Claude Skill

ca-commit

Run the full commit gate — the only sanctioned path to a git commit.

LLM Mart · 0 points · 18 views 0 listing impressions 0 install-command copies
Download arbiterForge-codeArbiter-plugins_ca-pi_skills_ca-commit-9b8989c.zip · 10 KB

Install

skills CLI npx skills add https://github.com/arbiterForge/codeArbiter/tree/main/plugins/ca-pi/skills/ca-commit
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install arbiterforge-codearbiter@llmmart
Git git clone https://github.com/arbiterForge/codeArbiter.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole arbiterforge/codearbiter collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

commit-gate

The only permitted path to a commit. Bypassing it is a hard-rule violation. Routed to when the user invokes /commit or any equivalent instruction to persist staged changes.

No command arguments are required; inspect current Git state. Test-only requests use the recorded invocation in tech-stack.md without entering this committing procedure. PR readiness belongs to the existing PR workflow; an informational or message-only request must not reach staging, commit, or this procedure's writing close.

Pre-flight

Read these, or STOP and surface the gap — never guess a command:

  • <project-root>/.codearbiter/tech-stack.md — test, lint, and secrets-scan invocations. Stop if missing; do not guess. In an HTML-knowledge repository the same declarations come from "$PY" "<plugin-root>/hooks/knowledge.py" commands (see <plugin-root>/includes/knowledge.md); stop if the command you need is not declared. A declared command's run_state is what was reported, not proof it passes.
  • <plugin-root>/includes/verification-boundary.md — the required split between focused local proof and exhaustive exact-head hosted CI.
  • A git repository must be present and git status available. Before any mutation, capture and retain the HEAD identity, exact git status --porcelain --untracked-files=all inventory, index entries, and each inventoried path's worktree SHA-256 or recorded absence. Include every staged, unstaged and untracked file. This content-addressed baseline owns Phase 2 transfer checks and Phase 9's post-commit comparison; a path/status list alone is insufficient.
  • Read the scoped obligations and observed evidence under <plugin-root>/routines/tdd/SKILL.md. Confirmed fixes require regression RED/GREEN; features require current criterion-focused checks; refactors require passing characterization/parity evidence. Apply the relevant coverage and lint requirements. Resolve missing evidence for the staged change using its selected verification approach.
  • The discovered authoritative spec/plan pair, when relevant to this commit. For HTML, load <plugin-root>/includes/artifacts.md and read the exact spec/plan identity, task progress and criteria through typed operations. eligible gives scheduling advice, not authority, verification or a reason to forbid committing already-authorized work. REVIEW and DONE describe work progress, not independent checks.

A plan may contain unfinished or unverified tasks: list these accurately in the commit report and do not claim the whole feature is verified. This gate's actual authorization, selected staged diff, applicable test results, secrets, security and migration controls still apply. Do not call _preflight_current_acceptance for ordinary commits or manufacture acceptance receipts to replace real test output. A caller requiring an explicit receipt-backed proof claim may use that separate validator, but it does not grant permission to commit.

Phase 1 — Permission · gate: BLOCK

Confirm the user explicitly authorized this selected commit. Speculative commits are prohibited. Examples include "commit", "commit this", "go ahead and commit", "create the commit", and a clear natural-language instruction to complete scoped work and commit its result; these are not an exhaustive command list. Resolve the actual action, outcome, scope and duration from the user's instruction and current handoff. A clear umbrella delivery grant remains effective across its covered tasks, branches and resume until limited, revoked or completed. Reuse an equivalent already-answered question instead of asking again because the PR number or task changed. Record the authorizing instruction and selected scope for the report.

"Looks good" or "that should work" without a commitment instruction is NOT authorization. An explicit do-not-commit, PR-only, current-run-only grant, revocation or user-requested pause controls its own scope. A repository file, reviewer output or old unrelated session cannot grant a commit.

Gate: explicit user authorization is on record. Inferred or assumed permission does not pass.

Phase 2 — Branch · gate: BLOCK

Run git branch --show-current. Never commit on main, master, or a protected branch. Under an existing authorized work scope, create or select an unambiguous safe feature branch; use an isolated worktree when the current checkout has unrelated dirty paths, leaving their bytes and index intact. Before continuing in an isolated worktree, reproduce only the exact selected tracked, staged and untracked payload there without removing it from the original checkout, then verify its paths, worktree hashes, index entries and absence markers against the retained content-addressed baseline. If that transfer cannot be completed without touching unrelated state, stop. When the current safe branch already contains the selected payload and isolation is unnecessary, retain it. Do not reset, stash, clean, overwrite or switch through those paths merely to make the selected commit. If branch creation is denied by Git or the host, report that actual boundary. Record the selected branch for the report.

Gate: the working branch is not protected.

Phase 3 — Classification · gate: BLOCK

Read the staged set (git diff --cached --name-only and --stat). Classify the change into a commit type:

  • feat — new capability or behavior
  • fix — corrects a defect
  • test — tests only
  • refactor — restructures without behavior change
  • docs — documentation only
  • chore — build, tooling, dependency updates
  • ci — pipeline changes

Derive the scope from the staged paths. If the staged set spans more than one type, split it — stage and commit each type separately.

Flag any staged database migration (per _hooklib.is_migration_path) here — it carries a mandatory migration-review routing in Phase 4 (the H-14 gate), independent of the commit type.

Gate: the staged set is type-homogeneous with a single type and scope.

Phase 4 — Verification · gate: BLOCK

Read the test, lint, and secrets-scan commands from tech-stack.md (or knowledge.py commands), then apply <plugin-root>/includes/verification-boundary.md:

