fix(sdd): task reviewers re-read illegible evidence instead of re-running to regenerate it

Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.

Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy

.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": "6.2.0",
       "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": "6.2.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.2.0",
   "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": "6.1.1",
+  "version": "6.2.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.kimi-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.2.0",
   "description": "An agentic skills framework and software development methodology.",
   "author": {
     "name": "Jesse Vincent",

README.md

@@ -3,12 +3,6 @@
 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).

RELEASE-NOTES.md

@@ -1,5 +1,38 @@
 # Superpowers Release Notes
 
+## v6.2.0 (2026-07-23)
+
+### Subagent-Driven Development
+
+Two structural changes to how SDD tracks progress and closes out review findings, both developed against live eval campaigns.
+
+- **The workspace is now plan-scoped.** `.superpowers/sdd/` had no plan identity and no end-of-life: a follow-up plan in the same working tree could read the previous plan's ledger as its own progress (observed in the wild, with multiple contamination rounds and ad-hoc workarounds). `sdd-workspace` now requires the plan file and resolves a per-plan directory, `.superpowers/sdd/<plan-basename>/`; `task-brief` and `review-package` write into their plan's directory (`review-package` gains the plan file as its first argument); the ledger names its plan on its first line; and the workspace is deleted once the final review is clean — git history is the durable record. Baseline evals showed controllers already refused foreign ledgers, but at a cost of 6–13 tool calls of cross-plan git forensics per resume; plan-scoping makes the answer structural instead. (25/25 baseline and GREEN eval runs documented in `docs/specs/` and `docs/plans/`.)
+- **The review-fix loop resumes the implementer.** The lifecycle restructure gives fix rounds resume-the-implementer semantics instead of fresh dispatches, adds a scoped re-review prompt (`re-review-prompt.md`) so the re-reviewer checks the fixes rather than re-reading the whole task, and installs a five-round circuit breaker with controller adjudication when it trips. SKILL.md reorganizes by lifecycle, and its Red Flags convert to the house rationalization-table form.
+
+### Skills
+
+A branch-wide compression campaign: recap sections, social proof, and benefits-selling prose aimed at a reader who has already invoked the skill are gone, with every load-bearing argument folded into a rationalization-table row or moved to its point of use. Each cut was micro-tested with subagent probes, and the one cut that measurably degraded behavior was reworked rather than shipped.
+
+- **`testing-anti-patterns.md` is now `writing-good-tests.md`.** The TDD reference doc is rebuilt as a positive catalog — six rules that lead with the GOOD example — and absorbs a falsifiability discipline: name the production change that would fail the test, derive expectations independently of the code under test, and a closing mutation check. It closes two holes by name: the string-presence trap (grep-style tests on scripts, skills, and prompts counterfeit falsifiability — the observable is behavior, never text) and the change-detector trap (a constant assertion can fail and still protect nothing), each with a hard stop in the gate function. Trivial code and human prose earn no test; the trigger broadens from "adding mocks" to any test writing.
+- **TDD's "Why Order Matters" rebuttals survive as rationalization rows.** Deleting the section outright measurably degraded test-first behavior under "just write it, tests after" pressure (control 8/10 → treatment 5/10, corroborated on Claude and Codex), so each prose rebuttal now lives in its Common Rationalizations row — the section is gone but the arguments fire where an agent hits them mid-rationalization.
+- **`finishing-a-development-branch` no longer offers to discard your work.** The completion menu dates from when throwing away branches was routine; "Discard this work" next to "Merge" advertised destroying finished, passing work. Discard survives as an explicit-request-only path with the same typed-confirmation ritual. The same pass made PR creation forge-agnostic (your forge's CLI or the URL printed on push, not a blessed list of tools) and fixed a real bug: the worktree path was recomputed after cleanup had already changed directory, so provenance checks never matched and cleanup silently no-oped.
+- **Recap and persuasion prose removed across the library.** `brainstorming`, `systematic-debugging`, `dispatching-parallel-agents`, `verification-before-completion`, `executing-plans`, `subagent-driven-development`, `requesting-code-review`, `receiving-code-review`, `using-git-worktrees`, `writing-plans`, and `writing-skills` all drop their Bottom Line / Key Principles / Real-World Impact / Advantages sections; `using-git-worktrees` and `finishing-a-development-branch` convert their guard sections to the house Excuse/Reality rationalization table.
+
+### Windows
+
+- **The SessionStart hook now dispatches via Git Bash.** The hook's command string starts with a quoted path, which broke both shells Claude Code might hand it to: PowerShell parsed the quoted string as an expression and died with a parser error (#1751), and cmd.exe's quote-stripping rule truncated the command when the profile path contained a metacharacter like `(` (#1918) — either way the bootstrap silently never loaded. The hook now declares `shell: "bash"`, which Claude Code ≥ 2.1.81 resolves to Git for Windows directly, and which surfaces an actionable install prompt when Git Bash is missing. Older Claude Code versions ignore the unknown key and behave as before. Verified end-to-end on Linux, Windows 11 with Git Bash under a hostile path, and Windows 11 without Git Bash.
+
+### Harness Support
+
+- **Gemini CLI support is restored.** The v6.1.0 removal (on the news that Google had EOLed the Gemini CLI) was premature; the install docs and the `gemini-tools.md` tool-mapping reference are back while permanent removal gets a proper evaluation. (#1959)
+
+### Fixes
+
+- **`find-polluter.sh` actually finds test files now.** `find .` emits `./`-prefixed paths, so the documented `-path "src/**/*.test.ts"` pattern matched nothing — and `wc -l` on empty input then reported "Found 1". Fixed the prefix mismatch (#2008, #2011), plus two follow-ups: a caller-supplied `./`-prefixed pattern no longer double-prefixes into a never-matching form, and `**/` is also matched collapsed so tests directly under the base directory (`src/top.test.ts` vs `src/**/*.test.ts`) aren't silently skipped. The script gains a deterministic test suite.
+- **The Codex package script works beyond macOS.** Deterministic-metadata tar flags were bsdtar-only spellings, staged file modes depended on two umasks canceling out, and the test's timestamp assertion parsed bsdtar's column layout in a US timezone. GNU tar now gets equivalent flags producing byte-identical headers, modes are pinned canonical, and the test asserts mtime via `tarfile`.
+- **SDD's skill test no longer flakes.** The file's worst case exceeded the runner's per-file ceiling (raised to 900s), and the assert helpers matched free-form model prose case-sensitively; matching is now case-insensitive and `assert_order` dumps output on failure so the next flake is diagnosable.
+- **Docs and test cleanup after the v6.1.0 reference pruning.** Dead links to the deleted `claude-code-tools.md`/`copilot-tools.md` are replaced with the current architecture (#1969), a dangling `#subagent-support` anchor in the Antigravity reference is dropped (#2010), and the Antigravity/Pi mapping tests assert only the surviving harness-specific mappings — scoped to the table so they fail again if it's deleted.
+
 ## v6.1.1 (2026-07-02)
 
