@t275005746/gse 0.1.1 → 0.2.0

package/assets/templates/role-fallback-packet.md

@@ -0,0 +1,49 @@
+# Role Fallback Packet
+
+Use this packet for one role in a real-subagent run, sequential fallback, or handoff session.
+
+## Dispatch Boundary
+
+- Execution mode: real-subagent | sequential-role | handoff-session
+- Real delegation used: yes | no
+- Host/tool used:
+- Tool status: verified | documented | unknown | unavailable
+- Fallback reason:
+- Dispatch evidence:
+
+## Role
+
+- Role: Planner | Locator | Implementer | Verifier | Reviewer | Docs/Evidence | Release
+- Skill focus:
+- Objective:
+- Non-goals:
+
+## Ownership
+
+- Allowed files:
+- Forbidden files:
+- Read-only files:
+- Shared files requiring coordinator review:
+- Pre-existing dirty files:
+
+## Required Inputs
+
+1.
+2.
+3.
+
+## Expected Output
+
+- Role output evidence:
+- Files inspected:
+- Files changed:
+- Verification command/check:
+- Evidence level: result | verified-unit | verified-component | verified-api | verified-browser | verified-ci | accepted-owner | accepted-release | external-required
+- Residual risk:
+- Stop condition:
+- Claim boundary:
+
+## Completion
+
+- Status: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED
+- Coordinator integration required: yes | no

package/package.json

@@ -1,10 +1,17 @@
 {
   "name": "@t275005746/gse",
-  "version": "0.1.1",
+  "version": "0.2.0",
   "description": "Goal-Spec-Evidence Engineering workflow skill for long-running agent-assisted software projects.",
   "type": "module",
-  "license": "MIT",
-  "homepage": "https://gatehub.top/",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/275005746/gse.git"
+  },
+  "bugs": {
+    "url": "https://github.com/275005746/gse/issues"
+  },
+  "homepage": "https://gatehub.top/",
   "bin": {
     "gse": "scripts/gse.mjs"
   },
@@ -30,13 +37,14 @@
     "references",
     "scripts"
   ],
-  "scripts": {
-    "audit:npm": "node scripts/audit-npm-package-metadata.mjs --root . --json",
-    "audit:npm-install": "node scripts/audit-npm-tarball-install.mjs --root . --json",
-    "audit:npm-publish": "node scripts/audit-npm-publish-dry-run.mjs --root . --json",
-    "validate": "node scripts/validate-gse.mjs --root . --json",
-    "pack:dry-run": "npm pack --dry-run --json"
-  },
+  "scripts": {
+    "audit:npm": "node scripts/audit-npm-package-metadata.mjs --root . --json",
+    "audit:npm-install": "node scripts/audit-npm-tarball-install.mjs --root . --json",
+    "audit:npm-publish": "node scripts/audit-npm-publish-dry-run.mjs --root . --json",
+    "check:encoding": "node scripts/check-encoding.mjs",
+    "validate": "node scripts/validate-gse.mjs --root . --json",
+    "pack:dry-run": "npm pack --dry-run --json"
+  },
   "keywords": [
     "gse",
     "goal-spec-evidence",

package/references/agent-roles.md

@@ -2,11 +2,17 @@
 
 Use roles to make multi-agent work predictable.
 
-## Coordinator
-
-Owns scope, task level, context selection, final integration, and final answer.
-
-Never delegates final judgment.
+## Coordinator
+
+Owns scope, task level, context selection, final integration, and final answer.
+
+Never delegates final judgment.
+
+## Planner
+
+Defines the slice outcome, scope, acceptance, evidence, residual risk, and next action.
+
+Maps to Coordinator or Product Analyst in smaller tasks.
 
 ## Product Analyst
 
@@ -16,13 +22,23 @@ Clarifies user outcome, pain, audience, competitive baseline, and priority.
 
 Defines state, data flow, module boundaries, contracts, risks, and rollback.
 
