101,8 +101,8 @@ digraph process {
     "Append completion to ledger, mark todo complete" -> "More tasks remain?";
     "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
     "More tasks remain?" -> "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [label="no"];
-    "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" -> "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals";
+    "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" -> "Final findings? ONE fix dispatch, one scoped fix review, adjudicate residuals";
-    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" -> "Final review clean: delete this plan's workspace";
+    "Final findings? ONE fix dispatch, one scoped fix review, adjudicate residuals" -> "Final review clean: delete this plan's workspace";
     "Final review clean: delete this plan's workspace" -> "Use superpowers:finishing-a-development-branch";
 }
 ```
@@ -158,6 +158,12 @@ conflicts that only emerge from implementation.
 
 Use the least powerful model that can handle each role to conserve cost and increase speed.
 
+When your platform's reference file (using-superpowers → Platform
+Adaptation) defines a dispatch role table, that table IS this section's
+mapping for your harness. Follow it over the tier language below — including
+for the final review and fix-loop escalation — and follow the
+`dispatch:` hint lines the task-brief and review-package scripts print.
+
 **Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
 
 **Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
@@ -168,7 +174,7 @@ capable available model, not the session default.
 
 **Review tasks**: choose the model with the same judgment, scaled to the
 diff's size, complexity, and risk. A small mechanical diff does not need the
-most capable model; a subtle concurrency change does. Scoped re-reviews of
+most capable model; a subtle concurrency change does. Scoped fix reviews of
 small fix diffs take a cheap-to-mid tier.
 
 **Fix-loop escalation (rounds 4-5)**: use a model at least one tier above
@@ -317,7 +323,8 @@ Before the loop starts, two routes leave it immediately:
   Do not dismiss the finding because the plan mandates it, and do not
   dispatch a fix that contradicts the plan without asking.
 Everything else enters the loop. A fix round is one fix dispatch plus one
-scoped re-review. Five rounds maximum per task:
+scoped fix review — a review of the fix diff, not a fresh review. Five
+rounds maximum per task:
 
 **Rounds 1-3 — resume the original implementer.** Send it the open findings
 verbatim. Its context is intact: it knows the task, the code, and its own
@@ -336,14 +343,14 @@ own problem — fresh eyes and a capability bump in one move.
 covering the amended code, appends its fix report to the same report file,
 and returns the short contract. Before re-dispatching the reviewer, confirm
 the fix report contains the covering tests, the command run, and the
-output; dispatch the re-review once all three are present. Name the
+output; dispatch the fix review once all three are present. Name the
 covering test files in the fix message — a one-line fix does not need the
 whole suite.
 
-**The re-review is scoped.** Run `scripts/review-package PLAN_FILE FIX_BASE HEAD`
+**The fix review is scoped.** Run `scripts/review-package --role fix-review PLAN_FILE FIX_BASE HEAD`
 where FIX_BASE is the head the previous review saw, and dispatch
-[re-review-prompt.md](re-review-prompt.md) with the findings list, the
+[fix-review-prompt.md](fix-review-prompt.md) with the findings list, the
-brief, the report file, and the printed diff path. The re-reviewer verdicts
+brief, the report file, and the printed diff path. The fix reviewer verdicts
 each finding ADDRESSED or NOT ADDRESSED and flags new breakage in the fix
 diff only. New Critical/Important breakage in the fix diff joins the open
 findings list. Out-of-scope observations go to the ledger as deferred
@@ -355,7 +362,7 @@ minors — they never extend the loop.
 Never fix findings yourself in the controller session — your context stays
 clean for coordination, and controller fixes skip review.
 
-**The breaker.** When round 5's re-review still leaves findings open, stop
+**The breaker.** When round 5's fix review still leaves findings open, stop
 dispatching. Adjudicate each open finding yourself — you hold the plan and
 the cross-task context the reviewer lacks:
 
@@ -391,7 +398,7 @@ parked-with-ruling at the cap.
 ## Final Review
 
 The final whole-branch review gets a package too: run
-`scripts/review-package PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the
+`scripts/review-package --role final-review PLAN_FILE 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. Dispatch
@@ -405,14 +412,23 @@ If the final whole-branch review returns findings, dispatch ONE fix subagent
 with the complete findings list — not one fixer per finding.