 ### Codex

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": "6.2.0",
   "contextFileName": "GEMINI.md"
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.1.1",
+  "version": "6.2.0",
   "description": "Superpowers skills and runtime bootstrap for coding agents",
   "type": "module",
   "main": ".opencode/plugins/superpowers.js",

skills/requesting-code-review/code-reviewer.md

@@ -34,6 +34,15 @@ Subagent (general-purpose):
 
     Your review is read-only on this checkout. Do not mutate the working tree, the index, HEAD, or branch state in any way. Use tools like `git show`, `git diff`, and `git log` to inspect history. If you need a working copy of a different revision, check it out into a separate temporary directory (e.g. `git worktree add /tmp/review-[SHA] [SHA]`) — never move HEAD on this checkout.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## What to Check
 
     **Plan alignment:**

skills/subagent-driven-development/SKILL.md

@@ -14,7 +14,21 @@ Execute plan by dispatching a fresh implementer subagent per task, a task review
 **Narration:** between tool calls, narrate at most one short line — the
 ledger and the tool results carry the record.
 
-**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
+**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
+
+**Rulings, not stalls.** A running plan does not wait on a human. Conflicts,
+ambiguities, plan defects, a cap you would have asked to exceed — decide
+them. The spec is the binding authority, the plan is its argument, and your
+judgment settles what neither answers. Record every decision in the ledger as
+`Ruling: <what you decided> — <why> — <what it costs if wrong>`, and keep
+going. A wrong ruling costs rework your human partner can see and undo; a
+session parked on a question costs their whole day and buys nothing.
+
+Four things stop you, and only these: an irreversible or destructive
+operation; a security-sensitive action; a side effect outside this worktree
+that norms say you ask about first (a merge, a push to a shared branch, a
+publish); and a plan so broken that every path forward is a guess. For those,
+stop and ask.
 
