cc-devflow 4.5.9 → 4.5.10

package/docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json

@@ -6,8 +6,9 @@
   "requirementId": "REQ-003",
   "requirementVersion": "REQ-003.v1",
   "planningMeta": {
-    "reqPlanSkillVersion": "3.8.5",
+    "reqPlanSkillVersion": "3.9.0",
     "designVersion": "design.v1",
+    "workBranch": "REQ/003-audit-log-export",
     "approvedAt": "2026-04-16T13:10:00.000Z",
     "basedOnOption": "Tiny design card",
     "aiLeverageDecisionLens": {
@@ -173,7 +174,7 @@
       ],
       "evidence": [
         "passing test output",
-        "checkpoint summary"
+        "CLI log summary"
       ],
       "context": {
         "readFiles": [

package/docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md

@@ -4,7 +4,8 @@
 
 - Requirement version: `REQ-003.v1`
 - Design version: `design.v1`
-- CC-Plan skill version: `3.8.5`
+- CC-Plan skill version: `3.9.0`
+- Work branch: `REQ/003-audit-log-export`
 - Source roadmap item: `RM-020`
 - Source roadmap version: `roadmap.v3`
 
@@ -41,12 +42,14 @@
 ClaudeCode / Codex 执行本计划时，必须把本文件当成任务模板合同，而不是普通 TODO 列表。
 
 - Template source: `assets/TASKS_TEMPLATE.md`
+- Context index first: run `cc-devflow query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact` before opening deep sections; use `packetOnly` plus `mustNotForget` first, verify `sourceHashes`, open `defaultOpen` refs only when needed, and reserve `deepOpen` for matching `openWhen.conditions`.
 - Task selection: read `planning/task-manifest.json.currentTaskId`; if empty, run the ready-task selector before choosing work.
 - Task block rule: read the full task block before coding; title-only execution is invalid.
 - Completion rule: after verification and review gates pass, run the completion script; do not manually edit checkbox, status, or `currentTaskId`.
-- Completion failure: if the script fails, fix the missing checkpoint / review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
+- Completion failure: if the script fails, fix the missing review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
 
 ```bash
+cc-devflow query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact
 SCRIPT_ROOT=".claude/skills/cc-do/scripts"
 if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then
   SCRIPT_ROOT=".codex/skills/cc-do/scripts"
@@ -64,7 +67,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   Read first: `design.md`, `src/admin/AuditSummaryPanel.tsx`
   Verification: `npm test -- src/admin/AuditSummaryPanel.test.tsx`
   Evidence: failing output
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T001`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T001`; do not hand-edit status.
   Test seam: admin audit panel UI behavior
   Public verification path: Run the audit summary panel test and observe CSV export through visible rows
   Allowed mocks: download / blob boundary
@@ -76,8 +79,8 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   Files: `src/admin/AuditSummaryPanel.tsx`
   Read first: `design.md`, `src/admin/AuditSummaryPanel.test.tsx`
   Verification: `npm test -- src/admin/AuditSummaryPanel.test.tsx`
-  Evidence: passing output + checkpoint
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T002`; do not hand-edit status.
+  Evidence: passing output + Git diff
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T002`; do not hand-edit status.
   Test seam: admin audit panel UI behavior
   Public verification path: Run the audit summary panel test and observe CSV export through visible rows
   Allowed mocks: download / blob boundary
@@ -94,7 +97,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   - `npm test -- src/admin/AuditSummaryPanel.test.tsx`
   - `npm run lint -- src/admin/AuditSummaryPanel.tsx`
   Evidence: passing output + clean lint output
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T003`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/tasks.md --task T003`; do not hand-edit status.
   Test seam: admin audit panel UI behavior
   Public verification path: Run the audit summary panel test and observe CSV export through visible rows
   Allowed mocks: download / blob boundary

package/docs/examples/local-handoff/changes/REQ-003-audit-log-export/review/report-card.json

@@ -120,7 +120,7 @@
       "reviewPacket": {
         "baseSha": "example-base",
         "headSha": "example-head",
-        "requirements": "planning/design.md",
+        "requirements": "planning/tasks.md#Contract Summary",
         "implemented": "audit log export summary view",
         "reviewerContext": "requirement diff, plan completion, scope drift, docs staleness"