 Per-finding fixers each rebuild context and re-run suites; a real
 session's final-review fix wave cost more than all its tasks combined.
-Then run exactly one scoped re-review of the fix wave
+Then run exactly one scoped fix review of the fix wave
-(`scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
+(`scripts/review-package --role fix-review PLAN_FILE FIX_BASE HEAD` over the fix range,
-[re-review-prompt.md](re-review-prompt.md)).
+[fix-review-prompt.md](fix-review-prompt.md)).
 Adjudicate any residual findings as in the task loop's breaker: park with
 rulings, or stop on load-bearing ones. There is no second fix wave —
 residual load-bearing findings surface to your human partner when
 finishing-a-development-branch presents the options.
 
+The wave closing is policy, not a verdict. A sufficiently strong reviewer
+finds real defects indefinitely, so "review until one comes back clean"
+never terminates — the completed wave is the exit, not a clean report.
+New Critical/Important breakage in the final fix diff joins the residuals
+for adjudication; it does not start a second wave. And review procedures
+your human partner sets up for one review — competing reviewers, scoring,
+extra seats — apply to that review only. Never adopt them as standing
+procedure for reviews they didn't ask about.
+
 ## Finish
 
 When the final whole-branch review is clean and its fixes are merged,
@@ -429,11 +445,13 @@ Use superpowers:finishing-a-development-branch.
 | "Close enough on spec compliance" | Reviewer found spec gaps = not done. Fix or hit the cap and adjudicate — those are the only exits. |
 | "I'll fix it myself, dispatching is overhead" | Controller fixes pollute your context and skip review. Resume the implementer. |
 | "One more round will converge" | Past the cap, rounds don't converge — the failure is structural. Adjudicate and route. |
-| "The reviewer will just find something new anyway" | Scoped re-reviews verify fixes; they cannot wander. New findings on untouched code go to the ledger, not the loop. |
+| "The reviewer will just find something new anyway" | Scoped fix reviews verify fixes; they cannot wander. New findings on untouched code go to the ledger, not the loop. |
 | "This finding is obviously wrong, I'll drop it" | You adjudicate only at the cap, and every ruling is a ledger entry. Silent discards are forbidden. |
-| "The fix was small, skip the re-review" | Unreviewed fixes are how regressions land. Every round ends with a scoped re-review. |
+| "The fix was small, skip the fix review" | Unreviewed fixes are how regressions land. Every round ends with a scoped fix review. |
 | "Reviews slow the loop down" | The loop without reviews is just unverified churn. Reviews are the loop's brakes and steering. |
 | "Ledger bookkeeping is overhead" | The ledger is what survives compaction. Controllers without one have re-dispatched entire completed task sequences. |
+| "This new finding is real — one more wave" | Real findings are infinite under a strong reviewer. The completed wave is the exit; adjudicate and route. |
+| "They liked competing reviewers earlier, I'll run them again" | One-off review procedures apply to the review they were given for. Re-adopting them unasked is scope creep in review clothing. |
 
 ## Example Workflow
 
@@ -483,8 +501,8 @@ Task reviewer: Spec ❌:
 Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
   Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.
 
-[Run review-package PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review]
+[Run review-package --role fix-review PLAN_FILE FIX_BASE HEAD; dispatch scoped fix review]
-Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
+Fix reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
   Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
   Verdict: all findings addressed.
 
@@ -494,7 +512,7 @@ Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
 ...
 
 [After all tasks]
-[Run review-package PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
+[Run review-package --role final-review PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
 Final reviewer: All requirements met. Deferred minors triaged: none block merge.
 
 [Delete this plan's workspace — the record now lives in git]

skills/subagent-driven-development/fix-review-prompt.md

@@ -1,7 +1,7 @@
-# Scoped Re-Review Prompt Template
+# Scoped Fix Review Prompt Template
 
-Use this template when dispatching a re-review after a fix round. The
+Use this template when dispatching a fix review after a fix round. The
-re-reviewer verifies the findings were addressed and checks the fix diff for
+fix reviewer verifies the findings were addressed and checks the fix diff for
 new breakage. It is not a fresh review — the full review already happened.
 
 **Purpose:** Verify each finding from the previous review was addressed, and
@@ -9,11 +9,11 @@ that the fix itself broke nothing.
 