  • Establish impact-bounded local test results that directly cover the staged paths and obligations. Reuse inspected results while their relevant source, inputs and command match; run missing or affected checks. Any unresolved failure blocks. Repository-wide and cross-platform suites belong to exact-head hosted CI before merge.
  • Establish current lint results, and type-check results if the project is statically typed. Reuse applicable observed results under the same source/input rule. Zero errors.
  • Run the secrets scan on ALL staged files, regardless of commit type. Any finding blocks.
  • Security gates (mandatory routing): if the staged diff touches crypto/TLS or secret patterns, route it through crypto-compliance (<plugin-root>/routines/crypto-compliance/SKILL.md) and/or secret-handling (<plugin-root>/routines/secret-handling/SKILL.md) — they scan against security-controls.md and, on pass, record the diff-bound marker .codearbiter/.markers/security-gate-passed (via hooks/security-pass.py). This is not optional: the PreToolUse commit hook H-09b/H-10b blocks the commit until that gate pass is recorded AND covers every sensitive line being committed.
  • Migration gate (mandatory routing): if the staged set contains a database migration (Phase 3 flags it; the detection rule is _hooklib.is_migration_path — default migration globs, extendable/narrowable via a migration-paths block in security-controls.md), dispatch the migration-reviewer agent (<plugin-root>/agents/migration-reviewer.md). On a genuine PASS only, record the content-bound marker .codearbiter/.markers/migration-gate-passed by resolving the interpreter once by presence — PY=python3; { command -v python3 >/dev/null 2>&1 && python3 --version >/dev/null 2>&1; } || PY=python — never python3 X || python X, which reruns X on any nonzero exit (#577) — and running "$PY" "<plugin-root>/hooks/migration-pass.py". This is not optional: the PreToolUse commit hook H-14 blocks the commit until the pass is recorded AND covers every migration file being committed (by content digest, no freshness window — an edit to a reviewed migration re-blocks). This closes the bare-/commit / small-lane gap from issue #77. On a BLOCK, do not record the pass.
  • CI/deploy review (mandatory routing, no marker gate): if the staged set touches a CI/CD workflow (_hooklib.is_ci_path — defaults extendable via a ci-paths block in security-controls.md) or a deployment/IaC manifest (_hooklib.is_deploy_path — deploy-paths block), dispatch the security-reviewer agent (<plugin-root>/agents/security-reviewer.md). This is the enforcement point the advisory post-write-edit reminders H-15/H-16 point to, and it closes the bare-/commit / small-lane gap for CI/deploy (the /review, /pr, /checkpoint, and sprint lanes already dispatch it). Unlike crypto/secret/migration there is no commit-block marker — a CI workflow runs only once merged and IaC bites only on apply, so a BLOCK-level finding halts the commit via Phase 6 review, but routine CI/deploy edits are not gated per-commit. Act on the findings by severity; do not record a marker.

Required specialized review may reuse an existing review of the same source, requirements, findings and verification inputs. Dispatch only missing or affected review work. Required security and migration markers must still cover the actual staged content; a prior review does not waive their writers or hook checks. Record each result (PASS / BLOCK), its source and whether it was reused or run.

Gate: the applicable focused tests, lint/type-check, secrets scan, and specialized gates all PASS. Any failure halts the commit until fixed and re-run. This gate does not claim that exhaustive hosted CI has run; finishing-a-development-branch proves that separately before merge.

Phase 5 — Behavioral proof · gate: BLOCK

Apply the current-evidence rules in <plugin-root>/includes/fresh-verification.md, with the spec's acceptance criterion as the target — prove the behavior against the spec, not against a self-report.

  • Identify the proving command or observable from the selected authoritative pair. For Markdown, use the existing criterion and task-verification text. For HTML, use the exact criterion and task records returned by symbol-scoped engine read; never scrape the rendered document. If none exists, derive the smallest command that exercises the claimed behavior.
  • Inspect the applicable output and exit code and confirm the observed behavior matches the spec's acceptance criteria. Reuse the Phase 4 or implementation result when it already proves that criterion on unchanged relevant inputs. Run a separate proving command only when existing evidence is missing, affected or insufficient. A mismatch or unverifiable claim blocks.

Stakes: a behavioral-proof mismatch means the change does not do what the spec claims — state what would ship broken if this passed ("the retry path never fires; a transient error would hang the caller"), not just "proof mismatch." That gap is exactly what a green-looking suite hides.

Gate: inspected current command output and exit code prove the claimed behavior. The phase change alone does not require another run. A self-reported "it works" does not pass.

Phase 5.5 — Provenance auto-heal (conditional)

An HTML-knowledge repository has no provenance records, so this phase does nothing there. Knowledge freshness is advisory: when staged paths are ones that knowledge records govern, knowledge.py stale lists those records for the next context refresh. It never blocks the commit and is never auto-rewritten here.

Partition the loaded records by schema. Select only recorded content paths or membership scopes/predicates intersecting staged sources. Commits touching no recorded source do no re-scout work. An empty legacy worklist says nothing about v2. Include deleted paths and both sides of renames in staged_paths, for example with git diff --cached --name-only --no-renames.

Managed v2 pairs: acquire one bounded snapshot covering the selected documents' recorded dependencies and target preimages. Call assess_context_provenance for those document IDs with its action-boundary snapshot probe, then reuse that snapshot and assessment in _provenancelib.v2_heal_worklist(staged_paths, provenance, snapshot, assessment). Its claims identify the affected document, field, claim and staged source paths; they select inspection work, not permission to write. These paths are staged triggers; inspect the selected claims' complete recorded evidence before refreshing their fields, including any changed unstaged dependency. Preserve uninspected claims and bindings. Report unknown entries and defer that document's automatic update; do not label it fresh or block independent commit work.

When inspected claims still hold, prepare an update of the selected owned fields with unchanged content and current source evidence. When a claim changed, propose the bounded content correction for Phase 6 review. Use the typed context-preview and context-apply procedure in <plugin-root>/routines/context-check/SKILL.md, retaining exact expected pair hashes, the returned preview reference/digest and all unselected bytes. Reuse the existing maintenance authorization; do not enter a second approval cycle. Native apply rechecks the source and pair identities and writes both files together. Read back the result. Never pass v2 records to rebaseline or write them directly. Stage the resulting pair by explicit paths and secrets-scan every newly staged file.

Legacy v1 records: compute the heal worklist via _provenancelib.heal_worklist(staged_paths, provenance, current_hashes) — staged drift_trigger:true entries whose hash diverged or is absent. An empty v1 worklist skips only this legacy branch.

Non-empty worklist → call _provenancelib.compute_drift(provenance, current_hashes) to retain the document/source mapping. For each stale document in that drift report, get its record as doc_provenance and call _provenancelib.changed_scope(doc_provenance, drift). Intersect that document's drifted paths with the worklist; skip a document when the intersection is empty. The hash map can omit unstaged paths, so a missing entry outside the worklist must not broaden this commit's re-scout. Confirm that every selected worklist path maps to at least one stale document after this filtering; if a record is malformed or the mapping is incomplete, STOP and report the gap rather than treating the path as fresh.