 ## When to Use
 
@@ -57,14 +71,14 @@ digraph process {
         "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
         "Spec ✅ and quality approved?" [shape=diamond];
         "Finding conflicts with plan text?" [shape=diamond];
-        "Ask human partner which governs" [shape=box];
+        "Rule on the conflict, ledger the ruling" [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];
         "All findings addressed?" [shape=diamond];
         "R = 5?" [shape=diamond];
         "Adjudicate each open finding" [shape=box];
         "Any load-bearing finding?" [shape=diamond];
-        "STOP: report BLOCKED to human partner" [shape=box];
+        "Rule and continue; stop only if every path forward is a guess" [shape=box];
         "Park findings in ledger with rulings" [shape=box];
         "Append completion to ledger, mark todo complete" [shape=box];
     }
@@ -85,8 +99,8 @@ digraph process {
     "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
     "Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
     "Spec ✅ and quality approved?" -> "Finding conflicts with plan text?" [label="no"];
-    "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?" -> "Rule on the conflict, ledger the ruling" [label="yes"];
+    "Rule on the conflict, ledger the ruling" -> "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)";
     "Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?";
@@ -95,7 +109,7 @@ digraph process {
     "R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no - next round"];
     "R = 5?" -> "Adjudicate each open finding" [label="yes - breaker trips"];
     "Adjudicate each open finding" -> "Any load-bearing finding?";
-    "Any load-bearing finding?" -> "STOP: report BLOCKED to human partner" [label="yes"];
+    "Any load-bearing finding?" -> "Rule and continue; stop only if every path forward is a guess" [label="yes"];
     "Any load-bearing finding?" -> "Park findings in ledger with rulings" [label="no"];
     "Park findings in ledger with rulings" -> "Append completion to ledger, mark todo complete";
     "Append completion to ledger, mark todo complete" -> "More tasks remain?";
@@ -142,17 +156,27 @@ a ledger file, not only in todos.
 Read the plan once, note its context and Global Constraints, and create a
 todo per task.
 
-Before dispatching Task 1, scan the plan once for conflicts:
+Before dispatching Task 1, scan the plan once for conflicts, writing down
+what you checked as you check it:
 
 - tasks that contradict each other or the plan's Global Constraints
 - anything the plan explicitly mandates that the review rubric treats as a
   defect (a test that asserts nothing, verbatim duplication of a logic block)
 
-Present everything you find to your human partner as one batched question —
-each finding beside the plan text that mandates it, asking which governs —
-before execution begins, not one interrupt per discovery mid-plan. If the
-scan is clean, proceed without comment. The review loop remains the net for
-conflicts that only emerge from implementation.
+The scan's output is a table, not a verdict. One row for every pair of tasks
+that share a file or an interface: the two tasks, what one produces against
+what the other consumes, and what you found. One row for every task: whether
+its own text agrees with itself — the tests it specifies against the code it
+specifies, the files it creates against the files it later touches. "The scan
+is clean" without those rows is not a scan you ran.
+
+Write the table to the ledger. Rule on everything you find before execution
+begins — each finding against the plan text that mandates it — and record
+each ruling in the ledger. If the scan is clean, proceed without comment.
+Rule on each conflict it surfaces — the spec is the binding authority, the
+plan is its argument — record the ruling beside its row, and dispatch
+Task 1. The review loop remains the net for conflicts that only emerge from
+implementation.
 
 ## Model Selection
 
@@ -193,10 +217,29 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
 
 ## The Task Loop
 
+**Batch small same-shape work.** When the plan lists several tasks that are
+each a small, independent edit of the same kind — the same one-line fix,
+constant change, or field addition repeated across files — do not dispatch
+one subagent per task. Compose ONE dispatch brief listing every file and
+its change, send the whole batch to a single subagent, and review its diff
+as one unit. Reserve one-dispatch-per-task for work that needs its own
+judgment, its own tests, or its own review surface.
+
 Everything you paste into a dispatch prompt — and everything a subagent
 prints back — stays resident in your context for the rest of the session
 and is re-read on every later turn. Hand artifacts over as files.
 
+**Waiting on dispatched subagents:** never poll a wait interface with
+short timeouts, and never sit in one silent, open-ended wait either.
+While you have local work — ledger updates, packaging the next review,
+reading reports — keep working; child results arrive on their own.
+When you are genuinely idle, wait in bounded stretches (five to ten
+minutes, where your platform allows), and between stretches post one
+line of status and reconcile your live children: list them, and chase
+any that finished without reporting. A bounded stretch keeps nearly
+all of a long wait's efficiency while guaranteeing a stuck or lost
+child is noticed within minutes, not at the end of the session.
+
 ### 1. Dispatch the implementer
 