 ```
 Subagent (general-purpose):
-  description: "Re-review Task N fix round R"
+  description: "Fix review Task N round R"
   model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
          model silently inherits the session's most expensive one]
   prompt: |
-    You are re-reviewing one task's fix round. A previous review produced
+    You are reviewing one task's fix round. A previous review produced
     findings; an implementer has attempted to fix them. Your job is to
     verdict each finding and inspect the fix diff — nothing else.
 
@@ -47,7 +47,7 @@ Subagent (general-purpose):
 
     Your scope is the findings list and the fix diff. Verdict every finding.
     Inspect the fix diff for new problems the fix itself introduced. Do NOT
-    re-review code the fix did not touch: if you notice an issue entirely
+    review code the fix did not touch: if you notice an issue entirely
     outside the fix diff, report it under Out-of-Scope Observations — it
     does not block this task and does not extend the loop. A broad
     whole-branch review happens after all tasks are complete.
@@ -93,14 +93,14 @@ Subagent (general-purpose):
 
 **Placeholders:**
 - `[MODEL]` — REQUIRED: reviewer model per SKILL.md Model Selection; scoped
-  re-reviews of small fix diffs take a cheap-to-mid tier
+  fix reviews of small fix diffs take a cheap-to-mid tier
 - `[BRIEF_FILE]` — the task brief file (same file the implementer worked from)
 - `[FINDINGS]` — the Critical/Important findings and spec gaps from the
   previous review, copied verbatim, one per bullet
 - `[REPORT_FILE]` — the implementer's report file (fix reports appended)
 - `[FIX_BASE_SHA]` — the head the previous review saw
 - `[HEAD_SHA]` — current commit
-- `[DIFF_FILE]` — the path `scripts/review-package PLAN_FILE FIX_BASE HEAD` printed
+- `[DIFF_FILE]` — the path `scripts/review-package --role fix-review PLAN_FILE FIX_BASE HEAD` printed
 
-**Re-reviewer returns:** per-finding verdicts (ADDRESSED / NOT ADDRESSED),
+**Fix reviewer returns:** per-finding verdicts (ADDRESSED / NOT ADDRESSED),
 new breakage in the fix diff, out-of-scope observations, and a round verdict.

skills/subagent-driven-development/implementer-prompt.md

@@ -110,14 +110,21 @@ Subagent (general-purpose):
     Fix them, re-run the tests that cover the amended code, and append a fix
     report to your report file: what you changed, the covering tests you
     ran, the command, and the output. Reviewers will not re-run tests for
-    you — your report is the test evidence. Then reply with the same short
+    you — your report is the test evidence. If your fix report claims a
-    status contract as your first report.
+    full-suite pass, that claim needs a fresh run after your last edit —
+    a suite run from before the findings arrived no longer counts. Then
+    reply with the same short status contract as your first report.
 
     ## Report Format
 
     Write your full report to [REPORT_FILE]:
     - What you implemented (or what you attempted, if blocked)
-    - What you tested and test results
+    - What you tested, and for every gate you claim — focused tests, full
+      suite, lint, build — the exact command and the tail of its fresh
+      output. Fresh means run after your final edit: if you edited anything
+      since your last full-suite run, that run is stale — rerun it or
+      report the suite as unverified. A gate claim without pasted fresh
+      output is itself a defect for the reviewer to flag.
     - **TDD Evidence** (if TDD was required for this task):
       - RED: command run, relevant failing output before implementation, and why the failure was expected
       - GREEN: command run and relevant passing output after implementation

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

@@ -4,13 +4,31 @@
 # call. Using the recorded per-task BASE (not HEAD~1) keeps multi-commit
 # tasks intact.
 #
-# Usage: review-package PLAN_FILE BASE HEAD [OUTFILE]
+# Usage: review-package [--role task-review|fix-review|final-review] 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).
+# (named per range, so a fix review after fixes gets a distinct fresh file).
+#
+# The trailing dispatch hint rides this output because the controller reads it
+# immediately before spawning the reviewer; skill text loaded at session start
+# does not survive context compaction, but this line is reprinted every round.
 set -euo pipefail
 
+script_dir=$(cd "$(dirname "$0")" && pwd)
+
+role=task-review
+if [ "${1:-}" = "--role" ]; then
+  [ $# -ge 2 ] || { echo "usage: review-package [--role task-review|fix-review|final-review] PLAN_FILE BASE HEAD [OUTFILE]" >&2; exit 2; }
+  role=$2
+  shift 2
+fi
+
+case "$role" in
+  task-review|fix-review|final-review) hint_key=$role ;;
+  *) echo "bad --role: ${role} (task-review|fix-review|final-review)" >&2; exit 2 ;;
+esac
+
 if [ $# -lt 3 ] || [ $# -gt 4 ]; then
-  echo "usage: review-package PLAN_FILE BASE HEAD [OUTFILE]" >&2
+  echo "usage: review-package [--role task-review|fix-review|final-review] PLAN_FILE BASE HEAD [OUTFILE]" >&2
   exit 2
 fi
 