-## Code Locator
-
-Read-only. Finds files, symbols, call chains, existing tests, and local patterns.
-
-## Builder
-
-Implements a bounded slice. Avoids unrelated refactors.
+## Code Locator
+
+Read-only. Finds files, symbols, call chains, existing tests, and local patterns.
+
+Also called Locator in portable role fallback packets.
+
+## Builder
+
+Implements a bounded slice. Avoids unrelated refactors.
+
+Also called Implementer in portable role fallback packets.
+
+## Verifier
+
+Runs focused checks and records what evidence level the check proves.
+
+Maps to QA in smaller tasks.
 
 ## Reviewer
 
@@ -32,18 +48,23 @@ Checks correctness, regressions, architecture drift, security, and missing tests
 
 Runs focused verification, browser smoke, API smoke, or screenshot checks.
 
-## Docs/Evidence
-
-Writes evidence, changelog notes, ADR links, and learning entries. Does not modify implementation unless explicitly assigned.
+## Docs/Evidence
+
+Writes evidence, changelog notes, ADR links, and learning entries. Does not modify implementation unless explicitly assigned.
+
+## Release
+
+Checks release, CI, package, public, owner, marketplace, registry, and host-runtime claim boundaries. Does not turn local evidence into external acceptance.
 
 ## Dispatch Rules
 
-- Use real subagent tools only when exposed by the current host.
-- Give each agent a role, files allowed, expected output, and forbidden actions. Use `assets/templates/dispatch-packet.md` when the assignment needs durable boundaries or evidence.
-- Avoid parallel writes to the same files.
-- If subagents are unavailable, execute roles sequentially in the main session and say so.
+- Use real subagent tools only when exposed by the current host.
+- Give each agent a role, files allowed, expected output, and forbidden actions. Use `assets/templates/dispatch-packet.md` when the assignment needs durable boundaries or evidence.
+- For portable fallback packets, use `references/role-dispatch-fallback.md` and `assets/templates/role-fallback-packet.md`.
+- Avoid parallel writes to the same files.
+- If subagents are unavailable, execute roles sequentially in the main session and say so.
 
 ## File Ownership
 
-Use `references/file-ownership.md` before assigning write access, running parallel implementation, or editing in a dirty worktree. Keep locator, reviewer, and QA roles read-only unless explicitly assigned otherwise.
+Use `references/file-ownership.md` before assigning write access, running parallel implementation, or editing in a dirty worktree. Keep locator, verifier, reviewer, release, and QA roles read-only unless explicitly assigned otherwise.
 

package/references/commands.md

@@ -19,9 +19,10 @@ node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gs
 node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gse probe --public-repo-url __PUBLIC_REPO_URL__" --json
 node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gse package" --json
 node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gse install --source __PACKAGE_DIR__ --install-target __INSTALL_SKILL_DIR__" --json
-node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gse public-release" --json
-node <gse-skill>/scripts/run-gse-command.mjs --target <project-root> --command "/gse learn --summary __LESSON__" --execute --json
-```
+node <gse-skill>/scripts/run-gse-command.mjs --target <gse-skill> --command "/gse public-release" --json
+node <gse-skill>/scripts/run-gse-command.mjs --target <project-root> --command "/gse learn --summary __LESSON__" --execute --json
+node <gse-skill>/scripts/run-gse-command.mjs --target <project-root> --command "/gse repair" --json
+```
 
 Validation profile helper:
 