 Record BASE (`git rev-parse HEAD`) before dispatching — the review package
@@ -211,15 +254,9 @@ and fix-round diffs need it.
   first — it is your requirements, with the exact values to use verbatim";
   (3) interfaces and decisions from earlier tasks that the brief cannot
   know; (4) your resolution of any ambiguity you noticed in the brief;
-  (5) the report-file path and report contract; (6) the plan's binding
-  constraint values — any Global Constraint that mandates an exact
-  mechanical form (commit-message rules, naming rules, fixed literals) —
-  pasted verbatim. Task-specific exact values (numbers, magic strings,
-  signatures, test cases) appear only in the brief; binding constraint
-  values are the one exception — they ride in EVERY dispatch, because a
-  subagent that must recall a constraint from memory will reconstruct it
-  from its own priors instead. Never make a subagent read the whole plan
-  file.
+  (5) the report-file path and report contract. Exact values (numbers,
+  magic strings, signatures, test cases) appear only in the brief. Never
+  make a subagent read the whole plan file.
 - **Report file:** name the implementer's report file after the brief
   (brief `…/task-N-brief.md` → report `…/task-N-report.md`) and put it in
   the dispatch prompt. The implementer writes the full report there and
@@ -229,6 +266,12 @@ and fix-round diffs need it.
   later dispatches — a real session's dispatch hit 42k chars of which 99%
   was pasted history. A fresh subagent needs its task, the interfaces it
   touches, and the global constraints. Nothing else.
+- The dispatch carries the no-subagents contract (it is in the
+  implementer template): the implementer never dispatches subagents —
+  not helpers, and never a reviewer. Review arrives from you, after the
+  report. In real sessions, every reviewer a worker spawned duplicated
+  the task review the controller dispatched anyway — a full extra
+  review seat per task.
 - If an earlier task parked a finding in the area this task touches, carry
   a pointer to that ledger entry in the dispatch.
 - Record the implementer's agent identity from the dispatch result —
@@ -251,7 +294,7 @@ Implementer subagents report one of four statuses. Handle each appropriately:
 1. If it's a context problem, provide more context and re-dispatch with the same model
 2. If the task requires more reasoning, re-dispatch with a more capable model
 3. If the task is too large, break it into smaller pieces
-4. If the plan itself is wrong, escalate to the human
+4. If the plan itself is wrong, rule on the correction, ledger it, and re-dispatch with the ruling carried in the dispatch
 
 **Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
 
@@ -279,10 +322,6 @@ needed.
 - **Reviewer inputs:** the task reviewer gets three paths — the same brief
   file, the report file, and the review package — plus the global
   constraints that bind the task.
-- **Persist the verdict:** when the review returns, write its full text to
-  `<workspace>/task-<N>-review.md` before acting on it. The file is the
-  gate: completion checks for the artifact, not for your memory of a
-  verdict.
 - The global-constraints block you hand the reviewer is its attention
   lens. Copy the binding requirements verbatim from the plan's Global
   Constraints section or the spec: exact values, exact formats, and the
@@ -322,10 +361,11 @@ Before the loop starts, two routes leave it immediately:
   before merge. A roll-up nobody reads is a silent discard. Minor findings
   never enter the loop.
 - A finding labeled plan-mandated — or any finding that conflicts with
-  what the plan's text requires — is the human's decision, like any plan
-  contradiction: present the finding and the plan text, ask which governs.
-  Do not dismiss the finding because the plan mandates it, and do not
-  dispatch a fix that contradicts the plan without asking.
+  what the plan's text requires — is yours to rule on: weigh the finding
+  against the plan text, decide with the spec as the binding authority, and
+  ledger the ruling before you act on it. Do not dismiss the finding because
+  the plan mandates it, and do not dispatch a fix that contradicts the plan
+  without a recorded ruling.
 Everything else enters the loop. A fix round is one fix dispatch plus one
 scoped re-review. Five rounds maximum per task:
 
@@ -333,26 +373,22 @@ scoped re-review. Five rounds maximum per task:
 verbatim. Its context is intact: it knows the task, the code, and its own
 choices. If your harness cannot send another message to a live subagent,
 dispatch a fresh implementer carrying the brief path, the report-file path,
-the findings, and the binding constraint values verbatim — the report file
-is the persistent memory either way.
+and the findings — the report file is the persistent memory either way.
 
 **Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
 Model Selection), with the brief path, the report-file path, the open
-findings, the binding constraint values verbatim, and this framing: "A
-prior implementer attempted this task [N] times; you own it now. Read the
-report file for what was tried." A loop that survives three resumes usually
-means the implementer cannot see its own problem — fresh eyes and a
-capability bump in one move.
+findings, and this framing: "A prior implementer attempted this task
+[N] times; you own it now. Read the report file for what was tried." A loop
+that survives three resumes usually means the implementer cannot see its
+own problem — fresh eyes and a capability bump in one move.
 