       },

package/docs/examples/pdca-loop/README.md

@@ -4,7 +4,7 @@
 
 - Example version: `1.0.0`
 - Last reviewed: `2026-04-17`
-- Bound skills: `cc-roadmap@5.3.0`, `cc-plan@3.8.5`, `cc-do@1.6.5`, `cc-check@1.10.1`, `cc-act@1.8.7`
+- Bound skills: `cc-roadmap@5.3.0`, `cc-plan@3.9.0`, `cc-do@1.6.7`, `cc-check@1.11.1`, `cc-act@1.8.8`
 
 This folder shows one minimal but complete `cc-roadmap -> cc-plan -> cc-do -> cc-check -> cc-act` loop.
 
@@ -30,8 +30,8 @@ The sample requirement is:
 - `roadmap.json`: editable roadmap truth that renders the generated views
 - `ROADMAP.md`: generated view of what `cc-roadmap` decided and why this item is first
 - `BACKLOG.md`: deprecated capability-aware projection that makes `RM-001` ready for `cc-plan`
-- `changes/REQ-001-copy-invite-link/planning/design.md`: approved tiny design
 - `changes/REQ-001-copy-invite-link/planning/tasks.md`: executable task handoff
+- `changes/REQ-001-copy-invite-link/planning/design.md`: legacy fallback sample for the approved tiny design
 - `changes/REQ-001-copy-invite-link/planning/task-manifest.json`: machine-readable execution truth
 - `changes/REQ-001-copy-invite-link/review/report-card.json`: `cc-check` proof and verdict
 - `changes/REQ-001-copy-invite-link/handoff/pr-brief.md`: ship-ready PR handoff

package/docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/handoff/pr-brief.md

@@ -28,7 +28,7 @@
 
 - Reviewed base SHA: `example-base`
 - Reviewed head SHA: `example-head`
-- Review packet: `planning/tasks.md#T001-T003`; `planning/design.md`
+- Review packet: `planning/tasks.md#Contract Summary`; `planning/tasks.md#T001-T003`
 - Finding triage: no findings
 - QA / claim evidence: `qa=pass`, `tests-pass=pass`, `requirements-met=pass`
 
@@ -82,7 +82,7 @@
 
 - Reviewed base SHA: `example-base`
 - Reviewed head SHA: `example-head`
-- Review packet: `planning/tasks.md#T001-T003`; `planning/design.md`
+- Review packet: `planning/tasks.md#Contract Summary`; `planning/tasks.md#T001-T003`
 - Finding triage: no findings
 - QA / claim evidence: `qa=pass`, `tests-pass=pass`, `requirements-met=pass`
 - Readiness: review freshness=`fresh`; QA coverage has no gaps; browser QA intentionally skipped for this fixture.

package/docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/design.md

@@ -4,7 +4,8 @@
 
 - Requirement version: `REQ-001.v1`
 - Design version: `design.v1`
-- CC-Plan skill version: `3.8.5`
+- CC-Plan skill version: `3.9.0`
+- Work branch: `REQ/001-copy-invite-link`
 - Requirement ID: `REQ-001`
 - Design mode: `tiny-design`
 - Why this stays `tiny-design`: the patch is limited to an existing dialog and test file, with no API or data model changes

package/docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json

@@ -6,8 +6,9 @@
   "requirementId": "REQ-001",
   "requirementVersion": "REQ-001.v1",
   "planningMeta": {
-    "reqPlanSkillVersion": "3.8.5",
+    "reqPlanSkillVersion": "3.9.0",
     "designVersion": "design.v1",
+    "workBranch": "REQ/001-copy-invite-link",
     "approvedAt": "2026-04-15T10:05:00.000Z",
     "basedOnOption": "Tiny design card",
     "aiLeverageDecisionLens": {

package/docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md

@@ -4,7 +4,8 @@
 
 - Requirement version: `REQ-001.v1`
 - Design version: `design.v1`
-- CC-Plan skill version: `3.8.5`
+- CC-Plan skill version: `3.9.0`
+- Work branch: `REQ/001-copy-invite-link`
 - Source roadmap item: `RM-001`
 - Source roadmap version: `roadmap.v1`
 
@@ -44,12 +45,14 @@
 ClaudeCode / Codex 执行本计划时，必须把本文件当成任务模板合同，而不是普通 TODO 列表。
 
 - Template source: `assets/TASKS_TEMPLATE.md`
+- Context index first: run `cc-devflow query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact` before opening deep sections; use `packetOnly` plus `mustNotForget` first, verify `sourceHashes`, open `defaultOpen` refs only when needed, and reserve `deepOpen` for matching `openWhen.conditions`.
 - Task selection: read `planning/task-manifest.json.currentTaskId`; if empty, run the ready-task selector before choosing work.
 - Task block rule: read the full task block before coding; title-only execution is invalid.
 - Completion rule: after verification and review gates pass, run the completion script; do not manually edit checkbox, status, or `currentTaskId`.
-- Completion failure: if the script fails, fix the missing checkpoint / review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
+- Completion failure: if the script fails, fix the missing review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
 