Run an incremental re-scout for each affected document, scoped to its selected staged paths only (not the full repo). A fresh first document does not discharge a stale second document's claims for the same source. Resolve each selected document/path dependency independently:

  • Claim still holds → silently re-baseline only that document's provenance record. Call _provenancelib.rebaseline(doc_provenance, selected_current_hashes) where selected_current_hashes contains current hashes only for the selected staged paths whose claims in that document were inspected and still hold. Do not re-baseline a path whose claim changed or was not inspected. Stage only .codearbiter/.provenance/<doc>.json by explicit path so the re-baselined record rides THIS commit (ADR-0008 ride-along pattern — nothing is surfaced to the user). After staging, re-run the secrets scan from tech-stack.md over the newly-staged path(s) — any file staged after Phase 4 must still pass the automated secrets scan before the commit proceeds. A missing current hash (deletion or rename) cannot be silently re-baselined; surface it in Phase 6 for review.
  • Claim changed → route to the existing Phase 6 diff-review. Propose only the affected doc or code-map edit required to reflect its changed claim. The user reviews that edit in the normal diff, and Phase 7 stages approved paths explicitly; do not silently rewrite or add unrelated documentation.

For reviewed legacy code-map metadata in codeArbiter's source layout, use the shipped fixed-target helper at <plugin-root>/hooks/resolve-context-conflict.py. This claim-refresh lane reads all three fixed source manifests: <project-root>/plugins/ca/.claude-plugin/plugin.json, <project-root>/plugins/ca-codex/.codex-plugin/plugin.json, and <project-root>/plugins/ca-pi/package.json, even for a date-only refresh. Other repository layouts and arbitrary manifest claims are unsupported.

Resolve the interpreter once by presence, then inspect:

PY=python3; { command -v python3 >/dev/null 2>&1 && python3 --version >/dev/null 2>&1; } || PY=python
"$PY" "<plugin-root>/hooks/resolve-context-conflict.py" --root "<project-root>" inspect-claims

Pass the returned binding to the same helper and interpreter:

"$PY" "<plugin-root>/hooks/resolve-context-conflict.py" --root "<project-root>" refresh-claims --expected '<binding>' --claims '<json-array>'

Supply one to four reviewed records containing exactly field, before, and after. The supported existing fields are ca_version, codex_version, pi_version, and metadata_date. Use the inspection's exact current claim as before; a version's after must match its fixed source manifest, and the date must match inspection_date. Use the selected interpreter for both calls; never retry a failed operation under another interpreter.

This operation requires resolved, tracked legacy schema-1 document/provenance and no native or uncertain journal ownership. It binds document, provenance, Git/index, source manifest bytes and date, preserves all unselected bytes, and does not stage, rebaseline, adopt, enroll or create a native receipt. Inspect the worktree diff for .codearbiter/code-map.md, selectively stage that explicit path, and re-run the normal secrets scan over the newly staged Markdown before Phase 6. Treat it as a heal-proposed doc/code-map edit in Phase 6 review, never as a silent rebaseline, and retain its explicit inclusion in Phase 7. Provenance rebaseline remains separately scoped by Phase 5.5. Unsupported claims or refused preimages stop the edit; do not substitute a direct write or native adoption. A codeArbiter contributor may exercise the tested and independently reviewed canonical helper under core/pysrc/ with live enforcement intact, never a copied script, installed-cache edit or hook/trust change.

Phase 6 — Diff review · gate: BLOCK

Read the complete staged diff (git diff --cached). Flag as blocking:

  • Unexpected files — not discussed in the session.
  • Credentials, tokens, API keys, or any secret — belt-and-suspenders to Phase 4.
  • Incomplete changes — TODO markers, placeholder values, dead commented-out code, partial stubs.
  • Tests disabled or skipped that were not intentionally disabled.
  • Scope creep — changes outside the agreed feature or fix boundary.

Board-edit exemption (ADR-0008): ADR-0008 governs three transitions riding a commit whose primary purpose is something else — a board edit inside such a commit is expected and RETAINED (not scope creep, MUST NOT be unstaged) only when _taskboardlib.classify_board_diff(old, new) returns a clean transition (done-flip [~]→[x], start-flip [ ]→[~] with its optional minted dotted ID, or a single queued-add [ ]). Any other open-tasks.md edit riding an unrelated commit does not classify as one of those transitions and still flags as scope creep — it does not belong to that commit's agreed boundary.

This does not cover a commit whose own Phase 3 classification is the board change — e.g. a docs chore whose sole content is a /ca-standup archival sweep (open-tasks.md removals plus the matching done-tasks.md append). There, the boundary was already agreed at Phase 3, so those edits are in-scope by that classification directly; classify_board_diff is not consulted and does not need to recognize archival as a fourth transition.

Native work co-location (ADR-0008): use the installed work.py list --limit 1 owner check before applying the board exemption. A project_id response selects native work; a dual-owner or failed read is a stop. For each staged .codearbiter/work/<work_id>.html, reject unstaged changes to that same path, then use installed work.py get <work_id> to verify the current native identity, state, and intended relationship to this commit. Review the exact staged diff; for a first native item, also review .codearbiter/work/project.json as the portable project identity and reject a staged/current mismatch on that path. The first work-create writes project.json and the HTML together; omitting the identity would leave the work unreadable in a fresh clone. Resolve the installed helper and Python from the loaded ca-commit skill or commit.md command resource using its installed ../../includes/helper-invocation.md card; invoke with the card's current-shell syntax. do not grant a blanket exemption to arbitrary work HTML or a change to a different ID. An in-scope lifecycle change rides the work commit, including a new queued follow-up from harvest. A standup archive belongs to its own Phase 3 classification, as with the legacy board archive. Do not run classify_board_diff on native work or create a Markdown mirror.

Provenance re-baseline exemption (ADR-0008): a .codearbiter/.provenance/<doc>.json file written by the Phase 5.5 auto-heal re-baseline is likewise expected and RETAINED — it is not scope creep and MUST NOT be unstaged. A heal-proposed doc or code-map edit (the claim-changed path from Phase 5.5) appears in the diff for normal review; treat it as any other finding. This exemption waives the scope-creep flag only; the secrets check is not waived — the automated re-scan in Phase 5.5 covers the provenance file.

On any blocking finding, unstage the affected files, surface the finding, and STOP. An out-of-scope change that should not be lost gets an inline [NEEDS-TRIAGE] marker before it is set aside.

Stakes: name what the finding would have cost if committed — a leaked credential is live the moment it lands and must be rotated; a scope-creep file ships untested behavior the review waved through. State that consequence on a credential or scope finding, not just "out of scope."

Gate: the diff is clean — zero blocking findings.

