pincer-workflow 0.3.0 → 0.4.0

package/README.md

@@ -86,7 +86,7 @@ want the repo-side rules too can copy `AGENTS.md` from the
 npx pincer-workflow@latest update
 ```
 
-Files you never touched are refreshed in place. (Installs older than v0.2.0 gain the ticket state machine, the status report and the ticket-guard hook on update; `.claude/settings.json` conflicts if you edited it — merge the new hook entry from the `.new` file. v0.2.2 replaces the Codex adapter: the commands are now skills in `.agents/skills/` invoked as `$pincer-*`, since Codex no longer loads `~/.codex/prompts/` — you can delete the copies there. v0.2.3 ships the playbooks, rubrics and templates under `.claude/` on every platform, which Codex- and Copilot-only installs were missing. v0.3.0 makes trust revocable: every verification attempt is recorded, `done` re-runs the check, tickets carry `prd:`, the release audit is read-only, and `.pincer.json` moves to schema 2 — an install from 0.2.x is treated as an untrusted baseline, so on the first update every changed file arrives as a `.new` proposal once; hooks now need Node 18+.) Files you edited are left
+Files you never touched are refreshed in place. (Installs older than v0.2.0 gain the ticket state machine, the status report and the ticket-guard hook on update; `.claude/settings.json` conflicts if you edited it — merge the new hook entry from the `.new` file. v0.2.2 replaces the Codex adapter: the commands are now skills in `.agents/skills/` invoked as `$pincer-*`, since Codex no longer loads `~/.codex/prompts/` — you can delete the copies there. v0.2.3 ships the playbooks, rubrics and templates under `.claude/` on every platform, which Codex- and Copilot-only installs were missing. v0.3.0 makes trust revocable: every verification attempt is recorded, `done` re-runs the check, tickets carry `prd:`, the release audit is read-only, and `.pincer.json` moves to schema 2 — an install from 0.2.x is treated as an untrusted baseline, so on the first update every changed file arrives as a `.new` proposal once; hooks now need Node 18+. v0.4.0 carries requirement IDs and `Proves:` checks from the PRD to evaluation, adds `profile: small|standard`, and saves candidate evidence under `.prd/evidence/`; the update is additive, but an existing `NOTES.md` without an `evidence:` manifest reads as stale until `/pincer-evaluate` is re-run.) Files you edited are left
 alone — the new version lands next to them as `<file>.new` for a manual merge.
 `npx pincer-workflow doctor` checks the health of an install (hook executable,
 `.gitignore` covering `.env*`, no unmerged `*.new` files, version current).
@@ -99,7 +99,8 @@ alone — the new version lands next to them as `<file>.new` for a manual merge.
 | `.claude/commands/` | The five playbooks plus `/pincer-status` (canonical — adapters are generated from them; ships on every platform together with `agents/` and `references/`) |
 | `.claude/agents/` | `codebase-explorer` and `code-quality-reviewer` subagents, with inline fallbacks for platforms without subagents |
 | `scripts/pincer-ticket.sh` | The ticket state machine: `start` (enforces dependency order) → `verify` (runs the ticket's check, stamps a receipt only on green) → `done` (refuses without a matching receipt or with unticked criteria) |
-| `scripts/pincer-status.sh` | Read-only state report: current PRD, associated tickets, clock-based elapsed time, optional user budget, warnings, and next command |
+| `scripts/pincer-status.sh` | Read-only state report: current PRD and profile, associated tickets, wall-clock elapsed time while work is active or against an explicit budget, evidence verdict, warnings, and next command |
+| `scripts/pincer-evidence.cjs` | Read-only validator for candidate evidence (schema 1): `/pincer-evaluate` writes `.prd/evidence/prd-vN/<candidate>/manifest.json` plus logs and screenshots; status and release validate schema, references, candidate association, required results, file containment and SHA-256 digests. Legacy `NOTES.md` without a manifest is readable but never release-ready; an older runtime does not enforce this contract |
 | `.claude/hooks/` + `settings.json` | Claude guardrails for documented destructive command forms and ticket state writes; Node.js 18+ parses hook payloads structurally |
 | `.agents/skills/` · `.codex/` · `.github/` | Generated Codex skills and Copilot prompt files + platform wiring (`.codex/README.md` covers the Codex posture) |
 | `scripts/sync-prompts.sh` | Regenerates the adapters after you edit a playbook |
@@ -118,6 +119,9 @@ alone — the new version lands next to them as `<file>.new` for a manual merge.