 ```bash
+cc-devflow query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact
 SCRIPT_ROOT=".claude/skills/cc-do/scripts"
 if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then
   SCRIPT_ROOT=".codex/skills/cc-do/scripts"
@@ -67,7 +70,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/cha
   Read first: `design.md`, `src/features/share/ShareDialog.tsx`
   Verification: `npm test -- src/features/share/ShareDialog.test.tsx`
   Evidence: failing output that shows the missing button / action
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T001`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T001`; do not hand-edit status.
   Test seam: share dialog UI behavior
   Public verification path: Run the share dialog test and observe the copy action through the rendered dialog
   Allowed mocks: clipboard boundary
@@ -79,8 +82,8 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/cha
   Files: `src/features/share/ShareDialog.tsx`
   Read first: `design.md`, `src/features/share/ShareDialog.test.tsx`
   Verification: `npm test -- src/features/share/ShareDialog.test.tsx`
-  Evidence: passing output + checkpoint + review notes
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T002`; do not hand-edit status.
+  Evidence: passing output + review notes
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T002`; do not hand-edit status.
   Test seam: share dialog UI behavior
   Public verification path: Run the share dialog test and observe the copy action through the rendered dialog
   Allowed mocks: clipboard boundary
@@ -97,7 +100,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/cha
   - `npm test -- src/features/share/ShareDialog.test.tsx`
   - `npm run lint -- src/features/share/ShareDialog.tsx`
   Evidence: passing test output + clean lint output
-  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T003`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json --tasks docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md --task T003`; do not hand-edit status.
   Test seam: share dialog UI behavior
   Public verification path: Run the share dialog test and observe the copy action through the rendered dialog
   Allowed mocks: clipboard boundary

package/docs/examples/pdca-loop/changes/REQ-001-copy-invite-link/review/report-card.json

@@ -120,7 +120,7 @@
       "reviewPacket": {
         "baseSha": "example-base",
         "headSha": "example-head",
-        "requirements": "planning/design.md",
+        "requirements": "planning/tasks.md#Contract Summary",
         "implemented": "copy invite link workflow",
         "reviewerContext": "requirement diff, plan completion, scope drift, docs staleness"
       },

package/docs/examples/scripts/check-example-bindings.sh

@@ -113,6 +113,8 @@ while IFS= read -r encoded; do
   ' "$planning_dir/task-manifest.json" >/dev/null
 
   assert_contains "$planning_dir/tasks.md" "## Execution Protocol"
+  assert_contains "$planning_dir/tasks.md" "cc-devflow query workflow-context"
+  assert_contains "$planning_dir/tasks.md" "--data-only --no-trace --compact"
   assert_contains "$planning_dir/tasks.md" "mark-task-complete.sh"
   assert_contains "$planning_dir/tasks.md" "TDD phase:"
   assert_contains "$planning_dir/tasks.md" "Completion:"