@@ -44,22 +45,24 @@ The Claude adapter writes `.claude/commands/gse.md`, matching Claude Code's docu
 | `/gse help` | Show available GSE commands and the current project entry files | Command help | `SKILL.md`, `references/commands.md` | none or file inspection |
 | `/gse init` | Initialize `.gse/` in a new project | Project bootstrap | project rules, `project-bootstrap.md` | scaffold file check |
 | `/gse adopt` | Adopt GSE in an existing project without overwriting local rules | Project adoption | project rules, `adoption-recipes.md`, `project-profile.md` | discovery or adoption smoke |
-| `/gse continue` | Continue the current project from its goal map or canonical plan | Execute workflow | project rules, `.gse/project-profile.md`, goal map or canonical plan | focused test/smoke for the slice |
-| `/gse status` | Show current project state; for the GSE skill, show final-form progress and remaining public/host blockers | Status workflow | `.gse/state.json`; for GSE skill, final readiness audits | state/report inspection |
-| `/gse doctor` | Diagnose public/host acceptance blockers for the GSE skill, or target-project GSE readiness for normal projects | Final acceptance or project doctor | final readiness matrix, `.gse/state.json`, project profile | public acceptance doctor or target project doctor |
-| `/gse acceptance` | Alias for `/gse doctor` when the user wants final acceptance boundaries | Final acceptance doctor | final readiness matrix and owner/external evidence records | public acceptance doctor |
+| `/gse continue` | Continue the current project through a hard preflight and compact state packet | Execute workflow | project rules, `.gse/state.json`, evidence index, `.gse/project-profile.md`, quality gates, goal map or canonical plan | continue preflight plus focused test/smoke for the slice |
+| `/gse status` | Show current project state; for the GSE skill, show final-form progress and pending public/host claim evidence | Status workflow | `.gse/state.json`; for GSE skill, final readiness audits | state/report inspection |
+| `/gse doctor` | Diagnose public/host claim evidence for the GSE skill, or target-project GSE readiness for normal projects | Final acceptance or project doctor | final readiness matrix, `.gse/state.json`, project profile | public acceptance doctor or target project doctor |
+| `/gse repair` | Diagnose or repair stale state, broken evidence JSONL, and overlong residual risks | State/evidence repair workflow | `.gse/state.json`, `.gse/evidence/index.jsonl`, latest evidence files | state repair audit; optional execute-gated residual risk compaction |
+| `/gse acceptance` | Alias for `/gse doctor` when the user wants final acceptance boundaries | Final acceptance doctor | final readiness matrix and owner/external evidence records | public acceptance doctor |
 | `/gse owner-actions` | Show the remaining owner/external actions required before the GSE skill can claim public acceptance | Owner/external action packet | final readiness matrix and public acceptance doctor | owner action command smoke |
 | `/gse probe` | Probe supplied owner/external evidence locations before accepted records are written | Public external gate probe | public repo/security/CI/registry/marketplace/host evidence inputs | public external gate probe audit |
 | `/gse release` | Dry-run or generate the GSE release bundle for open-source/package handoff | Release bundle workflow | release metadata, package snapshot, acceptance handoff, owner/external kit | release bundle audit |
 | `/gse package` | Dry-run or generate a local installable GSE package | Package workflow | package label and output directory | package manifest or distribution audit |
-| `/gse install` | Dry-run or install GSE from a local package path or URL-shaped package source | Install workflow | package source and install target | install dry-run or installed CLI smoke |
-| `/gse public-release` | Dry-run or generate the ordered public release checklist for owner execution | Public release checklist workflow | release status manifest and pending owner/external gates | public release checklist audit |
-| `/gse change` | Create or normalize a GSE change spec pack | Spec workflow | change id, task level, goal map | change folder structure check |
+| `/gse install` | Dry-run or install GSE from a local package path or URL-shaped package source | Install workflow | package source and install target | install dry-run or installed CLI smoke |
+| `/gse public-release` | Dry-run or generate the ordered public release checklist for owner execution | Public release checklist workflow | release status manifest and pending owner/external gates | public release checklist audit |
+| `/gse maintenance` | Audit recurring maintenance coverage for benchmark, drift, security, forward-test, target drills, public acceptance, and installed sync | Maintenance workflow | `maintenance-cadence.md`, validation profile, current final-form state | maintenance cadence audit |
+| `/gse change` | Create or normalize a GSE change spec pack | Spec workflow | change id, task level, goal map | change folder structure check |
 | `/gse slice` | Define or normalize outcome, scope, acceptance, evidence, risk, and next action | Spec workflow | `goal-map.md`, `spec-workflow.md`, `quality-gates.md` | structural check |
 | `/gse verify` | Run the smallest verification that proves the current slice | Verification gate | `quality-gates.md`, project profile, evidence taxonomy | focused test/API/browser smoke |
-| `/gse learn` | Record a reusable lesson in `.gse/learnings.md` | Learning workflow | summary, trigger, source, optional impact | learning command audit |
+| `/gse learn` | Record a reusable lesson in `.gse/learnings.md`; with `--promote`, classify repeated lessons into promotion candidates | Learning workflow | summary, trigger, source, optional impact, optional `--promote` | learning command and promotion audits |
 | `/gse audit` | Check workflow drift, stale claims, missing evidence, or too-heavy process | Audit workflow | `benchmark-audit.md`, `drift-audit.md`, project profile | audit script or checklist |
-| `/gse close` | Check whether the current slice is ready to close | Close readiness check | `.gse/state.json`, evidence index, quality gates | close gate audit |
+| `/gse close` | Check whether the current slice is ready to close | Close readiness check | `.gse/state.json`, evidence index, quality gates, role fallback packets, git status | close gate audit |
 