 - **State lives in files, not in the conversation** — a new session runs
   `/pincer-status` and knows exactly where to resume; elapsed time comes from
   timestamps, not from the model's sense of time.
+- **Evidence is saved, not narrated** — requirements carry stable IDs from the
+  PRD through tickets to evaluation, and the evaluation writes a validated
+  manifest under `.prd/evidence/` that release reads instead of trusting chat.
 - **Scope is a first-class artifact** — cuts are recorded, never silent.
 - **Security is threaded through every stage** — designed in at Plan, specified
   as reject-path criteria at Narrow, enforced by a pre-commit sweep at Code,

package/bin/pincer.js

@@ -26,7 +26,7 @@ const MANIFEST_SCHEMA = 2;
 // and Copilot prompts point at them), so they ship everywhere; only Claude
 // Code's own wiring (CLAUDE.md, settings.json, hooks) is platform-specific.
 const PLATFORM_ROOTS = {
-  common: ['AGENTS.md', 'docs/release-checklist.md', 'docs/dry-run-checklist.md', 'scripts/sync-prompts.sh', 'scripts/pincer-ticket.sh', 'scripts/pincer-ticket-lib.sh', 'scripts/pincer-status.sh', '.claude/commands', '.claude/agents', '.claude/references'],
+  common: ['AGENTS.md', 'docs/release-checklist.md', 'docs/dry-run-checklist.md', 'scripts/sync-prompts.sh', 'scripts/pincer-ticket.sh', 'scripts/pincer-ticket-lib.sh', 'scripts/pincer-status.sh', 'scripts/pincer-evidence.cjs', '.claude/commands', '.claude/agents', '.claude/references'],
   claude: ['CLAUDE.md', '.claude/settings.json', '.claude/hooks'],
   codex: ['.codex', '.agents'],
   copilot: ['.github'],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pincer-workflow",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "PINCER — a PRD-driven agentic delivery workflow for Claude Code, Codex CLI, and GitHub Copilot. Plan · Investigate · Narrow · Code · Evaluate · Release.",
   "bin": {
     "pincer": "bin/pincer.js"
@@ -14,7 +14,7 @@
     "node": ">=18"
   },
   "scripts": {
-    "test": "node test/smoke.test.js && node test/installer.test.js && node test/ticket.test.js && node test/validation.test.js && node test/verification.test.js && node test/recovery.test.js && node test/hooks.test.js && node test/workflow.test.js && node test/distribution.test.js"
+    "test": "node test/smoke.test.js && node test/installer.test.js && node test/ticket.test.js && node test/validation.test.js && node test/verification.test.js && node test/behavioral-verification.test.js && node test/evidence.test.js && node test/candidate.test.js && node test/recovery.test.js && node test/hooks.test.js && node test/workflow.test.js && node test/distribution.test.js"
   },
   "keywords": [
     "claude-code",

package/template/.agents/skills/pincer-code/SKILL.md

@@ -41,7 +41,11 @@ previously authorized work.
    conventions, and nothing else.
 3. **Verify:** `scripts/pincer-ticket.sh verify T-{NN}` — runs the Verification block and
    writes the receipt only if it exits 0. Red → fix and re-run; report the actual output,
-   not assumptions. Green output is the definition of done, not your confidence.
+   not assumptions. Green output is the definition of done, not your confidence. If the
+   check only validated syntax or a build, say so — that is not behavioral proof. A
+   visual judgment is recorded separately in evaluation, not as the receipt, and a tool
+   the check needs but cannot run yields an explicit `unverified` result, never
+   fabricated output.
 4. **Self-review the diff** before committing: silent failures (empty catches,
    un-awaited promises), leftover debug code, drift from the ticket's acceptance criteria.
    Then a security sweep of the same diff:
@@ -59,8 +63,33 @@ previously authorized work.
    Inspect `git status --short`, preserve pre-existing staged work, and stage only the
    explicit paths changed for this ticket plus its ticket file. Review `git diff --cached`
    before committing as `T-{NN}: {title}`.
-6. Give a one-line progress update using the elapsed figure from
-   `scripts/pincer-status.sh` ("T-02 done, 3 remaining, 38m elapsed") and continue.
+6. Give a one-line progress update ("T-02 done, 3 remaining") and continue. Quote the
+   wall-clock elapsed figure from `scripts/pincer-status.sh` when it shows one — it
+   appears while a ticket is in progress or a budget is set, and it is not a measure
+   of active execution time.