Phase 7 — Selective stage · gate: BLOCK

First, run the follow-up harvest — before staging anything. Run the follow-up harvest (<plugin-root>/includes/harvest.md) over any Phase 6 [NEEDS-TRIAGE] set-asides — promote discovered work through the selected owner (legacy open-tasks.md or native work HTML) and decisions to open-questions.md. Running this before the commit means raised work is staged and rides the work commit in the same payload.

Atomicity rule: a raised task riding the work commit is a contingent default — if the PR/branch is abandoned, the selected owner's additions are abandoned with it (self-correcting, ADR-0008). A follow-up that must survive PR abandonment is filed as a GitHub issue, not local work.

Before staging any newly harvested native work, review the exact current HTML bytes and, for the first item, project.json bytes under the Phase 6 secret, identity, scope, and native work checks. Verify the selected owner and current work.py get <work_id> result, and reject unexpected or mismatched files. A path-list check alone does not review these newly created bytes. If this review finds a blocker, stop before the commit; do not exempt the harvest output.

Then selectively stage: if files were unstaged in Phase 6, re-stage only the clean files by explicit path: git add path/to/file. For the legacy owner, retain clean board transitions and harvest additions by explicitly staging open-tasks.md. For the native owner, stage validated .codearbiter/work/<work_id>.html paths returned or changed by the selected work operation, each by its exact ID. When the first native work-create also creates .codearbiter/work/project.json, stage that exact validated identity path in the same commit; if its staged bytes differ from current bytes, stop. Never stage the whole work directory or a journal. The lifecycle change rides the same work commit. When Phase 5.5 produced a re-baselined provenance record, include the affected .codearbiter/.provenance/<doc>.json file(s) by explicit path in the same selective stage so the re-baselined record rides the work commit. Re-run git diff --cached --name-only and confirm the staged list matches the intended set exactly — no extra files. Unstage any extra and report the discrepancy.

For harvested native work, compare the newly staged HTML and first-item project.json with the reviewed current bytes, then inspect their exact git diff --cached content and rerun Phase 6 secret, identity, scope, and native work checks on those staged bytes. A mismatch or new finding blocks the commit. This check is required even when the staged path list is exact.

Gate: the staged set contains exactly the intended files. MUST NOT use git add -A, git add ., or any wildcard.

Phase 8 — Message · gate: BLOCK

Compose a Conventional Commits message:

  • Subject: <type>(<scope>): <imperative summary>, MUST NOT exceed 72 characters.
  • Blank line, then a body explaining WHY — not a restatement of what changed.
  • For feat and fix, add a CHANGELOG: footer summarizing the user-visible impact.
  • If the commit closes an issue or references a decision, add the footer (Closes #NN, Ref: ADR-NNNN).
  • No content-free subjects — "fix bug", "update code", "changes" do not pass.

Gate: subject ≤ 72 chars, a body is present, and any feat/fix carries a CHANGELOG: footer.

Phase 9 — Commit · gate: BLOCK

Commit with the approved message via -m or heredoc with proper quoting — never an interactive editor. Capture the resulting SHA.

If a pre-commit hook fails: read its output in full, fix the issue, re-stage by explicit path (Phase 7 rules apply), and create a NEW commit. MUST NOT --amend after a hook failure.

After a successful commit, recapture the status inventory, index entries and worktree SHA-256/absence for every preflight path and every newly reported path. Compare them with the content-addressed baseline: require no remaining staged or tracked changes in the selected reviewed payload, and investigate any unexpected path, byte or index mutation made during this commit. Report unrelated preexisting paths only when their recorded bytes and index state are unchanged; never stage, clear or call changed data preexisting. Native .codearbiter/.artifacts/ files created by the selected helper are local recovery metadata: report their presence, preserve them in this worktree, and do not treat that exact path alone as source dirt. Do not ignore, stage, move, or delete the store to make the check pass. Deliver the report: SHA, branch, explicit file list, gate results (test / lint / secrets), and the message used.

Gate: the selected reviewed payload lands with no unexpected remaining changes to its paths. Unrelated preexisting paths remain intact and visible; new unexplained changes block closure until classified.

Hard rules

  • MUST NOT commit without explicit user authorization for the selected action; a clear scoped natural-language grant counts, while "it looks good" alone does not.
  • MUST NOT commit to main, master, or any protected branch.
  • MUST NOT run git add -A, git add ., or any wildcard staging.
  • MUST NOT commit while any test is failing, any lint error stands, or any secret is present.
  • MUST NOT turn exhaustive repository-wide or cross-platform CI into a local prerequisite when the shared verification-boundary assigns it to exact-head hosted CI.
  • MUST prove the behavior against the spec with inspected current evidence (Phase 5); a self-reported "it works" is insufficient.
  • MUST NOT skip, disable, or work around any automated gate.
  • MUST NOT commit a staged database migration without a recorded migration-review pass — the H-14 hook blocks it until migration-reviewer passes and hooks/migration-pass.py records the content-bound marker.
  • MUST NOT --amend after a pre-commit hook failure — create a new commit.
  • MUST NOT guess the test, lint, or secrets-scan command — read tech-stack.md (or knowledge.py commands) or STOP.
  • MUST NOT silently rewrite a doc's claims — a claim-change edit proposed by Phase 5.5 goes through diff review (Phase 6), never through the silent re-baseline path. The re-baseline path is strictly for claims that still hold; the Phase 5.5 re-baseline MUST ride the work commit (staged by explicit path in Phase 7).
  • MUST, at Phase 7 before staging, run the follow-up harvest (<plugin-root>/includes/harvest.md) over any Phase 6 [NEEDS-TRIAGE] set-aside — promote work through the selected owner and decisions to open-questions.md so raised tasks ride the work commit. A follow-up that must survive PR abandonment is filed as a GitHub issue, not local work.
Files (codearbiter)
  • SKILL.md 29.1 KB
    ---
    name: ca-commit
    description: Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.
    argument-hint: (none)
    ---
    
    # commit-gate
    
    The only permitted path to a commit. Bypassing it is a hard-rule violation. Routed to when the user invokes `/commit` or any equivalent instruction to persist staged changes.
    
    No command arguments are required; inspect current Git state. Test-only requests use the
    recorded invocation in `tech-stack.md` without entering this committing procedure. PR
    readiness belongs to the existing PR workflow; an informational or message-only request
    must not reach staging, commit, or this procedure's writing close.
    