 ## Aliases
 
@@ -68,17 +71,19 @@ The Claude adapter writes `.claude/commands/gse.md`, matching Claude Code's docu
 - `gse adopt` -> `/gse adopt`
 - `gse continue` -> `/gse continue`
 - `gse next` -> `/gse continue`
-- `gse status` -> `/gse status`
-- `gse doctor` -> `/gse doctor`
-- `gse acceptance` -> `/gse acceptance`
+- `gse status` -> `/gse status`
+- `gse doctor` -> `/gse doctor`
+- `gse repair` -> `/gse repair`
+- `gse acceptance` -> `/gse acceptance`
 - `gse owner-actions` -> `/gse owner-actions`
 - `gse owner` -> `/gse owner-actions`
 - `gse probe` -> `/gse probe`
 - `gse release` -> `/gse release`
 - `gse package` -> `/gse package`
-- `gse install` -> `/gse install`
-- `gse public-release` -> `/gse public-release`
-- `gse change` -> `/gse change`
+- `gse install` -> `/gse install`
+- `gse public-release` -> `/gse public-release`
+- `gse maintenance` -> `/gse maintenance`
+- `gse change` -> `/gse change`
 - `gse spec` -> `/gse change`
 - `gse slice` -> `/gse slice`
 - `gse verify` -> `/gse verify`
@@ -92,19 +97,29 @@ The Claude adapter writes `.claude/commands/gse.md`, matching Claude Code's docu
 /gse continue AION
 ```
 
-Expected behavior:
-
-1. Enter the project root.
-2. Read project rules, `.gse/state.json`, and `.gse/project-profile.md`.
-3. Read the project's canonical plan when one is declared.
-4. Pick the next verifiable slice from the machine-readable state plus goal map.
-5. Execute, verify, record evidence, update `.gse/state.json` and `.gse/evidence/index.jsonl`, and close only when accepted by the applicable gate.
-
-Portable helper:
-
-```text
-node <gse-skill>/scripts/generate-session-prompt.mjs --target <project-root>
-```
+Expected behavior:
+
+1. Enter the project root.
+2. Run the hard preflight: `.gse/state.json`, `.gse/evidence/index.jsonl`, `.gse/project-profile.md`, `.gse/goal-map.md`, `.gse/quality-gates.md`, canonical plan, current slice, residual risks, and owner/external gates when the target exposes them.
+3. Return a compact state packet with project identity, phase, current slice, next action, top risks, blocked gates, gate taxonomy, tool statuses, latest evidence, active project guards, next checks, and `completionPlan`.
+4. Fail before implementation when local state or evidence index is broken.
+5. Keep owner/external evidence visible as public/release/host-specific claim requirements without converting it into GSE core workflow debt.
+6. Use `completionPlan.requiredSteps`, `completionPlan.requiredCloseCommands`, and active `completionPlan.conditionalCloseCommands` as the exact close checklist before claiming a slice is done.
+7. Use `gateTaxonomy` to distinguish default core blockers from release gates and host-adapter claim gates. Release and host-adapter gates block only the specific claim unless project policy promotes them.
+8. For a deliberate product support slice, set `currentSlice.supportSliceBoundary` to a narrow scope or exit criterion; `/gse continue` surfaces it and keeps `CP23` as a soft outcome-steering check.
+9. Execute, verify, record evidence, update `.gse/state.json` and `.gse/evidence/index.jsonl`, and close only when accepted by the applicable gate.
+
+Portable helper:
+
+```text
+node <gse-skill>/scripts/generate-continue-packet.mjs --target <project-root>
+```
+
+Project guard helper:
+
+```text
+node <gse-skill>/scripts/audit-project-guards.mjs --target <project-root> --json
+```
 
 For existing projects that have `.gse/` but do not yet have machine-readable continuation files:
 
@@ -163,7 +178,8 @@ Expected behavior:
 3. Do not fix unrelated project code unless explicitly asked.
 