@@ -25,7 +43,7 @@ git rev-parse --verify --quiet "$head" >/dev/null || { echo "bad HEAD: $head" >&
 if [ $# -eq 4 ]; then
   out=$4
 else
-  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
+  dir=$("$script_dir/sdd-workspace" "$plan")
   out="$dir/review-$(git rev-parse --short "$base")..$(git rev-parse --short "$head").diff"
 fi
 
@@ -44,3 +62,16 @@ fi
 
 commits=$(git rev-list --count "${base}..${head}")
 echo "wrote ${out}: ${commits} commit(s), $(wc -c < "$out" | tr -d ' ') bytes"
+
+# Platform dispatch hints ride this output because the controller reads it
+# immediately before spawning; the lines themselves are owned by the platform
+# reference layer (using-superpowers/references/*-dispatch.hints), not this
+# script. Claude Code's dispatch templates carry model selection already, so
+# the relay is suppressed there and on any harness without a hints file.
+hints_file="$script_dir/../../using-superpowers/references/codex-dispatch.hints"
+if [ -z "${CLAUDECODE:-}" ] && [ -f "$hints_file" ]; then
+  hint_line=$(grep "^${hint_key}:" "$hints_file" | head -1 | cut -d: -f2- | sed 's/^ *//') || true
+  if [ -n "$hint_line" ]; then
+    echo "$hint_line"
+  fi
+fi

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

@@ -18,10 +18,12 @@ plan=$1
 n=$2
 [ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }
 
+script_dir=$(cd "$(dirname "$0")" && pwd)
+
 if [ $# -eq 3 ]; then
   out=$3
 else
-  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
+  dir=$("$script_dir/sdd-workspace" "$plan")
   out="$dir/task-${n}-brief.md"
 fi
 
@@ -39,3 +41,16 @@ if [ ! -s "$out" ]; then
 fi
 
 echo "wrote ${out}: $(wc -l < "$out" | tr -d ' ') lines"
+
+# Platform dispatch hints ride this output because the controller reads it
+# immediately before spawning; the lines themselves are owned by the platform
+# reference layer (using-superpowers/references/*-dispatch.hints), not this
+# script. Claude Code's dispatch templates carry model selection already, so
+# the relay is suppressed there and on any harness without a hints file.
+hints_file="$script_dir/../../using-superpowers/references/codex-dispatch.hints"
+if [ -z "${CLAUDECODE:-}" ] && [ -f "$hints_file" ]; then
+  hint_line=$(grep "^implementer:" "$hints_file" | head -1 | cut -d: -f2- | sed 's/^ *//') || true
+  if [ -n "$hint_line" ]; then
+    echo "$hint_line"
+  fi
+fi

skills/using-superpowers/references/codex-dispatch.hints

@@ -0,0 +1,11 @@
+# Per-role dispatch lines for Codex spawn_agent, relayed by the
+# subagent-driven-development task-brief and review-package scripts at the
+# moment of dispatch (skill text loaded at session start does not survive
+# context compaction; these lines reprint every round).
+# Model names track Codex's spawn_agent allowlist (currently gpt-5.6-sol
+# and gpt-5.6-terra) — update this file when the allowlist changes.
+# Format: <role>: <line printed verbatim>
+implementer: dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high
+task-review: dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high
+fix-review: dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=medium
+final-review: dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high

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

@@ -9,6 +9,31 @@ 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, close reviewer subagents when their review returns. Keep each implementer subagent open until its task's review passes — the fix loop resumes the implementer — then close it. If your harness cannot send another message to a spawned agent, dispatch each fix round as a fresh implementer carrying the brief, the report file, and the findings.
 