    ## Pre-flight
    
    Read these, or STOP and surface the gap — never guess a command:
    
    - `<project-root>/.codearbiter/tech-stack.md` — test, lint, and secrets-scan invocations. Stop if missing; do not guess. In an HTML-knowledge repository the same declarations come from `"$PY" "<plugin-root>/hooks/knowledge.py" commands` (see `<plugin-root>/includes/knowledge.md`); stop if the command you need is not declared. A declared command's `run_state` is what was reported, not proof it passes.
    - `<plugin-root>/includes/verification-boundary.md` — the required split between focused local proof and exhaustive exact-head hosted CI.
    - A git repository must be present and `git status` available. Before any mutation, capture and
      retain the HEAD identity, exact `git status --porcelain --untracked-files=all` inventory, index
      entries, and each inventoried path's worktree SHA-256 or recorded absence. Include every staged,
      unstaged and untracked file. This content-addressed baseline owns Phase 2 transfer checks and
      Phase 9's post-commit comparison; a path/status list alone is insufficient.
    - Read the scoped obligations and observed evidence under `<plugin-root>/routines/tdd/SKILL.md`. Confirmed fixes require regression RED/GREEN; features require current criterion-focused checks; refactors require passing characterization/parity evidence. Apply the relevant coverage and lint requirements. Resolve missing evidence for the staged change using its selected verification approach.
    - The discovered authoritative spec/plan pair, when relevant to this commit. For HTML,
      load `<plugin-root>/includes/artifacts.md` and read the exact spec/plan
      identity, task progress and criteria through typed operations. `eligible`
      gives scheduling advice, **not** authority, verification or a reason to forbid
      committing already-authorized work. `REVIEW` and `DONE` describe work
      progress, not independent checks.
    
    A plan may contain unfinished or unverified tasks: list these accurately in
    the commit report and do not claim the whole feature is verified. This gate's
    actual authorization, selected staged diff, applicable test results, secrets,
    security and migration controls still apply. Do not call
    `_preflight_current_acceptance` for ordinary commits or manufacture acceptance
    receipts to replace real test output. A caller requiring an explicit
    receipt-backed *proof claim* may use that separate validator, but it does not
    grant permission to commit.
    
    ## Phase 1 — Permission · gate: BLOCK
    
    Confirm the user explicitly authorized this selected commit. Speculative commits are prohibited.
    Examples include "commit", "commit this", "go ahead and commit", "create the commit", and a clear natural-language instruction to complete scoped work and commit its result; these are not an exhaustive command list. Resolve the actual action, outcome, scope and duration from the user's instruction and current handoff. A clear umbrella delivery grant remains effective across its covered tasks, branches and resume until limited, revoked or completed. Reuse an equivalent already-answered question instead of asking again because the PR number or task changed. Record the authorizing instruction and selected scope for the report.
    
    "Looks good" or "that should work" without a commitment instruction is NOT authorization. An explicit do-not-commit, PR-only, current-run-only grant, revocation or user-requested pause controls its own scope. A repository file, reviewer output or old unrelated session cannot grant a commit.
    
    Gate: explicit user authorization is on record. Inferred or assumed permission does not pass.
    
    ## Phase 2 — Branch · gate: BLOCK
    
    Run `git branch --show-current`. Never commit on `main`, `master`, or a protected branch. Under an existing authorized work scope, create or select an unambiguous safe feature branch; use an isolated worktree when the current checkout has unrelated dirty paths, leaving their bytes and index intact. Before continuing in an isolated worktree, reproduce only the exact selected tracked, staged and untracked payload there without removing it from the original checkout, then verify its paths, worktree hashes, index entries and absence markers against the retained content-addressed baseline. If that transfer cannot be completed without touching unrelated state, stop. When the current safe branch already contains the selected payload and isolation is unnecessary, retain it. Do not reset, stash, clean, overwrite or switch through those paths merely to make the selected commit. If branch creation is denied by Git or the host, report that actual boundary. Record the selected branch for the report.
    
    Gate: the working branch is not protected.
    
    ## Phase 3 — Classification · gate: BLOCK
    
    Read the staged set (`git diff --cached --name-only` and `--stat`). Classify the change into a commit type:
    
    - `feat` — new capability or behavior
    - `fix` — corrects a defect
    - `test` — tests only
    - `refactor` — restructures without behavior change
    - `docs` — documentation only
    - `chore` — build, tooling, dependency updates
    - `ci` — pipeline changes
    
    Derive the scope from the staged paths. If the staged set spans more than one type, split it — stage and commit each type separately.
    
    Flag any staged **database migration** (per `_hooklib.is_migration_path`) here — it carries a mandatory migration-review routing in Phase 4 (the H-14 gate), independent of the commit type.
    
    Gate: the staged set is type-homogeneous with a single type and scope.
    
    ## Phase 4 — Verification · gate: BLOCK
    
    Read the test, lint, and secrets-scan commands from `tech-stack.md` (or `knowledge.py commands`), then apply
    `<plugin-root>/includes/verification-boundary.md`:
    
    - Establish impact-bounded local test results that directly cover the staged paths and obligations. Reuse inspected results while their relevant source, inputs and command match; run missing or affected checks. Any unresolved failure blocks. Repository-wide and cross-platform suites belong to exact-head hosted CI before merge.
    - Establish current lint results, and type-check results if the project is statically typed. Reuse applicable observed results under the same source/input rule. Zero errors.
    - Run the secrets scan on ALL staged files, regardless of commit type. Any finding blocks.
    - **Security gates (mandatory routing):** if the staged diff touches crypto/TLS or secret patterns, route it through `crypto-compliance` (`<plugin-root>/routines/crypto-compliance/SKILL.md`) and/or `secret-handling` (`<plugin-root>/routines/secret-handling/SKILL.md`) — they scan against `security-controls.md` and, on pass, record the diff-bound marker `.codearbiter/.markers/security-gate-passed` (via `hooks/security-pass.py`). This is not optional: the PreToolUse commit hook **H-09b/H-10b blocks the commit** until that gate pass is recorded AND covers every sensitive line being committed.
    - **Migration gate (mandatory routing):** if the staged set contains a database migration (Phase 3 flags it; the detection rule is `_hooklib.is_migration_path` — default migration globs, extendable/narrowable via a `migration-paths` block in `security-controls.md`), dispatch the `migration-reviewer` agent (`<plugin-root>/agents/migration-reviewer.md`). **On a genuine PASS only**, record the content-bound marker `.codearbiter/.markers/migration-gate-passed` by resolving the interpreter once by presence — `PY=python3; { command -v python3 >/dev/null 2>&1 && python3 --version >/dev/null 2>&1; } || PY=python` — never `python3 X || python X`, which reruns X on any nonzero exit (#577) — and running `"$PY" "<plugin-root>/hooks/migration-pass.py"`. This is not optional: the PreToolUse commit hook **H-14 blocks the commit** until the pass is recorded AND covers every migration file being committed (by content digest, no freshness window — an edit to a reviewed migration re-blocks). This closes the bare-`/commit` / small-lane gap from issue #77. On a BLOCK, do not record the pass.
    - **CI/deploy review (mandatory routing, no marker gate):** if the staged set touches a CI/CD workflow (`_hooklib.is_ci_path` — defaults extendable via a `ci-paths` block in `security-controls.md`) or a deployment/IaC manifest (`_hooklib.is_deploy_path` — `deploy-paths` block), dispatch the `security-reviewer` agent (`<plugin-root>/agents/security-reviewer.md`). This is the enforcement point the advisory `post-write-edit` reminders **H-15/H-16** point to, and it closes the bare-`/commit` / small-lane gap for CI/deploy (the `/review`, `/pr`, `/checkpoint`, and sprint lanes already dispatch it). Unlike crypto/secret/migration there is **no commit-block marker** — a CI workflow runs only once merged and IaC bites only on apply, so a BLOCK-level finding halts the commit via Phase 6 review, but routine CI/deploy edits are not gated per-commit. Act on the findings by severity; do not record a marker.
    