+
+## Recovering a ticket file
+
+Ticket lifecycle fields are written only by `scripts/pincer-ticket.sh`, and the guard
+also blocks shell restores that would touch ticket files from the assistant's shell:
+`git checkout`/`git restore`/`git switch` naming a ticket path or a normalized
+pathspec that cannot be shown to stay outside `tickets/` (the whole tree, `.`, `:/`,
+`:(top)`, globs, absolute or unexpanded paths, `tickets/…` in any spelling, a
+`-C tickets` prefix), force flags (`-f`, `--force`, `--discard-changes`,
+`--pathspec-from-file`), `git reset --hard|--merge|--keep`, `git stash` (except
+`list`, `show`, `create`, `store`), `git clean -f` without a narrow pathspec,
+`git checkout-index -a` and `git read-tree -u|--reset`, including when wrapped in
+`bash -c`, `eval`, `nice`, `time`, `nohup`, `timeout` or `xargs`. Restoring HEAD
+would erase a newer failed attempt and revive an old passing receipt. Branch
+switches and file-specific restores outside `tickets/` stay allowed. The guard is a
+pattern-based safety net for documented mistake forms, not a complete shell
+boundary; the receipt and status checks remain the source of trust. When a ticket file is malformed or its state was hand
+edited, preserve the malformed contents as they are, report the validation error that
+the script or `scripts/pincer-status.sh` printed, and hand the repair to the user, who
+performs it in their own terminal. Then return through the lifecycle — `start`,
+`verify`, `done` — so the ticket carries fresh verification; a restored receipt is
+never evidence. Do not recommend restoring source files or unrelated edits as routine
+ticket repair. Automated recovery that preserves attempt history is later work (M1).
 
 ## Budget rules
 
@@ -73,5 +102,18 @@ previously authorized work.
 
 ## When all tickets are done
 
-Update the PRD to `status: built`, then finish with:
+Update the PRD to `status: built` and commit that change on its own (`PRD vN: built`).
+The built transition is part of the candidate that `$pincer-evaluate` reviews; it is
+never moved into a later evidence-only commit. Then finish with:
 "All tickets built. Run `$pincer-evaluate` for a final quality pass."
+
+## Authorization rule (shared by plan, narrow, code and evaluate)
+
+Reuse explicit authorization for the same scope and decisions; ask only about a
+material choice not already authorized, and prepare the concrete proposal before
+asking. A decision the user delegated (for example "pick the architecture") does not
+need another approval when you exercise it, but a newly discovered consequential
+choice is surfaced before implementation. Record the authorization basis and the
+scope it covers in the PRD or the handover. An agent-written record or a status
+field is not authenticated human approval. When resuming without the context that
+granted authorization, do not invent it — ask.

package/template/.agents/skills/pincer-evaluate/SKILL.md

@@ -20,13 +20,26 @@ run the pipeline, then present results.
    its ticket commits and recorded context. If it cannot be established, resolve
    that uncertainty before claiming a complete review. Record full commit IDs for
    `base` and `candidate` (`git rev-parse HEAD`), then review `git diff <base>..<candidate>`.
-   Require a clean candidate before review, excluding only the notes being written.
+   The candidate is the clean, committed tree that already includes the implementation,
+   the ticket closures and the PRD `status: built` commit: `git status --short` must be
+   empty before review. If anything is uncommitted or the PRD is not yet built, return
+   to `$pincer-code`; do not review a dirty tree.
 2. Dispatch a `code-quality-reviewer` agent with: the diff, the PRD's Success Criteria and
    Scope sections, and the list of tickets. If the diff is large, split by area and
    dispatch two in parallel. (No subagents on this platform? Review the diff yourself
    in a separate pass, applying `.claude/agents/code-quality-reviewer.md` as the rubric.)
-3. Yourself, in parallel, check spec compliance: does what was built match every ticket's
-   acceptance criteria and the PRD scope? List any gaps.
+   Keep the reviewer's report — or its explicit no-findings statement — for step 9,
+   where it is saved as an artifact; a review that left no record cannot be audited.
+3. Yourself, in parallel, check spec compliance. For every requirement `R-NN` in the
+   PRD record one disposition: `delivered` (evidence on this candidate), `blocked`
+   (required behavior failed or was left unverified — this blocks PASS; do not relabel
+   it a known limitation to pass), or `deferred` (only with explicit user authorization;
+   record the scope decision in the PRD's Out of Scope and evaluate the revised
+   candidate). Compare what was built against every ticket's acceptance criteria and
+   the PRD scope, and list any gaps. Whether the requirement map is complete and each
+   check is semantically adequate is your judgment as reviewer — record that judgment
+   in the evaluation; the kit is not a mechanical traceability engine and does not
+   validate requirement-revision impact.