package/docs/get-shit-done-strategy-audit.md

@@ -68,7 +68,7 @@ lib/skill-runtime
         |
         v
 durable artifacts
-  task-manifest.json / report-card.json / change-state.json / analysis.md
+  planning/tasks.md / task-manifest.json / report-card.json / change-meta.json
 ```
 
 SKILL/PLAYBOOK 拥有 workflow 语义。`lib/skill-runtime` 只拥有 typed reads、
@@ -125,11 +125,11 @@ Codebase Map 七件套只作为按需缓存：
 
 | Contract | Artifact owner | Gate | Tests |
 | --- | --- | --- | --- |
-| WHAT/WHY ambiguity score | `task-manifest.json.planningMeta` + `planning/design.md` | score above threshold blocks task manifest approval | unit fixture: ambiguous input blocks; clear input passes |
-| Assumptions preview | `planning/design.md` decision log | user-visible assumptions before approval | fixture: hidden assumption fails review |
-| Bounded review loop | `planning/design.md` | max attempts and stall detection reroute to `cc-roadmap` or user question | hostile fixture: repeated issue count blocks |
-| External doc conflict buckets | `planning/design.md` | imported docs classified as auto-resolved, competing, unresolved | fixture: conflicting ADR/PRD creates blocker |
-| Trust boundary | `planning/design.md` | external text is evidence/source only, never instruction | hostile fixture: prompt injection remains evidence-only |
+| WHAT/WHY ambiguity score | `task-manifest.json.planningMeta` + `planning/tasks.md#Contract Summary` | score above threshold blocks task manifest approval | unit fixture: ambiguous input blocks; clear input passes |
+| Assumptions preview | `planning/tasks.md#Contract Summary` decision log | user-visible assumptions before approval | fixture: hidden assumption fails review |
+| Bounded review loop | `planning/tasks.md#Contract Summary` | max attempts and stall detection reroute to `cc-roadmap` or user question | hostile fixture: repeated issue count blocks |
+| External doc conflict buckets | `planning/tasks.md#Contract Summary` | imported docs classified as auto-resolved, competing, unresolved | fixture: conflicting ADR/PRD creates blocker |
+| Trust boundary | `planning/tasks.md#Contract Summary` | external text is evidence/source only, never instruction | hostile fixture: prompt injection remains evidence-only |
 
 `cc-plan` must keep design decisions readable in Markdown and machine truth in JSON.
 No separate GSD-style `.planning/` tree.
@@ -140,20 +140,20 @@ No separate GSD-style `.planning/` tree.
 | --- | --- | --- | --- |
 | Wave scheduling | `task-manifest.json.tasks[].phase/parallel/dependsOn/touches` | parallel only when dependencies and touches do not conflict | schema fixture: shared touches rejected |
 | Submodule-aware worktree gate | `task-manifest.json.tasks[].touches` + runtime submodule scan | only tasks touching submodule paths lose isolation | hostile fixture: repo with `.gitmodules` but unrelated touches still parallel |
-| Quick lane mini manifest | `task-manifest.json.metadata.lane=quick` | small work still has checkpoint, verification, handoff | fixture: quick lane without verification blocks |
-| Thread/pause/resume | `change-state.json` + one final handoff file | resume query returns stable next action | integration: stale checkpoint restores to pending |
+| Quick lane mini manifest | `task-manifest.json.metadata.lane=quick` | small work still has task-state truth, verification, handoff | fixture: quick lane without verification blocks |
+| Thread/pause/resume | `change-meta.json`, manifest task state, optional CLI logs, and one final handoff file | resume query returns stable next action | integration: stale manifest state restores to pending |
 
-`cc-do` should not invent new task state outside `task-manifest.json` and checkpoints.
+`cc-do` should not invent new task state outside `task-manifest.json`.
 
 ### `cc-investigate`
 
 | Contract | Artifact owner | Gate | Tests |
 | --- | --- | --- | --- |
-| Persistent debug session | `planning/analysis.md` session block, optional machine summary in `task-manifest.json` | hypotheses, probes, symptom match, cleanup recorded | fixture: missing cleanup blocks freeze |
-| Diagnose-only report | `planning/analysis.md` | no code edits required; root cause and next action explicit | fixture: diagnose-only does not mark implementation complete |
-| Workflow forensics | `planning/analysis.md` + trace refs | git/artifact/state failures classified before fixes | hostile fixture: corrupt manifest produces named failure |
+| Persistent debug session | `planning/tasks.md#Root Cause Contract`, optional machine summary in `task-manifest.json` | hypotheses, probes, symptom match, cleanup recorded | fixture: missing cleanup blocks freeze |
+| Diagnose-only report | `planning/tasks.md#Root Cause Contract` | no code edits required; root cause and next action explicit | fixture: diagnose-only does not mark implementation complete |
+| Workflow forensics | `planning/tasks.md#Root Cause Contract` + trace refs | git/artifact/state failures classified before fixes | hostile fixture: corrupt manifest produces named failure |
 
-Prefer extending `planning/analysis.md` over adding `planning/debug-session.md`.
+Prefer extending `planning/tasks.md#Root Cause Contract` over adding `planning/debug-session.md`.
 Only add a new file if the debug transcript becomes too large and has a single owner.
 
 ### `cc-check`
@@ -208,11 +208,11 @@ default planning path.
 
 | Data | Owner | Human view | Machine truth |
 | --- | --- | --- | --- |
-| Ambiguity and assumptions | `cc-plan` | `planning/design.md` | `task-manifest.json.planningMeta` |