    Required specialized review may reuse an existing review of the same source,
    requirements, findings and verification inputs. Dispatch only missing or affected
    review work. Required security and migration markers must still cover the actual
    staged content; a prior review does not waive their writers or hook checks.
    Record each result (PASS / BLOCK), its source and whether it was reused or run.
    
    Gate: the applicable focused tests, lint/type-check, secrets scan, and specialized gates all PASS. Any failure halts the commit until fixed and re-run. This gate does not claim that exhaustive hosted CI has run; `finishing-a-development-branch` proves that separately before merge.
    
    ## Phase 5 — Behavioral proof · gate: BLOCK
    
    Apply the current-evidence rules in `<plugin-root>/includes/fresh-verification.md`, with
    **the spec's acceptance criterion** as the target — prove the behavior against the spec, not against a
    self-report.
    
    - Identify the proving command or observable from the selected authoritative
      pair. For Markdown, use the existing criterion and task-verification text. For
      HTML, use the exact criterion and task records returned by symbol-scoped
      engine `read`; never scrape the rendered document. If none exists, derive the
      smallest command that exercises the claimed behavior.
    - Inspect the applicable output and exit code and confirm the observed behavior matches the spec's acceptance criteria. Reuse the Phase 4 or implementation result when it already proves that criterion on unchanged relevant inputs. Run a separate proving command only when existing evidence is missing, affected or insufficient. A mismatch or unverifiable claim blocks.
    
    **Stakes:** a behavioral-proof mismatch means the change does not do what the spec claims — state what would ship broken if this passed ("the retry path never fires; a transient error would hang the caller"), not just "proof mismatch." That gap is exactly what a green-looking suite hides.
    
    Gate: inspected current command output and exit code prove the claimed behavior. The phase change alone does not require another run. A self-reported "it works" does not pass.
    
    ## Phase 5.5 — Provenance auto-heal (conditional)
    
    An HTML-knowledge repository has no provenance records, so this phase does
    nothing there. Knowledge freshness is advisory: when staged paths are ones that
    knowledge records govern, `knowledge.py stale` lists those records for the next
    context refresh. It never blocks the commit and is never auto-rewritten here.
    
    Partition the loaded records by schema. Select only recorded content paths or
    membership scopes/predicates intersecting staged sources. Commits touching no
    recorded source do no re-scout work. An empty legacy worklist says nothing about v2.
    Include deleted paths and both sides of renames in `staged_paths`, for example
    with `git diff --cached --name-only --no-renames`.
    
    **Managed v2 pairs:** acquire one bounded snapshot covering the selected documents'
    recorded dependencies and target preimages. Call `assess_context_provenance` for
    those document IDs with its action-boundary snapshot probe, then reuse that
    snapshot and assessment in
    `_provenancelib.v2_heal_worklist(staged_paths, provenance, snapshot, assessment)`.
    Its `claims` identify the affected document, field, claim and staged source paths;
    they select inspection work, not permission to write. These paths are staged triggers;
    inspect the selected claims' complete recorded evidence before refreshing their fields,
    including any changed unstaged dependency. Preserve uninspected claims and bindings.
    Report `unknown` entries and defer that document's automatic
    update; do not label it fresh or block independent commit work.
    
    When inspected claims still hold, prepare an `update` of the selected owned fields
    with unchanged content and current source evidence. When a claim changed, propose
    the bounded content correction for Phase 6 review. Use the typed `context-preview`
    and `context-apply` procedure in
    `<plugin-root>/routines/context-check/SKILL.md`, retaining exact expected pair hashes,
    the returned preview reference/digest and all unselected bytes. Reuse the existing
    maintenance authorization; do not enter a second approval cycle. Native apply
    rechecks the source and pair identities and writes both files together. Read back
    the result. Never pass v2 records to `rebaseline` or write them directly. Stage the
    resulting pair by explicit paths and secrets-scan every newly staged file.
    
    **Legacy v1 records:** compute the heal worklist via
    `_provenancelib.heal_worklist(staged_paths, provenance, current_hashes)` — staged
    `drift_trigger:true` entries whose hash diverged or is absent. An empty v1 worklist
    skips only this legacy branch.
    
    Non-empty worklist → call `_provenancelib.compute_drift(provenance, current_hashes)` to retain the document/source mapping. For each stale document in that drift report, get its record as `doc_provenance` and call `_provenancelib.changed_scope(doc_provenance, drift)`. Intersect that document's drifted paths with the worklist; skip a document when the intersection is empty. The hash map can omit unstaged paths, so a missing entry outside the worklist must not broaden this commit's re-scout. Confirm that every selected worklist path maps to at least one stale document after this filtering; if a record is malformed or the mapping is incomplete, STOP and report the gap rather than treating the path as fresh.
    