 4. If the project has a UI, look at it — don't only read the code. Start it, open it in
    the browser (screenshot via Chrome DevTools MCP if available), and check it against
    the PRD's Visual Direction and Success Criteria. Note anything visibly broken or off.
@@ -44,28 +57,66 @@ run the pipeline, then present results.
    concrete bugs, silent failures, misleading code. Drop nitpicks and style opinions.
 7. Present findings as a short list with `file:line` references, ordered by severity.
    Security findings always rank above style-adjacent ones. For each, say whether you
-   recommend fixing now (within the timebox) or noting as known-issue.
+   recommend fixing now through a ticket or recording it as a known issue.
 8. Fix findings clearly within the authorized PRD through a new ticket associated with
    that PRD. Use `pincer-ticket.sh` to start, verify, and close it, then make a scoped
    `T-{NN}: {title}` commit. Ask only when a fix changes scope, architecture, or another
-   material decision; never make an ad-hoc `review: fixes` commit.
-9. Close out: write a brief `NOTES.md` at the repo root with frontmatter:
+   material decision; never make an ad-hoc `review: fixes` commit. Every fix commit
+   produces a new candidate: re-record `candidate`, re-run the checks against it, and
+   write fresh evidence in step 9 — never reuse a manifest from a previous candidate.
+9. Persist evidence for the candidate under `.prd/evidence/prd-vN/<candidate>/`:
+   - `checks/C-NN.log` — the command and a redacted summary or safe log of each
+     executable check. Never secrets, never an environment dump.
+   - `visual/<scenario>.png` — each visual capture from step 4, with its scenario,
+     viewport and observed result recorded in the manifest. When nothing renders,
+     record `visual_review: {applicable: false, reason}` and say why.
+   - `review/code-quality.md` — the reviewer's findings from step 2 with their
+     dispositions, or its explicit no-findings statement, recorded as a check of
+     kind `review` and referenced by the requirements it covers.
+   - `manifest.json` — evidence schema 1 (field list in the header of
+     `scripts/pincer-evidence.cjs`): selected PRD, full `base` and `candidate` IDs,
+     `created`, `environment` with tool limitations, `coverage_review` (your judgment
+     from step 3), one `requirements` entry per `R-NN` with its disposition, tickets
+     and check IDs, one `checks` entry per check with `kind`, `required`, `result`,
+     `command`, timestamp and artifact paths, and `artifacts` with digests from
+     `node scripts/pincer-evidence.cjs digest <file>...`.
+   A tool you cannot run yields a check with `result: unverified` and a note — never a
+   fabricated artifact. A deferred requirement carries `authorized_by` naming the
+   user's explicit authorization. Then run
+   `node scripts/pincer-evidence.cjs validate .prd/evidence/prd-vN/<candidate>/manifest.json --candidate <candidate> --prd .prd/prd-vN.md`
+   and correct the manifest until it prints `ok`; the same validator runs in status
+   and release. It checks the record's consistency, not that the commands ran.
+10. Close out: write a brief `NOTES.md` at the repo root with frontmatter:
    ```yaml
    ---
    prd: .prd/prd-vN.md
    base: <full reviewed base commit ID>
    candidate: <full reviewed candidate commit ID>
+   evidence: .prd/evidence/prd-vN/<candidate>/manifest.json
    ---
    ```
-   Record the candidate before the separate NOTES commit. Status accepts a later
-   commit only when its diff from the candidate changes solely `NOTES.md`; changes
-   to source, tickets, or PRD require reevaluation. Legacy notes without these
-   references do not establish readiness. Then describe what was built, what was cut
+   Then commit NOTES.md, the manifest and its listed artifacts — and nothing else —
+   as `evaluate: PRD vN candidate <short sha>`. Status accepts this later commit only
+   when its diff from the candidate is limited to `NOTES.md` and the evidence files
+   the manifest lists; changes to source, tests, configuration, tickets, the PRD or
+   other evaluations require reevaluation. Legacy notes without these references
+   do not establish readiness. Then describe what was built, what was cut
    and why, known issues, and what you'd do next with more time. Then a **Handover**
    section, written for the stranger who inherits this repo in six months: how to get
    oriented (which file to read first), what each dependency is for and why it earned
    its place, and what breaks first as the code ages (the riskiest assumption, the
-   least-tested path). Commit it. This is the first document a reviewer of this repo
-   should read.