-| Imported doc trust classification | `cc-plan` | `planning/design.md` | `planning/design.md` |
+| Ambiguity and assumptions | `cc-plan` | `planning/tasks.md#Contract Summary` | `task-manifest.json.planningMeta` |
+| Imported doc trust classification | `cc-plan` | `planning/tasks.md#Contract Summary` | `planning/tasks.md` |
 | Task graph and waves | `cc-plan` / `cc-do` | `planning/tasks.md` | `task-manifest.json.tasks[]` |
-| Quick lane state | `cc-do` | checkpoint summary | `task-manifest.json.metadata`, `checkpoint.json` |
-| Debug hypotheses and probes | `cc-investigate` | `planning/analysis.md` | optional `task-manifest.json.investigation` |
+| Quick lane state | `cc-do` | task-state summary | `task-manifest.json.metadata`, `planning/tasks.md` |
+| Debug hypotheses and probes | `cc-investigate` | `planning/tasks.md#Root Cause Contract` | optional `task-manifest.json.investigation` |
 | Verification/UAT/facets | `cc-check` | review summary | `report-card.json` |
 | Runtime failures | `cc-check` | review summary | `report-card.json.runtime.failureOwnership[]` |
 | Ship target and rollback | `cc-act` | `handoff/pr-brief.md` / `release-note.md` | structured preflight output |
@@ -243,7 +243,7 @@ owner skill, and next action.
 | --- | --- | --- | --- | --- | --- | --- |
 | external docs -> `cc-plan` | block with missing source | skip with reason | `TrustBoundaryError` | conflict bucket | mark stale source | partial import warning |
 | `tasks.md` -> `task-manifest.json` | block | block | schema error | dependency conflict | plan version mismatch | no manifest approval |
-| manifest -> wave scheduling | block | no runnable task | `InvalidTaskGraphError` | serialize or block | stale checkpoint rejected | reroute resume |
+| manifest -> wave scheduling | block | no runnable task | `InvalidTaskGraphError` | serialize or block | stale manifest state rejected | reroute resume |
 | debug session -> analysis | block freeze | require note | schema/narrative mismatch | competing hypotheses | stale symptom | diagnose-only |
 | query registry -> next action | `MissingArtifactError` | no next action with reason | named parse/schema error | blocked graph | stale state warning | degraded output |
 | inventory -> publish gate | missing inventory blocks | empty inventory blocks | schema error | drift blocks | stale hash blocks | publish blocked |
@@ -320,7 +320,7 @@ Large-file guardrails:
 
 ### Phase 3: `cc-investigate` debug session and forensics
 
-- Extend `planning/analysis.md` and optional machine summary.
+- Extend `planning/tasks.md#Root Cause Contract` and optional machine summary.
 - Required proof: diagnose-only and missing cleanup fixtures.
 
 ### Phase 4: `cc-check` and `cc-act` consumers
@@ -354,7 +354,7 @@ These rules protect cc-devflow's identity:
 | Existing cc-devflow asset | Reuse |
 | --- | --- |
 | `lib/skill-runtime/query.js` | current progress/next/full-state facade |
-| `lib/skill-runtime/schemas.js` | manifest/report/checkpoint schema boundary |
+| `lib/skill-runtime/schemas.js` | manifest/report/runtime schema boundary |
 | `lib/skill-runtime/config.js` | layered config and doctor pattern |
 | `lib/compiler/manifest.js` | hash and drift detection foundation |
 | `scripts/validate-publish.js` | publish validation orchestrator |
@@ -404,7 +404,7 @@ not the cc-devflow implementation order.
 | `ship` | structured ship preflight |
 | `next` | runtime query `route.next-action` |
 | `fast` | TDD exception / quick lane rule |
-| `quick` | mini manifest + checkpoint |
+| `quick` | mini manifest + task-state truth |
 | `ui-review` | conditional frontend `cc-check` facet |
 | `code-review` | finding schema |
 | `code-review-fix` | fix loop and return to `cc-check` |
@@ -433,7 +433,7 @@ not the cc-devflow implementation order.
 | `cleanup` | low priority cleanup |
 | `manager` | skip UI |
 | `workstreams` | active pointer only |
-| `autonomous` | smart-discuss/checkpoint guard only |
+| `autonomous` | smart-discuss/task-state guard only |
 | `undo` | rollback guard |
 
 ### Session And Navigation

package/docs/guides/artifact-contract.md

@@ -20,7 +20,7 @@ If a field has no clear opener and no downstream consumer, remove it.
 | Capability/spec sync state | `devflow/changes/<change-key>/change-meta.json` | `planning/tasks.md`, `review/report-card.json`, handoff summaries |
 | Execution task status | `planning/task-manifest.json.tasks[].status` | `planning/tasks.md` checkboxes, recovery summaries |
 | Ready task / phase | derived from `tasks[].status`, `tasks[].phase`, and `tasks[].dependsOn` | `currentTaskId` cache, ready-task selector output |
-| Runtime checkpoint state | `execution/tasks/<task-id>/checkpoint.json` | `events.jsonl`, recovery summaries |
+| Runtime event log | `execution/tasks/<task-id>/events.jsonl` only for debug/failed runs | recovery summaries |
 | Review verdict | `review/report-card.json.verdict` | PR brief, release note, act gate |
 | PR / remote queue truth | live GitHub API / `gh` output | local review notes and handoff summaries |
 | Project postmortem facts and principles | `devflow/postmortems/` | planning recall, investigation hypotheses, task guardrails |

package/docs/guides/getting-started.md

@@ -11,10 +11,10 @@ CC-DevFlow has two entry paths:
 - `cc-devflow init`: install the whole `.claude` pack into your project
 - `cc-devflow adapt`: generate platform outputs such as Codex rules
 
-The core workflow is driven by six visible skills, with `cc-review` available as an optional deep review pass:
+The core workflow can run manually through PDCA/IDCA skills or automatically through the PR harness skills:
 