 ```text
-/gse learn --summary "Prefer UTF-8 safe readers for Chinese docs before judging mojibake" --trigger "encoding review" --source "project slice"
+/gse learn --summary "Prefer UTF-8 safe readers for Chinese docs before judging mojibake" --trigger "encoding review" --source "project slice"
+/gse learn --promote
 ```
 
 Expected behavior:
@@ -172,7 +188,8 @@ Expected behavior:
 2. Require `--summary`; accept optional `--trigger`, `--source`, `--impact`, and `--promotion`.
 3. Append the entry only when `--execute` is supplied.
 4. Skip duplicate summaries instead of appending repeated lessons.
-5. Keep raw chain-of-thought, long logs, and temporary attempts out of learnings.
+5. Keep raw chain-of-thought, long logs, and temporary attempts out of learnings.
+6. With `--promote`, run learning promotion analysis. Add `--execute` only to write candidate-only `.gse/learning-promotions.md`; do not mutate guards, gates, templates, scripts, or skill files automatically.
 
 ```text
 /gse status
@@ -181,22 +198,34 @@ Expected behavior:
 Expected behavior:
 
 1. For normal projects, read `.gse/state.json` and show phase, current slice, next action, and declared project files.
-2. For the GSE skill package itself, run the final-form progress report in dry-run mode and show local engineering readiness, full final-form readiness, pending owner/external gates, and `publicAccepted`.
+2. For the GSE skill package itself, run the final-form progress report in dry-run mode and show local engineering readiness, full final-form readiness, pending owner/external release evidence, and `publicAccepted`.
 3. Do not treat status output as completion evidence unless the relevant gate audit is also recorded.
 
-```text
-/gse doctor
-```
+```text
+/gse doctor
+```
 
 Expected behavior:
 
-1. For the GSE skill package, run the public acceptance doctor and list remaining owner/external blockers with concrete record commands.
+1. For the GSE skill package, run the public acceptance doctor and list pending owner/external claim evidence with concrete record commands.
 2. For normal target projects, run the target project doctor and report `.gse/` readiness, canonical plan visibility, evidence state, and host adapter drift.
-3. Keep owner-required and external-required gates explicit. Do not convert local mechanics into public acceptance.
-
-```text
-/gse owner-actions
-```
+3. Keep owner-required and external-required gates explicit. Do not convert local mechanics into public acceptance.
+
+```text
+/gse repair
+```
+
+Expected behavior:
+
+1. Read `.gse/state.json` and `.gse/evidence/index.jsonl`.
+2. Return concrete repair actions for invalid state JSON, invalid evidence JSONL, missing latest evidence files, stale state/evidence next actions, and overlong residual risks.
+3. Stay read-only by default.
+4. Automatic writes are limited to reversible residual-risk compaction with a backup, and require `--execute`.
+5. Do not guess or overwrite broken JSON/JSONL; report the file and line/error so the owner or agent can repair deliberately.
+
+```text
+/gse owner-actions
+```
 
 Expected behavior:
 