-10. Suggest `$pincer-release` as the final step: "Run `$pincer-release` for a pass/fail audit of the
+   least-tested path). This is the first document a reviewer of this repo should read;
+   summarize the requirement dispositions from the manifest in it.
+11. Suggest `$pincer-release` as the final step: "Run `$pincer-release` for a pass/fail audit of the
    whole workflow's artifacts."
+
+## Authorization rule (shared by plan, narrow, code and evaluate)
+
+Reuse explicit authorization for the same scope and decisions; ask only about a
+material choice not already authorized, and prepare the concrete proposal before
+asking. A decision the user delegated (for example "pick the architecture") does not
+need another approval when you exercise it, but a newly discovered consequential
+choice is surfaced before implementation. Record the authorization basis and the
+scope it covers in the PRD or the handover. An agent-written record or a status
+field is not authenticated human approval. When resuming without the context that
+granted authorization, do not invent it — ask.

package/template/.agents/skills/pincer-narrow/SKILL.md

@@ -9,7 +9,10 @@ description: "Turn the approved PRD into local, AI-ready ticket files"
 
 You are decomposing the PRD into coherent, independently verifiable tickets stored as
 local markdown files (no external tracker needed). Ticket count and size follow the
-change's dependencies and risk, plus any budget the user supplied.
+change's dependencies and risk, plus any budget the user supplied. There is no hard
+one-to-two-ticket cap for small PRDs and no default timebox: cohesion and dependencies
+decide the count. A breakdown that follows the PRD needs no second approval; a newly
+discovered consequential choice is surfaced before implementation.
 
 **Initial request:** the text that follows the `$pincer-narrow` mention, if any (when omitted, use the playbook's documented default)
 
@@ -28,10 +31,29 @@ change's dependencies and risk, plus any budget the user supplied.
      brownfield work, begin with the smallest protected vertical change; add a
      characterization ticket before changing load-bearing code that lacks coverage.
    - Order by dependency; note blockers explicitly ("depends on T-01").
+   - Build the requirement map: for every `R-NN` in the PRD and each of its
+     scenarios, name the ticket that owns the implementation and the executable
+     check that exercises it, or an explicit review method when no executable check
+     exists. Record the IDs in each ticket's Context as `Implements: R-NN, R-MM`.
+     Enabling work that implements no requirement states its purpose in the ticket
+     Objective. Resolve missing coverage and conflicting criteria with the user
+     before implementation; do not start with an unmapped required scenario.
    - Every ticket gets a runnable command in its Verification block — a fenced `bash`
      block that exits 0 only when the ticket is done. `scripts/pincer-ticket.sh verify`
      runs it verbatim and stamps the receipt that `done` requires, so it must be
      non-interactive and self-contained (no "check by hand").
+   - Each Verification section opens with `Proves:` — what the check establishes and
+     which regression it detects. A check for an executable change must exercise
+     observable behavior (including relevant rejection paths and, in brownfield work,
+     preservation of existing behavior) and fail when the behavior is wrong, not only
+     when an identifier is renamed. Reuse adequate focused tests. A build, a syntax
+     check, or an identifier grep alone is not proof; static assertions are primary
+     evidence only for static contracts such as generated files, and `Proves:` says so.
+   - Adequacy is a judgment about what the command observes, never a word match: do
+     not call a command sufficient because it contains `grep`, `test`, or a runner
+     name, nor insufficient for lacking them. Manual visual judgment is recorded
+     separately in evaluation; a tool the check needs but cannot run yields an
+     explicit `unverified` result, never fabricated evidence or a silent waiver.
    - If the brief or stack implies automated tests, at least one ticket's verification
      command must be the test runner (e.g. `npm test`) — manual checks alone don't count.
    - Any ticket whose surface accepts external input (HTTP endpoint, form, file,
@@ -48,12 +70,29 @@ change's dependencies and risk, plus any budget the user supplied.
    numbering or old notes. The other state fields
    (`started`, `last_check`, `verified`, `finished`) are added later by `scripts/pincer-ticket.sh` —
    never write them yourself.
-4. Present the ticket list (number, title, size, dependencies) as a table.
+4. Present the ticket list (number, title, size, dependencies) as a table, followed
+   by the requirement map as a second table (requirement · scenario · ticket · check
+   or review method). Whether the map is complete and each check is adequate is your
+   judgment as the author; say so rather than presenting the table as mechanical proof.
 
-Present the concrete breakdown and build order. Reuse existing authorization for the same
-scope and order; ask only when the breakdown introduces a material decision or scope change.