 **Every round, either way:** the implementer fixes, re-runs the tests
 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 covering test
-files in the fix message — a one-line fix does not need the whole suite.
-Append the re-review's returned text to `<workspace>/task-<N>-review.md` as
-well — the artifact accumulates every verdict, and the file's last entry is
-the one completion relies on.
+the fix report contains the covering tests, the command run, and the
+output; dispatch the re-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`
 where FIX_BASE is the head the previous review saw, and dispatch
@@ -374,15 +410,16 @@ dispatching. Adjudicate each open finding yourself — you hold the plan and
 the cross-task context the reviewer lacks:
 
 - **The reviewer is wrong, or the point is contestable:** park it —
-  `Task <N>: parked — <finding> — ruling: <why the code stands>`. The final
+  `Task <N>: parked — <finding> — Ruling: <why the code stands>`. The final
   review sees both sides.
 - **Real, but nothing downstream builds on it:** park it the same way, with
   a ruling that says it's real and deferred.
 - **Real and load-bearing** — a later task builds on it, or it reveals a
-  plan defect: STOP. Append `Task <N>: BLOCKED — <reason>` and report to
-  your human partner with the finding, the plan text it collides with, and
-  the fix history. Parking a structural failure lets every dependent task
-  build on it and hands the final review a problem it cannot fix either.
+  plan defect: rule on the smallest change that unblocks the dependent work,
+  ledger it as `Task <N>: Ruling: <finding> — <what you decided and why>`,
+  and carry it into the next task's dispatch. Parking a structural failure
+  silently lets every dependent task build on it. Stop only when the defect
+  leaves every path forward a guess.
 
 Adjudicate only at the cap. Adjudicating earlier to end a loop is
 pre-judging with a different name. Every adjudication is a ledger entry —
@@ -397,20 +434,10 @@ message as your other bookkeeping:
 - `Task <N>: complete (commits <base7>..<head7>, review clean)`
 - `Task <N>: complete (commits <base7>..<head7>, <K> parked)` after a
   tripped breaker
-- `Task <N>: complete (commits <base7>..<head7>, deviation parked: <rule>)`
-  when a landed commit violates a mechanical constraint that nothing
-  downstream builds on. Record the ruling in the ledger. A green build with
-  a parked, recorded deviation is complete — do not fail the task, and do
-  not rewrite landed history to chase cosmetics. A load-bearing violation
-  is different: that is a BLOCKED, not a deviation. This valve is not the
-  breaker: it needs no exhausted fix rounds — a mechanical deviation
-  discovered at completion parks here directly, with its ruling in the ledger.
 
-Then mark the todo complete and move on — but only once
-`<workspace>/task-<N>-review.md` exists; a completion line without its review
-artifact is invalid, whatever you remember about the review. Never move to
-the next task while the review has open Critical/Important issues that are
-neither fixed nor parked-with-ruling at the cap.
+Then mark the todo complete and move on. Never move to the next task while
+the review has open Critical/Important issues that are neither fixed nor
+parked-with-ruling at the cap.
 
 ## Final Review
 
@@ -423,27 +450,32 @@ on the most capable available model (see Model Selection), using
 superpowers:requesting-code-review's
 [code-reviewer.md](../requesting-code-review/code-reviewer.md). Point it at
 the ledger's deferred-minor and parked lines so it can triage which must be
-fixed before merge. Write the returned review to `<workspace>/final-review.md`
-before dispatching any fix wave — the merge decision cites the artifact, not a
-recollection.
+fixed before merge.
 
 If the final whole-branch review returns findings, dispatch ONE fix subagent
-with the complete findings list and the binding constraint values
-verbatim — not one fixer per finding.
+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
 (`scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
 [re-review-prompt.md](re-review-prompt.md)).
 Adjudicate any residual findings as in the task loop's breaker: park with
-rulings, or stop on load-bearing ones. The same valve applies to
-mechanical-constraint misses discovered at the end: non-load-bearing means
-parked with a ruling, not a failed branch. There is no second fix wave —
+rulings, or rule on the load-bearing ones and ledger what you decided. Only
+the four classes above stop you here. There is no second fix wave —
 residual load-bearing findings surface to your human partner when
 finishing-a-development-branch presents the options.
 
 ## Finish
 
+Before you delete anything, collect every ledger line containing `Ruling:` —
+preflight rulings, parked findings, breaker adjudications, all of them — into
+your final message under "Rulings I made", in the order you made them, each
+with what it costs if wrong. The list is exhaustive: if the ledger holds a
+ruling, the list holds it. That list is the only place the decisions you
+took on your human partner's behalf reach them — they read it and rework
+whatever you got wrong. A ruling that dies with the workspace was a decision
+made in secret.
+
 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
@@ -463,6 +495,7 @@ Use superpowers:finishing-a-development-branch.
 | "The fix was small, skip the re-review" | Unreviewed fixes are how regressions land. Every round ends with a scoped re-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. |
+| "The implementer spawned its own reviewer — free extra assurance" | It's a duplicate seat reviewing the same diff; the task review is the gate. A worker-spawned reviewer is a defect to flag, not rigor. |
 
 ## Example Workflow
 

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

@@ -15,12 +15,6 @@ Subagent (general-purpose):
     Read your task brief first: [BRIEF_FILE]
     It contains the full task text from the plan.
 