    Run an **incremental re-scout for each affected document**, scoped to its selected staged paths only (not the full repo). A fresh first document does not discharge a stale second document's claims for the same source. Resolve each selected document/path dependency independently:
    
    - **Claim still holds → silently re-baseline only that document's provenance record.** Call `_provenancelib.rebaseline(doc_provenance, selected_current_hashes)` where `selected_current_hashes` contains current hashes only for the selected staged paths whose claims in that document were inspected and still hold. Do not re-baseline a path whose claim changed or was not inspected. Stage only `.codearbiter/.provenance/<doc>.json` by explicit path so the re-baselined record rides THIS commit (ADR-0008 ride-along pattern — nothing is surfaced to the user). After staging, re-run the secrets scan from `tech-stack.md` over the newly-staged path(s) — any file staged after Phase 4 must still pass the automated secrets scan before the commit proceeds. A missing current hash (deletion or rename) cannot be silently re-baselined; surface it in Phase 6 for review.
    - **Claim changed → route to the existing Phase 6 diff-review.** Propose only the affected doc or code-map edit required to reflect its changed claim. The user reviews that edit in the normal diff, and Phase 7 stages approved paths explicitly; do not silently rewrite or add unrelated documentation.
    
    For reviewed legacy code-map metadata in codeArbiter's source layout, use the
    shipped fixed-target helper at `<plugin-root>/hooks/resolve-context-conflict.py`.
    This claim-refresh lane reads all three fixed source manifests:
    `<project-root>/plugins/ca/.claude-plugin/plugin.json`,
    `<project-root>/plugins/ca-codex/.codex-plugin/plugin.json`, and `<project-root>/plugins/ca-pi/package.json`,
    even for a date-only refresh. Other repository layouts and arbitrary manifest
    claims are unsupported.
    
    Resolve the interpreter once by presence, then inspect:
    
    ```sh
    PY=python3; { command -v python3 >/dev/null 2>&1 && python3 --version >/dev/null 2>&1; } || PY=python
    "$PY" "<plugin-root>/hooks/resolve-context-conflict.py" --root "<project-root>" inspect-claims
    ```
    
    Pass the returned `binding` to the same helper and interpreter:
    
    ```sh
    "$PY" "<plugin-root>/hooks/resolve-context-conflict.py" --root "<project-root>" refresh-claims --expected '<binding>' --claims '<json-array>'
    ```
    
    Supply one to four reviewed records containing exactly
    `field`, `before`, and `after`. The supported existing fields are `ca_version`,
    `codex_version`, `pi_version`, and `metadata_date`. Use the inspection's exact
    current claim as `before`; a version's `after` must match its fixed source
    manifest, and the date must match `inspection_date`. Use the selected interpreter
    for both calls; never retry a failed operation under another interpreter.
    
    This operation requires resolved, tracked legacy schema-1 document/provenance
    and no native or uncertain journal ownership. It binds document, provenance,
    Git/index, source manifest bytes and date, preserves all unselected bytes, and
    does not stage, rebaseline, adopt, enroll or create a native receipt. Inspect the
    worktree diff for `.codearbiter/code-map.md`, selectively stage that explicit
    path, and re-run the normal secrets scan over the newly staged Markdown before
    Phase 6. Treat it as a heal-proposed doc/code-map edit in Phase 6 review, never as
    a silent rebaseline, and retain its explicit inclusion in Phase 7. Provenance
    rebaseline remains separately scoped by Phase 5.5. Unsupported
    claims or refused preimages stop the edit; do not substitute a direct write or
    native adoption. A codeArbiter contributor may exercise the tested and
    independently reviewed canonical helper under `core/pysrc/` with live enforcement
    intact, never a copied script, installed-cache edit or hook/trust change.
    
    ## Phase 6 — Diff review · gate: BLOCK
    
    Read the complete staged diff (`git diff --cached`). Flag as blocking:
    
    - Unexpected files — not discussed in the session.
    - Credentials, tokens, API keys, or any secret — belt-and-suspenders to Phase 4.
    - Incomplete changes — TODO markers, placeholder values, dead commented-out code, partial stubs.
    - Tests disabled or skipped that were not intentionally disabled.
    - Scope creep — changes outside the agreed feature or fix boundary.
    
    **Board-edit exemption (ADR-0008):** ADR-0008 governs three transitions riding a commit whose primary purpose is something else — a board edit inside such a commit is **expected and RETAINED** (not scope creep, MUST NOT be unstaged) only when `_taskboardlib.classify_board_diff(old, new)` returns a clean transition (done-flip `[~]`→`[x]`, start-flip `[ ]`→`[~]` with its optional minted dotted ID, or a single queued-add `[ ]`). Any other `open-tasks.md` edit riding an unrelated commit does not classify as one of those transitions and still flags as scope creep — it does not belong to that commit's agreed boundary.
    
    This does not cover a commit whose own Phase 3 classification **is** the board change — e.g. a `docs` chore whose sole content is a `/ca-standup` archival sweep (open-tasks.md removals plus the matching `done-tasks.md` append). There, the boundary was already agreed at Phase 3, so those edits are in-scope by that classification directly; `classify_board_diff` is not consulted and does not need to recognize archival as a fourth transition.
    
    **Native work co-location (ADR-0008):** use the installed `work.py list --limit 1`
    owner check before applying the board exemption. A `project_id` response selects
    native work; a dual-owner or failed read is a stop. For each staged
    `.codearbiter/work/<work_id>.html`, reject unstaged changes to that same path,
    then use installed `work.py get <work_id>` to verify the current native identity,
    state, and intended relationship to this commit. Review the exact staged diff;
    for a first native item, also review `.codearbiter/work/project.json` as the
    portable project identity and reject a staged/current mismatch on that path.
    The first work-create writes project.json and the HTML together; omitting the
    identity would leave the work unreadable in a fresh clone. Resolve the installed
    helper and Python from the loaded `ca-commit` skill or `commit.md` command
    resource using its installed
    `../../includes/helper-invocation.md`
    card; invoke with the card's current-shell syntax.
    do not grant a blanket exemption to arbitrary work HTML or a change to a
    different ID. An in-scope lifecycle change rides the work commit, including a
    new queued follow-up from harvest. A standup archive belongs to its own Phase 3
    classification, as with the legacy board archive. Do not run
    `classify_board_diff` on native work or create a Markdown mirror.
    
    **Provenance re-baseline exemption (ADR-0008):** a `.codearbiter/.provenance/<doc>.json` file written by the Phase 5.5 auto-heal re-baseline is likewise **expected and RETAINED** — it is not scope creep and MUST NOT be unstaged. A heal-proposed doc or code-map edit (the claim-changed path from Phase 5.5) appears in the diff for normal review; treat it as any other finding. This exemption waives the scope-creep flag only; the secrets check is not waived — the automated re-scan in Phase 5.5 covers the provenance file.
    
    On any blocking finding, unstage the affected files, surface the finding, and STOP. An out-of-scope change that should not be lost gets an inline `[NEEDS-TRIAGE]` marker before it is set aside.
    