 ```text
-cc-roadmap
+cc-roadmap -> cc-next -> cc-dev
 
 PDCA: cc-plan -> [cc-review] -> cc-do -> [cc-review] -> cc-check -> cc-act
 IDCA: cc-investigate -> [cc-review] -> cc-do -> [cc-review] -> cc-check -> cc-act
@@ -36,7 +36,7 @@ The public skills are the visible harness. Each distributed `SKILL.md` now carri
 npx cc-devflow init --dir /path/to/your/project
 ```
 
-The whole-pack install includes the six core workflow skills, optional `cc-review`, plus `cc-spec-init` and `cc-simplify` as maintenance helpers.
+The whole-pack install includes roadmap, next-work selection, autonomous dev, manual PDCA/IDCA, optional `cc-review`, PR review/landing, plus `cc-spec-init` and `cc-simplify` as maintenance helpers.
 
 ### Single Skill Install
 
@@ -87,9 +87,9 @@ Typical outputs:
 
 - `cc-roadmap` writes `devflow/roadmap.json` as the editable roadmap truth, then generates `devflow/ROADMAP.md` and deprecated `devflow/BACKLOG.md`
 - `cc-spec-init` writes `devflow/specs/INDEX.md`, capability specs, and `change-meta.json`
-- `cc-plan` writes `planning/design.md`, `planning/tasks.md`, `task-manifest.json`, and `change-meta.json`
-- `cc-investigate` writes `planning/analysis.md`, `planning/tasks.md`, `task-manifest.json`, and `change-meta.json`
-- `cc-review` writes `cc-review-plan.md`, `cc-review-ledger.jsonl`, `cc-review-report.md`, optional `cc-review-agent-results.jsonl`, and optional structured findings for deep plan or implementation review
+- `cc-plan` writes `planning/tasks.md#Contract Summary`, CLI-generated `task-manifest.json`, and `change-meta.json`
+- `cc-investigate` writes `planning/tasks.md#Root Cause Contract`, CLI-generated `task-manifest.json`, and `change-meta.json`
+- `cc-review` writes `review-ledger.jsonl`, optional `review-findings.json`, and Markdown reports only when rendered on demand
 - `cc-check` writes `report-card.json`
 - `cc-act` writes exactly one final handoff file: `handoff/pr-brief.md`, `handoff/resume-index.md`, or `handoff/release-note.md`
 
@@ -98,7 +98,8 @@ Change truth lives in `devflow/changes/<change>/`.
 
 - Keep `INDEX.md` plus capability markdown under `devflow/specs/`.
 - Name new change directories as `REQ-<number>-<description>` for requirements or `FIX-<number>-<description>` for bug fixes. `REQ` and `FIX` advance as separate local sequences, so cross-prefix duplicates are valid. Parallel worktrees may still repeat numbers; the full change key, especially the description, distinguishes the work. Old lowercase directories are compatibility reads only.
-- Keep `change-state.json`, `change-meta.json`, planning docs, `task-manifest.json`, optional `team-state.json`, task `checkpoint.json`, `report-card.json`, and one final handoff file under each `devflow/changes/<change>/`.
+- Keep `change-meta.json`, `planning/tasks.md`, CLI-generated `task-manifest.json`, review ledger/findings records, optional CLI logs for debug/failure, `report-card.json`, and one final handoff file under each `devflow/changes/<change>/`. Do not generate task `context.md`, `checkpoint.json`, or AI-written process files.
+- Legacy `planning/design.md`, `planning/analysis.md`, and `cc-review-*.md` are readable fallback inputs for older changes, not new default writes.
 - Worker prompts, journals, assignments, and session logs belong under `devflow/workspaces/<change>/` as ephemeral scratch.
 
 Planning handoffs should be evidence-rich before implementation starts:
@@ -154,7 +155,7 @@ npx cc-devflow adapt --cwd /path/to/your/project --platform codex
 
 If your project has no optional `.claude/commands/` input, this is expected: the compiler will still generate the skills registry and mirror the distributed skill set for Codex.
 
-Codex mirrors the distributed skills from `.claude/skills/<skill>/` into `.codex/skills/<skill>/`. That set includes the six core workflow skills, optional `cc-review`, `cc-spec-init`, and `cc-simplify`, and the mirror is additive-only: existing project-owned Codex skills are preserved instead of being deleted.
+Codex mirrors the distributed skills from `.claude/skills/<skill>/` into `.codex/skills/<skill>/`. That set includes the public workflow skills plus maintenance skills `cc-spec-init` and `cc-simplify`, and the mirror is additive-only: existing project-owned Codex skills are preserved instead of being deleted.
 
 ### Keep skills and examples in sync
 
@@ -173,6 +174,7 @@ npm run verify:publish
 - [CLI And Skills](../commands/README.md)
 - [Workflow Guide](./workflow-guide.md)
 - [Best Practices](./best-practices.md)
+- [Minimized Artifact Contract](./minimize-artifacts.md)
 - [Example Entry Page](../examples/START-HERE.md)
 - [Compact Example List](../examples/README.md)
 - [Project README](../../README.md)

package/docs/guides/getting-started.zh-CN.md

@@ -11,10 +11,10 @@ CC-DevFlow 现在有两条入口：
 - `cc-devflow init`：把整包 `.claude` 安装到你的项目里
 - `cc-devflow adapt`：生成 Codex、Cursor、Qwen、Antigravity 等平台产物
 
-核心工作流由 6 个可见 Skill 组成，复杂工作可选 `cc-review` 做深度 Review：
+核心工作流可以手动走 PDCA/IDCA Skill，也可以通过 PR harness Skill 自动推进：
 