-    ## Binding Constraint Values
-
-    [CONSTRAINT_VALUES — the plan's mechanical constraints, pasted verbatim
-    by the dispatcher. If a rule here mandates an exact form (commit-message
-    text, naming, fixed literals), reproduce it exactly — never from memory.]
-
     ## Context
 
     [Scene-setting: where this fits, dependencies, architectural context]
@@ -42,12 +36,8 @@ Subagent (general-purpose):
     2. Write tests (following TDD if task says to)
     3. Verify implementation works
     4. Commit your work
-    5. Immediately after each commit, verify it against the Binding Constraint
-       Values above (commit-message rules, naming rules, fixed literals) while
-       history is still local. A miss is cheap now — amend or forward-fix at
-       once — and expensive after your work is delivered.
-    6. Self-review (see below)
-    7. Report back
+    5. Self-review (see below)
+    6. Report back
 
     Work from: [directory]
 
@@ -57,6 +47,18 @@ Subagent (general-purpose):
     While iterating, run the focused test for what you're changing; run the
     full suite once before committing, not after every edit.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this task's work yourself. Never spawn a subagent to
+    implement part of the task, and above all never spawn a reviewer to
+    check your work. Self-review (below) means reading your own diff.
+    Review is the controller's job: after you report, it dispatches a
+    fresh reviewer against your diff. A reviewer you spawn duplicates
+    that review at full cost, and its approval counts for nothing in
+    the process. If you catch yourself thinking "an independent review
+    would strengthen my report" — that review is already scheduled.
+    Report instead.
+
     ## Code Organization
 
     You reason best about code you can hold in context at once, and your edits are more
@@ -106,10 +108,6 @@ Subagent (general-purpose):
     - Did I only build what was requested?
     - Did I follow existing patterns in the codebase?
 
-    **Constraints:**
-    - Does every commit message satisfy the Binding Constraint Values exactly?
-    - Did I reproduce mandated literals from the constraint text, not from memory?
-
     **Testing:**
     - Do tests actually verify behavior (not just mock behavior)?
     - Did I follow TDD if required?
@@ -118,12 +116,6 @@ Subagent (general-purpose):
 
     If you find issues during self-review, fix them now before reporting.
 
-    If a constraint violation is already in a landed commit you cannot safely
-    amend, forward-fix it in a new commit when possible; when it is not, report
-    the deviation explicitly with Status DONE_WITH_CONCERNS — never report the
-    task incomplete solely for a cosmetic miss on an otherwise green build.
-    Whether the deviation parks or blocks is the dispatching controller's call.
-
     ## After Review Findings
 
     If the task review finds issues, you will be resumed with the findings.
@@ -156,8 +148,7 @@ Subagent (general-purpose):
     If BLOCKED or NEEDS_CONTEXT, put the specifics in the final message
     itself — the controller acts on it directly.
 