+Present the concrete breakdown and build order as a report, not a question. Reuse
+existing authorization for the same scope and order.
 
-5. Once authorized, update the selected PRD frontmatter to `status: ticketed`. Inspect
-   existing staged changes, stage that PRD and the explicit new ticket paths, review
-   `git diff --cached`, and commit only those paths. Finish with:
+5. Finalize. A breakdown that follows the PRD is already authorized by the PRD: do not
+   ask whether to proceed. Update the selected PRD frontmatter to `status: ticketed`,
+   inspect existing staged changes, stage that PRD and the explicit new ticket paths,
+   review `git diff --cached`, and commit only those paths. Ask first — and finalize
+   once it is resolved — only when step 4 surfaced a newly discovered consequential
+   choice or a scope change the PRD does not cover. Finish with:
    "Tickets ready in `tickets/`. Run `$pincer-code` to start implementing."
+
+## Authorization rule (shared by plan, narrow, code and evaluate)
+
+Reuse explicit authorization for the same scope and decisions; ask only about a
+material choice not already authorized, and prepare the concrete proposal before
+asking. A decision the user delegated (for example "pick the architecture") does not
+need another approval when you exercise it, but a newly discovered consequential
+choice is surfaced before implementation. Record the authorization basis and the
+scope it covers in the PRD or the handover. An agent-written record or a status
+field is not authenticated human approval. When resuming without the context that
+granted authorization, do not invent it — ask.

package/template/.agents/skills/pincer-plan/SKILL.md

@@ -11,6 +11,14 @@ You are turning a task brief into a reviewable PRD. Scale discovery and detail t
 the change's uncertainty, risk, and any time budget the user supplied. The PRD feeds
 `$pincer-narrow` next.
 
+Choose the planning profile and record why it fits: `profile: small` for bounded
+scope, low risk, known behavior and straightforward verification; otherwise
+`standard` (the default). Few changed lines alone do not qualify — migrations,
+authorization boundaries, uncertain requirements and broad effects need proper
+investigation even for a tiny patch. Honor an explicit budget the user supplied;
+there is no default timebox, and a budget never silently cuts requirements —
+record any cut in Out of Scope.
+
 **Initial request:** the text that follows the `$pincer-plan` mention in the user's message (ask only if the required input is missing)
 
 First run `scripts/pincer-status.sh`. If a PRD already exists, preserve it and select
@@ -22,7 +30,11 @@ unless the user explicitly authorized a separate change.
 ## Phase 1: Discovery
 
 1. If `the text that follows the `$pincer-plan` mention in the user's message (ask only if the required input is missing)` contains the brief, extract what you can before asking anything.
-   Never ask a question the brief already answers.
+   Never ask a question the brief already answers. Preserve or link the original
+   brief in the PRD, and record the desired outcome, assumptions and exclusions.
+   If the user supplied a PRD, review it: keep its meaning and existing requirement
+   IDs; do not silently replace either. Where its structure needs adapting to the
+   template, record a mapping table (`their section or ID → R-NN`) inside the PRD.
 2. Ask only the questions whose answers would change the architecture or scope.
    Batch them (max 3–4 at once). Typical ones:
    - What does "done" look like — what will be run, demoed, or reviewed at the end?
@@ -70,6 +82,11 @@ concrete scope and architecture; do not repeat an approval already given for the
 ## Phase 4: Write the PRD
 
 1. Load `.claude/references/prd-template.md` and write all core sections.
+   In Requirements, assign stable `R-NN` IDs within the selected PRD: a revision
+   keeps existing IDs and adds new ones, never renumbers. Every requirement has
+   observable acceptance scenarios, the relevant failure paths, and the existing
+   behavior it must preserve — `$pincer-narrow` maps each scenario to a ticket and
+   a check, and `$pincer-evaluate` dispositions every ID.
 2. Include optional sections when risk or the product context warrants them.
 3. Save to the next unused `.prd/prd-v{N}.md` (create `.prd/` if needed), with `N`
    matching the filename and frontmatter:
@@ -78,6 +95,7 @@ concrete scope and architecture; do not repeat an approval already given for the
    version: {N}
    status: draft
    date: {today}
+   profile: small   # only when small; omit for standard
    ---
    ```
 4. If `.git/` doesn't exist, run `git init`. Commit the PRD and only the intended setup
@@ -87,3 +105,14 @@ concrete scope and architecture; do not repeat an approval already given for the
 Present the saved draft and obtain approval only when the same scope/architecture was not
 already authorized. Finish with: "PRD saved to `.prd/prd-v{N}.md`. Run `$pincer-narrow`
 to break it into work items."