 ```text
-cc-roadmap
+cc-roadmap -> cc-next -> cc-dev
 
 PDCA: cc-plan -> [cc-review] -> cc-do -> [cc-review] -> cc-check -> cc-act
 IDCA: cc-investigate -> [cc-review] -> cc-do -> [cc-review] -> cc-check -> cc-act
@@ -36,7 +36,7 @@ IDCA: cc-investigate -> [cc-review] -> cc-do -> [cc-review] -> cc-check -> cc-ac
 npx cc-devflow init --dir /path/to/your/project
 ```
 
-整包安装会带上 6 个核心 workflow skill、可选 `cc-review`，以及维护用的 `cc-spec-init` 和 `cc-simplify`。
+整包安装会带上 roadmap、next-work selection、autonomous dev、手动 PDCA/IDCA、可选 `cc-review`、PR review/landing，以及维护用的 `cc-spec-init` 和 `cc-simplify`。
 
 ### 单个 Skill 安装
 
@@ -87,9 +87,9 @@ find .codex/skills -mindepth 2 -maxdepth 2 -name SKILL.md | sort
 
 - `cc-roadmap` 产出可编辑真相 `devflow/roadmap.json`，再生成 `devflow/ROADMAP.md` 和 deprecated `devflow/BACKLOG.md`
 - `cc-spec-init` 产出 `devflow/specs/INDEX.md`、capability spec 和 `change-meta.json`
-- `cc-plan` 产出 `planning/design.md`、`planning/tasks.md`、`task-manifest.json` 和 `change-meta.json`
-- `cc-investigate` 产出 `planning/analysis.md`、`planning/tasks.md`、`task-manifest.json` 和 `change-meta.json`
-- `cc-review` 产出 `cc-review-plan.md`、`cc-review-ledger.jsonl`、`cc-review-report.md`、可选 `cc-review-agent-results.jsonl`，以及可选的结构化深度 Review findings
+- `cc-plan` 产出 `planning/tasks.md#Contract Summary`、CLI 生成的 `task-manifest.json` 和 `change-meta.json`
+- `cc-investigate` 产出 `planning/tasks.md#Root Cause Contract`、CLI 生成的 `task-manifest.json` 和 `change-meta.json`
+- `cc-review` 产出 `review-ledger.jsonl`、可选 `review-findings.json`，Markdown 报告只在需要时按需渲染
 - `cc-check` 产出 `report-card.json`
 - `cc-act` 只产出一个最终 handoff 文件：`handoff/pr-brief.md`、`handoff/resume-index.md` 或 `handoff/release-note.md`
 
@@ -97,7 +97,8 @@ durable truth 分两层：
 
 - `devflow/specs/`：capability 真相，保留 `INDEX.md` 与 `capabilities/*.md`
 - 新 change 目录必须命名为 `REQ-<number>-<description>`（需求）或 `FIX-<number>-<description>`（修复）；`REQ` 和 `FIX` 分别维护自己的递增编号，跨前缀同号不是冲突；并行工作树造成重复编号时，完整 change key 的描述负责区分业务内容，旧小写目录只作为历史兼容读取。
-- `devflow/changes/<change>/`：变更真相，保留 `change-state.json`、`change-meta.json`、planning 文档、`task-manifest.json`、可选 `team-state.json`、任务级 `checkpoint.json`、`report-card.json` 和唯一的最终 handoff 文件。
+- `devflow/changes/<change>/`：变更真相，保留 `change-meta.json`、`planning/tasks.md`、CLI 生成的 `task-manifest.json`、review ledger / findings 记录、debug / failed 的可选 CLI 日志、`report-card.json` 和唯一的最终 handoff 文件。不要生成任务级 `context.md`、`checkpoint.json` 或 AI 手写过程文件。
+- 历史 `planning/design.md`、`planning/analysis.md` 和 `cc-review-*.md` 是旧 change 的可读 fallback，不再是新默认写入。
 - worker prompt、journal、assignment、session log 统一放到 `devflow/workspaces/<change>/`，作为 ephemeral scratch。
 
 进入实现前，planning handoff 应该先把证据写实：
@@ -153,7 +154,7 @@ npx cc-devflow adapt --cwd /path/to/your/project --platform codex
 
 如果你的项目没有可选的 `.claude/commands/` 输入目录，这也是正常的；编译器仍然会生成 skills registry，并为 Codex 镜像正式分发 skill 集合。
 
-Codex 现在会把正式分发的 skill 从 `.claude/skills/<skill>/` 镜像到 `.codex/skills/<skill>/`。这套集合包含 6 个核心 workflow skill、可选 `cc-review` 和维护类 skill `cc-spec-init`、`cc-simplify`，并且镜像是纯增量的：项目里已有的自定义 Codex skill 不会被删除。
+Codex 现在会把正式分发的 skill 从 `.claude/skills/<skill>/` 镜像到 `.codex/skills/<skill>/`。这套集合包含公开 workflow skill 和维护类 skill `cc-spec-init`、`cc-simplify`，并且镜像是纯增量的：项目里已有的自定义 Codex skill 不会被删除。
 
 ### 保持 skill 和样例同步
 
@@ -172,6 +173,7 @@ npm run verify:publish
 - [CLI 与 Skill](../commands/README.zh-CN.md)
 - [工作流详解](./workflow-guide.md)
 - [最佳实践](./best-practices.md)
+- [最小 Artifact 合同](./minimize-artifacts.md)
 - [样例入口页](../examples/START-HERE.md)
 - [简版样例列表](../examples/README.md)
 - [项目 README](../../README.zh-CN.md)

package/docs/guides/minimize-artifacts.md

@@ -0,0 +1,123 @@
+# Minimized Workflow Artifacts
+
+This guide describes the default artifact contract for new cc-devflow changes.
+The goal is simple: keep durable workflow truth readable, small, and measurable.
+
+## Default Shape
+
+Each new change keeps durable truth under `devflow/changes/<change-key>/`.
+
+Default human-authored Markdown:
+
+- `planning/tasks.md`
+
+Default machine-owned records:
+
+- `change-meta.json`
+- `planning/task-manifest.json`
+- `review/review-ledger.jsonl`