-    Use DONE_WITH_CONCERNS if you completed the work but have doubts about correctness, or
-    when you are reporting a known deviation you could not safely fix.
+    Use DONE_WITH_CONCERNS if you completed the work but have doubts about correctness.
     Use BLOCKED if you cannot complete the task. Use NEEDS_CONTEXT if you need
     information that wasn't provided. Never silently produce work you're unsure about.
 ```

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

@@ -43,6 +43,15 @@ Subagent (general-purpose):
     Your review is read-only on this checkout. Do not mutate the working
     tree, the index, HEAD, or branch state in any way.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## Scope
 
     Your scope is the findings list and the fix diff. Verdict every finding.

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

@@ -52,6 +52,15 @@ Subagent (general-purpose):
     Your review is read-only on this checkout. Do not mutate the working
     tree, the index, HEAD, or branch state in any way.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## Do Not Trust the Report
 
     Treat the implementer's report as unverified claims about the code. It
@@ -75,6 +84,13 @@ Subagent (general-purpose):
     Warnings or other noise in the implementer's reported test output are
     findings — test output should be pristine.
 
+    Evidence you cannot see is not evidence that doesn't exist. If the
+    report or its test evidence looks truncated, or you cannot locate the
+    results it claims, re-read the file at its stated path — and if it is
+    genuinely missing or garbled, report that as a gap for the controller.
+    Re-running the suite to regenerate what you failed to read is not
+    verification; illegibility of the evidence is not invalidation of it.
+
     ## Part 1: Spec Compliance
 
     Compare the diff against What Was Requested:
@@ -86,6 +102,12 @@ Subagent (general-purpose):
     - **Misunderstood:** right feature built the wrong way, wrong problem
       solved
 
+    If the brief lists several files each with its own change (a batched
+    dispatch), check the diff against that list file by file: every listed
+    file must have its corresponding hunk. A listed file the diff never
+    touches is a Missing finding, no matter how clean the rest of the
+    batch looks.
+
     If a requirement cannot be verified from this diff alone (it lives in
     unchanged code or spans tasks), report it as a ⚠️ item instead of
     broadening your search.

skills/systematic-debugging/find-polluter.sh

@@ -18,9 +18,18 @@ echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
 echo "Test pattern: $TEST_PATTERN"
 echo ""
 
-# Get list of test files
-TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
-TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
+# Get list of test files (find . emits ./-prefixed paths, so accept the
+# pattern written with or without a leading ./)
+TEST_PATTERN="${TEST_PATTERN#./}"
+# find -path can't match '**/' against zero directory levels, so a pattern
+# like src/**/*.test.ts would skip src/top.test.ts; also try the pattern
+# with '**/' collapsed to cover files directly under the base directory.
+TEST_FILES=$(find . \( -path "./$TEST_PATTERN" -o -path "./${TEST_PATTERN//\*\*\//}" \) | sort -u)
+if [ -z "$TEST_FILES" ]; then
+  TOTAL=0
+else
+  TOTAL=$(printf '%s\n' "$TEST_FILES" | wc -l | tr -d ' ')
+fi
 
 echo "Found $TOTAL test files"
 echo ""

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

@@ -4,7 +4,7 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file").
 
 | Action skills request | Antigravity CLI equivalent |
 |----------------------|----------------------|
-| 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)) |
+| Dispatch a subagent (`Subagent (general-purpose):` template) | `invoke_subagent` with a built-in `TypeName` — `self` for full-capability work, `research` for read-only |
 | 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. |
 
 ## Task tracking

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

@@ -7,7 +7,76 @@ 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, 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.
+This enables the multi-agent tools that skills like
+`dispatching-parallel-agents` and `subagent-driven-development` use.
+Which tools you get depends on the multi-agent version your model
+preset selects (current presets run V2; older ones run V1). Trust your
+actual tool list over any table — including this one — when they
+disagree.
+
+- **Spawning:** give children a clean context with
+  `spawn_agent {fork_turns: "none"}`; the default `"all"` copies your
+  entire transcript into the child. On Codex 0.145+, role files under
+  `~/.codex/agents/` attach to isolated forks via `agent_type`.
+  Full-history forks accept `model` and `reasoning_effort` overrides
+  (only `agent_type` is refused there) — isolated forks are the SDD
+  default for context hygiene, not because overrides require them.
+- **Fix rounds:** resume the implementer with `followup_task` — it
+  delivers your message, triggers a turn, and transparently reloads a
+  child the harness evicted. Never dispatch a fresh implementer on the
+  theory that a spawned agent cannot be messaged again; on V2 it
+  always can.
+- **Lifecycle:** V2 has no `close_agent`. Finished children are
+  evicted automatically when slots are needed; leaving them unclosed
+  costs nothing. Only V1 sessions have `close_agent` — there, close
+  reviewers when their review returns, and close each implementer
+  after its task's review passes.
+- **Model names:** never copy a model name from a skill, table, or old
+  session into `spawn_agent` without checking it against your current
+  spawn allowlist — V2 accepts only V2-capable presets and hard-errors
+  on the rest.
+
+## Waiting on children
+
+`wait_agent` is an event subscription, not a poll: a long wait wakes
+the moment a child produces mailbox activity, with the same latency as
+a short one. Short-timeout polling buys nothing and costs a tool call —
+and a context rebill — per poll. In measured sessions, roughly
+two-thirds of all wait calls were short polls that timed out.
+
+- While you still have local work, do not wait at all. A completed
+  child's final answer is pushed into your mailbox and arrives with
+  your next turn.
+- When you are genuinely idle with children outstanding, wait in
+  bounded stretches: `wait_agent` with `timeout_ms` 300000-600000
+  (5-10 minutes). After each stretch — wake or timeout — post one
+  status line, run `list_agents`, and chase any child that finished
+  without reporting. Never stack polls shorter than five minutes; the
+  event subscription wakes a bounded stretch just as fast as a short
+  one.
+- Completion mail cannot wake an idle controller (it is delivered
+  without triggering a turn); covering that idle window is
+  `wait_agent`'s only job. A stretch that times out with no activity
+  is your cue to reconcile, not to shorten the next stretch.
+
+## Model routing on spawns
+
+Every `spawn_agent` you issue — including when you are yourself a
+spawned child running a fan-out — sets `model` AND `reasoning_effort`
+explicitly, per the Model Selection rules of the skill you are
+executing. Setting `model` alone is a trap: the child's effort
+silently resets to that model's default, not to yours.
+
+Ask your human partner to add a machine-level backstop to
+`~/.codex/config.toml` so any spawn that slips through still routes to
+a deliberate tier instead of silently inheriting the session's most
+expensive model:
+
+```toml
+[agents]
+default_subagent_model = "<a mid-tier model from your spawn allowlist>"
+default_subagent_reasoning_effort = "medium"
+```
 
 ## Environment Detection
 

skills/writing-plans/SKILL.md

@@ -71,11 +71,7 @@ independently testable deliverable.
 [The spec's project-wide requirements — version floors, dependency limits,
 naming and copy rules, platform requirements — one line each, with exact
 values copied verbatim from the spec. Every task's requirements implicitly
-include this section. Three things may never enter it: cosmetic absolutes
-on every commit (a fixed trailer or byline the work does not need), your
-own identity or model name promoted into a rule, and environment
-constraints (versions, platforms, paths) you have not verified against the
-environment the plan will execute in.]
+include this section.]
 
 ---
 ```
@@ -129,8 +125,6 @@ git commit -m "feat: add specific feature"
 ```
 ````
 