+
+## Authorization rule (shared by plan, narrow, code and evaluate)
+
+Reuse explicit authorization for the same scope and decisions; ask only about a
+material choice not already authorized, and prepare the concrete proposal before
+asking. A decision the user delegated (for example "pick the architecture") does not
+need another approval when you exercise it, but a newly discovered consequential
+choice is surfaced before implementation. Record the authorization basis and the
+scope it covers in the PRD or the handover. An agent-written record or a status
+field is not authenticated human approval. When resuming without the context that
+granted authorization, do not invent it — ask.

package/template/.agents/skills/pincer-release/SKILL.md

@@ -8,7 +8,11 @@ description: "Audit the repo against the workflow checklist — pass/fail per it
 # $pincer-release — Workflow Audit
 
 You are auditing the current repo state against `docs/release-checklist.md`. Read-only:
-report pass/fail, never fix anything — fixes belong to the stage commands.
+report pass/fail, never fix anything — fixes belong to the stage commands. Release does
+not repair tickets, rewrite evidence, change PRD state, or publish. A check that mutates
+the candidate invalidates the audit: if `git status --short` is not empty afterwards,
+the verdict is FAIL and names the mutation. The verdict is reported to the user; a
+durable runtime-owned release record is later work.
 
 **Requested stage:** the text that follows the `$pincer-release` mention, if any (when omitted, use the playbook's documented default)
 
@@ -27,13 +31,23 @@ report pass/fail, never fix anything — fixes belong to the stage commands.
    - Receipts: every done ticket carries current `last_check` and `verified` evidence;
      any status warning fails the audit. Do not call `pincer-ticket.sh` from Release:
      it writes receipts and would invalidate the evaluated candidate.
+   - Evidence: `scripts/pincer-status.sh` runs the shared validator
+     (`scripts/pincer-evidence.cjs`) against the manifest `NOTES.md` names. The `Notes`
+     line must read `current` and the `Evidence` line `ok`; any other text fails the
+     audit with that diagnostic. Do not re-implement evidence checks and do not accept
+     screenshots described in chat: read the manifest's `checks`, requirement
+     dispositions and `visual_review`. Validation establishes that the record is
+     consistent, not that the commands ran — say so if asked.
+   - Every file the manifest lists is tracked, and `git status --short` is empty before
+     and after the audit.
    - Run the repository's candidate-wide release gate directly (`npm test`, or the
      equivalent declared by the project) and report its actual output. Any failure
      blocks PASS. Confirm `git status --short` remains clean afterward.
 4. For judgment items (tickets genuinely S/M, history reads as a story), give your
    verdict AND one sentence of evidence — never a bare pass.
 5. Present a table: checklist item | pass/fail/skipped | evidence. Order by stage.
-6. End with a one-line verdict: "PASS — workflow artifacts complete" or
-   "FAIL — {n} items failed; fix via {command}". For each failure, name the command
+6. End with a one-line verdict naming the candidate: "PASS — candidate {sha}: workflow
+   artifacts complete" or "FAIL — candidate {sha}: {n} items failed; fix via {command}".
+   Fixes go through a new ticket, a new candidate and a new evaluation. For each failure, name the command
    file (`.claude/commands/*.md`) whose instructions should be tightened if the
    failure is a workflow bug rather than a run mistake.

package/template/.agents/skills/pincer-status/SKILL.md

@@ -13,11 +13,13 @@ start of a session. Read-only: change nothing.
 ## Steps
 
 1. Run `scripts/pincer-status.sh`. It reads the artifacts on disk (`.prd/`, `tickets/`,
-   `NOTES.md`) and prints the PRD state, every ticket with its state and clock-based
-   elapsed time, what is blocked, build time against any explicit user budget, any warnings (a ticket
-   marked done without a verification receipt), and the next command to run.
+   `NOTES.md`) and prints the PRD state and profile, every ticket with its state and
+   clock-based elapsed time, what is blocked, wall-clock build time while a ticket is in
+   progress or against an explicit user budget, the evidence verdict for the evaluated
+   candidate, any warnings (each readiness problem once), and the next command to run.
 2. Report in three lines: where the workflow is, what is in progress or blocked, and the
    next command. Quote the `Next` line as-is.
 3. If a ticket is `in_progress`, read it and `git status`, then offer to resume it with
    `$pincer-code T-{NN}`. If the script printed a warning, surface it — a done ticket
    without a receipt was marked by hand and needs `scripts/pincer-ticket.sh verify T-{NN}`.