@@ -278,7 +307,7 @@ Expected behavior:
 ## Completion Rules
 
 - `/gse continue`, `/gse verify`, and `/gse close` must preserve the result -> verified -> accepted distinction.
-- `/gse close` is read-only in the portable command runner. It cannot mark a slice complete, archive a change, or write evidence by itself.
+- `/gse close` is read-only in the portable command runner. It checks state, evidence, role dispatch honesty, worktree ownership, staged generated artifacts, and `.gse` git state. It cannot mark a slice complete, archive a change, or write evidence by itself.
 - Portable close check:
 
 ```text
@@ -291,5 +320,6 @@ node <gse-skill>/scripts/audit-close-gate.mjs --target <project-root>
 node <gse-skill>/scripts/close-change.mjs --target <project-root> --change-id <change-id> --status result|verified|accepted --json
 ```
 
-- `/gse audit` cannot certify arbitrary repositories unless project-specific checks ran.
+- `/gse maintenance` verifies recurring upkeep coverage and command wiring; it does not replace real external host, CI, marketplace, or owner evidence.
+- `/gse audit` cannot certify arbitrary repositories unless project-specific checks ran.
 - `/gse init` and `/gse adopt` cannot overwrite existing project workflow files without explicit owner approval or `--force` with a recorded reason.

package/references/drift-audit.md

@@ -67,7 +67,8 @@ Choose the smallest durable remediation:
 - Refresh host adapter notes when host-specific folders duplicate policy or claim unavailable capabilities.
 - Refresh tool/model routing notes when provider, model, MCP, LSP, browser, CI, or deployment assumptions changed.
 - Add a learning entry only when the drift pattern is reusable beyond the current slice.
-- Add or update a script/template/gate when the same drift appears repeatedly.
+- Add or update a script/template/gate when the same drift appears repeatedly.
+- Run `scripts/audit-learning-drift.mjs --root <gse-skill> --target <project-root> --json` when `.gse/learning-promotions.md` or `/gse continue` shows promoted learning candidates. The audit surfaces candidates that are documented but not yet covered by a guard, quality gate, continue/close check, or focused script.
 
 Never update stale docs by inventing support. Prefer `unknown` plus a focused verification action.
 

package/references/evidence-taxonomy.md

@@ -2,13 +2,48 @@
 
 Use this to decide whether work is only produced, actually verified, or accepted.
 
-GSE uses three evidence gates:
+GSE uses three evidence gates:
 
 ```text
 result -> verified -> accepted
 ```
 
-Do not skip gates. Do not claim a higher gate when the evidence only proves a lower gate.
+Do not skip gates. Do not claim a higher gate when the evidence only proves a lower gate.
+
+## Evidence Status vs Evidence Level
+
+Evidence status answers whether the work is result, verified, or accepted.
+
+Evidence level answers what kind of proof produced that status.
+
+Keep both dimensions visible for non-trivial work:
+
+```text
+status: result | verified | accepted | blocked | not ready
+evidenceLevel: result | verified-unit | verified-component | verified-api | verified-browser | verified-ci | accepted-owner | accepted-release | external-required
+requiredEvidenceLevel: optional expected level for the claim
+```
+
+Use the narrowest honest level:
+
+| Evidence level | Meaning | Typical proof |
+|---|---|---|
+| `result` | Artifact exists or command produced an output, but behavior is not verified. | file exists, generated report, dry-run output |
+| `verified-unit` | Unit or script-level behavior is verified. | focused unit test, parser test, structure audit |
+| `verified-component` | Component-level or local integration behavior is verified without a real browser/runtime path. | component test, fixture integration, store/API mock |
+| `verified-api` | API/state contract is verified through an API, route, database, or state-machine check. | API smoke, state contract test, persistence fixture |
+| `verified-browser` | User-visible browser behavior is verified in a real browser automation or equivalent rendered UI smoke. | Playwright/browser smoke, screenshot-backed UI check |
+| `verified-ci` | CI or release pipeline executed and passed in the target environment. | public CI run, release workflow run, build pipeline evidence |
+| `accepted-owner` | Owner/reviewer accepts a verified result. | explicit owner acceptance, review approval, accepted project record |
+| `accepted-release` | Release/publication gate accepts the verified result. | release record, package publication record, marketplace approval |
+| `external-required` | Required evidence depends on an external owner, host, marketplace, registry, or runtime not available in the current local run. | native slash-command host proof, marketplace approval, public release gate |
+
+Examples:
+
+- A UI component test can be `status: verified` with `evidenceLevel: verified-component`, but it must not be described as browser proof.
+- A Playwright smoke can be `status: verified` with `evidenceLevel: verified-browser`.
+- A public CI record can be `status: verified` or `accepted` with `evidenceLevel: verified-ci`, depending on the project acceptance policy.
+- A pending native slash-command claim should stay `evidenceLevel: external-required` until a real host invocation record exists.
 