-Commit messages describe the change. Never mandate session boilerplate — trailers, bylines, model names — as a per-commit rule; what your session stamps on its commits is not a requirement of the work.
-
 ## No Placeholders
 
 Every step must contain the actual content an engineer needs. These are **plan failures** — never write them:
@@ -151,8 +145,6 @@ After writing the complete plan, look at the spec with fresh eyes and check the
 
 **3. Type consistency:** Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.
 
-**4. Constraint hygiene:** Does any Global Constraint mandate a per-commit cosmetic absolute, name the authoring model or session, or assert an environment fact (version floor, platform, path) you did not verify? Cut or verify it.
-
 If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.
 
 ## Execution Handoff

tests/systematic-debugging/test-find-polluter.sh

@@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+SCRIPT_UNDER_TEST="$REPO_ROOT/skills/systematic-debugging/find-polluter.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_contains() {
+  local haystack="$1"
+  local needle="$2"
+  local description="$3"
+
+  if printf '%s' "$haystack" | grep -Fq -- "$needle"; then
+    pass "$description"
+  else
+    fail "$description (expected output to contain: $needle)"
+  fi
+}
+
+# Toy project: one top-level test, one nested test. A stubbed `npm` on PATH
+# creates the pollution marker whenever any test runs, so the first test file
+# executed is always identified as the polluter.
+setup_project() {
+  PROJECT="$TEST_ROOT/project"
+  rm -rf "$PROJECT"
+  mkdir -p "$PROJECT/src/feature" "$PROJECT/bin"
+  echo "test('top')" > "$PROJECT/src/top.test.ts"
+  echo "test('nested')" > "$PROJECT/src/feature/nested.test.ts"
+  cat > "$PROJECT/bin/npm" <<'EOF'
+#!/usr/bin/env bash
+touch pollution.marker
+EOF
+  chmod +x "$PROJECT/bin/npm"
+}
+
+# run_polluter <pattern> — runs the script in the toy project with the stub
+# npm first on PATH; captures combined output, never aborts on exit code.
+run_polluter() {
+  local pattern="$1"
+  rm -f "$PROJECT/pollution.marker"
+  (
+    cd "$PROJECT"
+    PATH="$PROJECT/bin:$PATH" "$SCRIPT_UNDER_TEST" 'pollution.marker' "$pattern" 2>&1
+  ) || true
+}
+
+echo "Test: documented pattern finds nested test files (issue #2008)"
+setup_project
+OUTPUT="$(run_polluter 'src/**/*.test.ts')"
+assert_contains "$OUTPUT" "FOUND POLLUTER" "documented pattern runs tests and detects pollution"
+
+echo "Test: documented pattern also finds top-level test files"
+setup_project
+OUTPUT="$(run_polluter 'src/**/*.test.ts')"
+assert_contains "$OUTPUT" "Found 2 test files" "src/**/*.test.ts matches src/top.test.ts and src/feature/nested.test.ts"
+
+echo "Test: ./-prefixed pattern matches the same files"
+setup_project
+OUTPUT="$(run_polluter './src/**/*.test.ts')"
+assert_contains "$OUTPUT" "Found 2 test files" "leading ./ on the pattern is accepted"
+
+echo "Test: non-matching pattern reports an honest zero"
+setup_project
+OUTPUT="$(run_polluter 'nomatch/**/*.test.ts')"
+assert_contains "$OUTPUT" "Found 0 test files" "empty result counts as 0, not 1"
+assert_contains "$OUTPUT" "No polluter found" "empty result exits via the clean path"
+
+echo ""
+if [ "$FAILURES" -gt 0 ]; then
+  echo "$FAILURES test(s) failed"
+  exit 1
+fi
+echo "All tests passed"