+## SDD dispatch on Codex
+
+Every SDD `spawn_agent` call sets `fork_turns: "none"` — the default
+`"all"` forks your whole transcript into the child and refuses model
+and effort overrides.
+
+If your `spawn_agent` schema has `model` and `reasoning_effort`
+parameters (Codex 0.145+), set both on every dispatch: task-brief and
+review-package print a `dispatch:` hint line with the exact values —
+copy it onto the call verbatim, every time, even late in a long
+session. Those hints are the Model Selection mapping on Codex:
+reviewer tier never exceeds implementer tier, no fix round gets an
+effort bump, and rounds 4-5's "more capable model" means a fresh
+implementer at the same tier — needing more is a BLOCKED escalation
+to your human partner. Inherited frontier-tier subagents are a
+measured cause of runs spinning out for hours. (Values live in
+`codex-dispatch.hints` beside this file; they track the spawn_agent
+model allowlist.)
+
+Without those parameters (Codex 0.144 and earlier), children inherit
+your model and effort with no override — role files in
+`~/.codex/agents/` do not attach to spawns either. Tell your human
+partner before starting a plan of more than a few tasks, and offer a
+lower-effort session instead.
+
 ## Environment Detection
 
 Skills that create worktrees or finish branches should detect their

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

@@ -165,6 +165,63 @@ PLAN
         echo "    got: $rp_explicit"
     fi
 
+    # --- platform dispatch hints ride the script output (suppressed on CC) ---
+    local brief_hint
+    brief_hint="$(cd "$repo" && env -u CLAUDECODE "$SDD_SCRIPTS/task-brief" plan-a.md 1)"
+    if [[ "$brief_hint" == *"dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high"* ]]; then
+        pass "task-brief relays the implementer dispatch hint off Claude Code"
+    else
+        fail "task-brief relays the implementer dispatch hint off Claude Code"
+        echo "    got: $brief_hint"
+    fi
+
+    local rp_hint
+    rp_hint="$(cd "$repo" && env -u CLAUDECODE "$SDD_SCRIPTS/review-package" plan-a.md HEAD~1 HEAD)"
+    if [[ "$rp_hint" == *"dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high"* ]]; then
+        pass "review-package relays the default-role hint off Claude Code"
+    else
+        fail "review-package relays the default-role hint off Claude Code"
+        echo "    got: $rp_hint"
+    fi
+
+    local rp_fixreview
+    rp_fixreview="$(cd "$repo" && env -u CLAUDECODE "$SDD_SCRIPTS/review-package" --role fix-review plan-a.md HEAD~1 HEAD)"
+    if [[ "$rp_fixreview" == *"dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=medium"* ]]; then
+        pass "review-package --role fix-review relays the medium-effort hint"
+    else
+        fail "review-package --role fix-review relays the medium-effort hint"
+        echo "    got: $rp_fixreview"
+    fi
+
+    local rp_final
+    rp_final="$(cd "$repo" && env -u CLAUDECODE "$SDD_SCRIPTS/review-package" --role final-review plan-a.md HEAD~1 HEAD)"
+    if [[ "$rp_final" == *"dispatch (spawn_agent): fork_turns=none model=gpt-5.6-terra reasoning_effort=high"* ]]; then
+        pass "review-package --role final-review relays the high-effort hint"
+    else
+        fail "review-package --role final-review relays the high-effort hint"
+        echo "    got: $rp_final"
+    fi
+
+    local brief_cc rp_cc
+    brief_cc="$(cd "$repo" && CLAUDECODE=1 "$SDD_SCRIPTS/task-brief" plan-a.md 1)"
+    rp_cc="$(cd "$repo" && CLAUDECODE=1 "$SDD_SCRIPTS/review-package" plan-a.md HEAD~1 HEAD)"
+    if [[ "$brief_cc" != *"dispatch (spawn_agent)"* && "$rp_cc" != *"dispatch (spawn_agent)"* ]]; then
+        pass "dispatch hints are suppressed under Claude Code (CLAUDECODE set)"
+    else
+        fail "dispatch hints are suppressed under Claude Code (CLAUDECODE set)"
+        echo "    brief: $brief_cc"
+        echo "    rp:    $rp_cc"
+    fi
+
+    rc=0
+    (cd "$repo" && "$SDD_SCRIPTS/review-package" --role bogus plan-a.md HEAD~1 HEAD >/dev/null 2>&1) || rc=$?
+    if [[ "$rc" -eq 2 ]]; then
+        pass "review-package rejects an unknown --role with exit 2"
+    else
+        fail "review-package rejects an unknown --role with exit 2"
+        echo "    exit: $rc"
+    fi
+
     # --- Worktree isolation: a linked worktree resolves its own workspace ---
     local wt="$TEST_ROOT/wt"
     ( cd "$repo" && git worktree add -q "$wt" -b wt-feature )