 ## Gate 1: Result
 
@@ -78,18 +113,20 @@ Example:
 
 ## Required Evidence Record
 
-Every non-trivial GSE slice should record:
+Every non-trivial GSE slice should record:
 
 ```text
 Outcome:
 Scope:
 Acceptance:
-Result evidence:
-Verification evidence:
-Accepted by:
-Residual risk:
-Next action:
-```
+Result evidence:
+Verification evidence:
+Evidence level:
+Required evidence level:
+Accepted by:
+Residual risk:
+Next action:
+```
 
 Use `accepted by: policy` only when the applicable policy is named, such as `Lite focused smoke policy`.
 

package/references/file-ownership.md

@@ -53,8 +53,9 @@ Claims should be short and local to the task. Do not create permanent process ar
 
 When real subagent tools exist:
 
-- Give each subagent a role, objective, allowed files, forbidden files, and expected output.
-- Prefer read-only locator/reviewer/QA roles for broad exploration.
+- Give each subagent a role, objective, allowed files, forbidden files, and expected output.
+- Prefer read-only locator/reviewer/QA roles for broad exploration.
+- Keep release roles focused on release/public/owner/external claim boundaries unless they are explicitly assigned release-file edits.
 - Do not dispatch parallel builders to the same files or tightly coupled modules.
 - Require implementers to report files changed and verification run.
 - Run spec review before code-quality review when both exist.
@@ -62,10 +63,11 @@ When real subagent tools exist:
 
 When no real subagent tool exists:
 
-- Execute roles sequentially in the main session.
-- Say that no real subagent dispatch occurred if the distinction matters.
-- Keep the same ownership boundaries: locator is read-only, builder writes assigned files, reviewer is read-only, QA writes evidence only.
-- Do not fake parallelism, independent review, or subagent status.
+- Execute roles sequentially in the main session.
+- Say that no real subagent dispatch occurred if the distinction matters.
+- Keep the same ownership boundaries: locator is read-only, builder writes assigned files, reviewer is read-only, QA writes evidence only.
+- Verifier records commands and evidence level; release records claim boundaries and external gates.
+- Do not fake parallelism, independent review, or subagent status.
 
 ## Shared File Rules
 
@@ -91,13 +93,15 @@ If two tasks need the same file:
 
 ## Verification Checklist
 
-Before claiming completion:
-
-- Intended files are the only files changed, or every extra file is explained.
-- Pre-existing dirty files were not reverted or overwritten.
-- Generated/test/output artifacts are excluded unless the project requires them.
-- Subagent work, if any, has role, allowed files, and verification evidence.
-- The evidence record names focused validation and residual risk.
+Before claiming completion:
+
+- Intended files are the only files changed, or every extra file is explained.
+- Pre-existing dirty files were not reverted or overwritten.
+- Generated/test/output artifacts are excluded unless the project requires them.
+- Subagent work, if any, has role, allowed files, and verification evidence.
+- The evidence record names focused validation and residual risk.
+
+`scripts/audit-close-gate.mjs` reports staged, unstaged, untracked, mixed, conflict, and common generated/test artifact paths so close reviews do not have to infer ownership from prose.
 
 ## Project Integration