+   Never restore a ticket file from git to clear a warning; a failed attempt is a record.

package/template/.claude/commands/pincer-code.md

@@ -39,7 +39,11 @@ previously authorized work.
    conventions, and nothing else.
 3. **Verify:** `scripts/pincer-ticket.sh verify T-{NN}` — runs the Verification block and
    writes the receipt only if it exits 0. Red → fix and re-run; report the actual output,
-   not assumptions. Green output is the definition of done, not your confidence.
+   not assumptions. Green output is the definition of done, not your confidence. If the
+   check only validated syntax or a build, say so — that is not behavioral proof. A
+   visual judgment is recorded separately in evaluation, not as the receipt, and a tool
+   the check needs but cannot run yields an explicit `unverified` result, never
+   fabricated output.
 4. **Self-review the diff** before committing: silent failures (empty catches,
    un-awaited promises), leftover debug code, drift from the ticket's acceptance criteria.
    Then a security sweep of the same diff:
@@ -57,8 +61,33 @@ previously authorized work.
    Inspect `git status --short`, preserve pre-existing staged work, and stage only the
    explicit paths changed for this ticket plus its ticket file. Review `git diff --cached`
    before committing as `T-{NN}: {title}`.
-6. Give a one-line progress update using the elapsed figure from
-   `scripts/pincer-status.sh` ("T-02 done, 3 remaining, 38m elapsed") and continue.
+6. Give a one-line progress update ("T-02 done, 3 remaining") and continue. Quote the
+   wall-clock elapsed figure from `scripts/pincer-status.sh` when it shows one — it
+   appears while a ticket is in progress or a budget is set, and it is not a measure
+   of active execution time.
+
+## Recovering a ticket file
+
+Ticket lifecycle fields are written only by `scripts/pincer-ticket.sh`, and the guard
+also blocks shell restores that would touch ticket files from the assistant's shell:
+`git checkout`/`git restore`/`git switch` naming a ticket path or a normalized
+pathspec that cannot be shown to stay outside `tickets/` (the whole tree, `.`, `:/`,
+`:(top)`, globs, absolute or unexpanded paths, `tickets/…` in any spelling, a
+`-C tickets` prefix), force flags (`-f`, `--force`, `--discard-changes`,
+`--pathspec-from-file`), `git reset --hard|--merge|--keep`, `git stash` (except
+`list`, `show`, `create`, `store`), `git clean -f` without a narrow pathspec,
+`git checkout-index -a` and `git read-tree -u|--reset`, including when wrapped in
+`bash -c`, `eval`, `nice`, `time`, `nohup`, `timeout` or `xargs`. Restoring HEAD
+would erase a newer failed attempt and revive an old passing receipt. Branch
+switches and file-specific restores outside `tickets/` stay allowed. The guard is a
+pattern-based safety net for documented mistake forms, not a complete shell
+boundary; the receipt and status checks remain the source of trust. When a ticket file is malformed or its state was hand
+edited, preserve the malformed contents as they are, report the validation error that
+the script or `scripts/pincer-status.sh` printed, and hand the repair to the user, who
+performs it in their own terminal. Then return through the lifecycle — `start`,
+`verify`, `done` — so the ticket carries fresh verification; a restored receipt is
+never evidence. Do not recommend restoring source files or unrelated edits as routine
+ticket repair. Automated recovery that preserves attempt history is later work (M1).
 
 ## Budget rules
 
@@ -71,5 +100,18 @@ previously authorized work.
 
 ## When all tickets are done
 
-Update the PRD to `status: built`, then finish with:
+Update the PRD to `status: built` and commit that change on its own (`PRD vN: built`).
+The built transition is part of the candidate that `/pincer-evaluate` reviews; it is
+never moved into a later evidence-only commit. Then finish with:
 "All tickets built. Run `/pincer-evaluate` for a final quality pass."
+
+## Authorization rule (shared by plan, narrow, code and evaluate)
+
+Reuse explicit authorization for the same scope and decisions; ask only about a
+material choice not already authorized, and prepare the concrete proposal before
+asking. A decision the user delegated (for example "pick the architecture") does not
+need another approval when you exercise it, but a newly discovered consequential
+choice is surfaced before implementation. Record the authorization basis and the
+scope it covers in the PRD or the handover. An agent-written record or a status
+field is not authenticated human approval. When resuming without the context that
+granted authorization, do not invent it — ask.