    **Stakes:** name what the finding would have cost if committed — a leaked credential is live the moment it lands and must be rotated; a scope-creep file ships untested behavior the review waved through. State that consequence on a credential or scope finding, not just "out of scope."
    
    Gate: the diff is clean — zero blocking findings.
    
    ## Phase 7 — Selective stage · gate: BLOCK
    
    **First, run the follow-up harvest — before staging anything.** Run the follow-up harvest (`<plugin-root>/includes/harvest.md`) over any Phase 6 `[NEEDS-TRIAGE]` set-asides — promote discovered work through the selected owner (legacy `open-tasks.md` or native work HTML) and decisions to `open-questions.md`. Running this before the commit means raised work is staged and rides the work commit in the same payload.
    
    **Atomicity rule:** a raised task riding the work commit is a **contingent default** — if the PR/branch is abandoned, the selected owner's additions are abandoned with it (self-correcting, ADR-0008). A follow-up that **must survive** PR abandonment is filed as a **GitHub issue**, not local work.
    
    Before staging any newly harvested native work, review the exact current HTML
    bytes and, for the first item, `project.json` bytes under the Phase 6 secret,
    identity, scope, and native work checks. Verify the selected owner and current
    `work.py get <work_id>` result, and reject unexpected or mismatched files. A
    path-list check alone does not review these newly created bytes. If this review
    finds a blocker, stop before the commit; do not exempt the harvest output.
    
    Then selectively stage: if files were unstaged in Phase 6, re-stage only the clean files by explicit path: `git add path/to/file`. For the legacy owner, retain clean board transitions and harvest additions by explicitly staging `open-tasks.md`. For the native owner, stage validated `.codearbiter/work/<work_id>.html` paths returned or changed by the selected work operation, each by its exact ID. When the first native work-create also creates `.codearbiter/work/project.json`, stage that exact validated identity path in the same commit; if its staged bytes differ from current bytes, stop. Never stage the whole work directory or a journal. The lifecycle change rides the same work commit. When Phase 5.5 produced a re-baselined provenance record, include the affected `.codearbiter/.provenance/<doc>.json` file(s) by explicit path in the same selective stage so the re-baselined record rides the work commit. Re-run `git diff --cached --name-only` and confirm the staged list matches the intended set exactly — no extra files. Unstage any extra and report the discrepancy.
    
    For harvested native work, compare the newly staged HTML and first-item
    `project.json` with the reviewed current bytes, then inspect their exact
    `git diff --cached` content and rerun Phase 6 secret, identity, scope, and
    native work checks on those staged bytes. A mismatch or new finding blocks
    the commit. This check is required even when the staged path list is exact.
    
    Gate: the staged set contains exactly the intended files. MUST NOT use `git add -A`, `git add .`, or any wildcard.
    
    ## Phase 8 — Message · gate: BLOCK
    
    Compose a Conventional Commits message:
    
    - Subject: `<type>(<scope>): <imperative summary>`, MUST NOT exceed 72 characters.
    - Blank line, then a body explaining WHY — not a restatement of what changed.
    - For `feat` and `fix`, add a `CHANGELOG:` footer summarizing the user-visible impact.
    - If the commit closes an issue or references a decision, add the footer (`Closes #NN`, `Ref: ADR-NNNN`).
    - No content-free subjects — "fix bug", "update code", "changes" do not pass.
    
    Gate: subject ≤ 72 chars, a body is present, and any `feat`/`fix` carries a `CHANGELOG:` footer.
    
    ## Phase 9 — Commit · gate: BLOCK
    
    Commit with the approved message via `-m` or heredoc with proper quoting — never an interactive editor. Capture the resulting SHA.
    
    If a pre-commit hook fails: read its output in full, fix the issue, re-stage by explicit path (Phase 7 rules apply), and create a NEW commit. MUST NOT `--amend` after a hook failure.
    
    After a successful commit, recapture the status inventory, index entries and worktree SHA-256/absence for every preflight path and every newly reported path. Compare them with the content-addressed baseline: require no remaining staged or tracked changes in the selected reviewed payload, and investigate any unexpected path, byte or index mutation made during this commit. Report unrelated preexisting paths only when their recorded bytes and index state are unchanged; never stage, clear or call changed data preexisting. Native `.codearbiter/.artifacts/` files created by the selected helper are local recovery metadata: report their presence, preserve them in this worktree, and do not treat that exact path alone as source dirt. Do not ignore, stage, move, or delete the store to make the check pass. Deliver the report: SHA, branch, explicit file list, gate results (test / lint / secrets), and the message used.
    
    Gate: the selected reviewed payload lands with no unexpected remaining changes to its paths. Unrelated preexisting paths remain intact and visible; new unexplained changes block closure until classified.
    
    ## Hard rules
    
    - MUST NOT commit without explicit user authorization for the selected action; a clear scoped natural-language grant counts, while "it looks good" alone does not.
    - MUST NOT commit to `main`, `master`, or any protected branch.
    - MUST NOT run `git add -A`, `git add .`, or any wildcard staging.
    - MUST NOT commit while any test is failing, any lint error stands, or any secret is present.
    - MUST NOT turn exhaustive repository-wide or cross-platform CI into a local prerequisite when the shared `verification-boundary` assigns it to exact-head hosted CI.
    - MUST prove the behavior against the spec with inspected current evidence (Phase 5); a self-reported "it works" is insufficient.
    - MUST NOT skip, disable, or work around any automated gate.
    - MUST NOT commit a staged database migration without a recorded migration-review pass — the H-14 hook blocks it until `migration-reviewer` passes and `hooks/migration-pass.py` records the content-bound marker.
    - MUST NOT `--amend` after a pre-commit hook failure — create a new commit.
    - MUST NOT guess the test, lint, or secrets-scan command — read `tech-stack.md` (or `knowledge.py commands`) or STOP.
    - MUST NOT silently rewrite a doc's claims — a claim-change edit proposed by Phase 5.5 goes through diff review (Phase 6), never through the silent re-baseline path. The re-baseline path is strictly for claims that still hold; the Phase 5.5 re-baseline MUST ride the work commit (staged by explicit path in Phase 7).
    - MUST, **at Phase 7 before staging**, run the follow-up harvest (`<plugin-root>/includes/harvest.md`) over any Phase 6 `[NEEDS-TRIAGE]` set-aside — promote work through the selected owner and decisions to `open-questions.md` so raised tasks ride the work commit. A follow-up that must survive PR abandonment is filed as a GitHub issue, not local work.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.