+- `review/review-findings.json` when findings exist
+- `execution/tasks/<task-id>/checkpoint.json`
+- `review/report-card.json`
+- one final handoff file under `handoff/`
+
+Runtime scratch, worker prompts, journals, assignments, and session logs belong
+under `devflow/workspaces/<change-key>/`, not beside durable change truth.
+
+## Feature Plans
+
+Feature and scope changes use:
+
+- `planning/tasks.md#Contract Summary`
+- `planning/task-manifest.json`
+- `change-meta.json`
+
+`Contract Summary` owns the frozen human-readable plan: user story, non-negotiable
+constraints, decisions that must not be reopened, task slices, and verification
+expectations. The task manifest is generated or validated by CLI tooling and owns
+machine-readable task status.
+
+## Bug Investigations
+
+Bug, regression, and unexpected-behavior work uses:
+
+- `planning/tasks.md#Root Cause Contract`
+- `planning/task-manifest.json`
+- `change-meta.json`
+
+`Root Cause Contract` owns the symptom, reproduction evidence, confirmed cause,
+rejected near-causes, repair boundary, and task handoff. `cc-do` should implement
+from that frozen contract instead of reopening investigation during execution.
+
+## Review Records
+
+`cc-review` writes structured lifecycle events first:
+
+- `review/review-ledger.jsonl`
+- optional `review/review-findings.json`
+- optional rendered Markdown from `cc-devflow review render`
+
+Markdown review reports are for human reading when needed. They are not the
+default durable review source.
+
+Useful commands:
+
+```bash
+npx cc-devflow review start --change REQ-001 --change-key REQ-001-copy-invite-link --base-sha abc123 --head-sha def456
+npx cc-devflow review record-node --change REQ-001 --change-key REQ-001-copy-invite-link --review-id <review-id> --node-id R001 --target planning/tasks.md --status checked --coverage contract --evidence-ref "cmd:npm run verify"
+npx cc-devflow review add-finding --change REQ-001 --change-key REQ-001-copy-invite-link --review-id <review-id> --finding-id F001 --severity important --confidence 8 --display-tier blocking --fingerprint sha256:<hash> --scope "current change" --path planning/tasks.md --evidence "finding evidence" --recommendation "repair action" --route cc-do
+npx cc-devflow review close --change REQ-001 --change-key REQ-001-copy-invite-link --review-id <review-id> --status clean --blocking-count 0 --warning-count 0 --next cc-check
+npx cc-devflow review render --change REQ-001 --change-key REQ-001-copy-invite-link --review-id <review-id> --output review/review-report.md
+```
+
+## Legacy Fallback
+
+Older changes may still contain:
+
+- `planning/design.md`
+- `planning/analysis.md`
+- `review/cc-review-plan.md`
+- `review/cc-review-report.md`
+- `review/cc-review-agent-results.jsonl`
+
+Those files remain readable compatibility inputs. New changes should not write
+them by default. When migrating old work, fold feature-plan truth into
+`planning/tasks.md#Contract Summary` and bug-investigation truth into
+`planning/tasks.md#Root Cause Contract`.
+
+## Validation Gates
+
+Validate one change:
+
+```bash
+npx cc-devflow task-contract validate --change REQ-001 --change-key REQ-001-copy-invite-link
+```
+
+Validate the repository artifact contract:
+
+```bash
+npm run verify:artifacts
+```
+
+Measure the contract:
+
+```bash
+npm run benchmark:artifacts
+```
+
+The package-level verification command also includes artifact validation:
+
+```bash
+npm run verify
+```
+
+## Authoring Rule
+
+Before adding a durable file under `devflow/changes/<change-key>/`, answer:
+
+1. Which downstream skill reads it by default?
+2. Which state does it own that no existing artifact owns?
+3. Which command fails if it drifts?
+
+If those answers are unclear, keep the information in `planning/tasks.md`, a
+machine record, or ephemeral workspace scratch instead.

package/lib/compiler/__tests__/skills-registry.test.js

@@ -159,9 +159,9 @@ describe('Skills Registry Generator', () => {
       expect(execute.writes).toEqual(
         expect.arrayContaining([
           expect.objectContaining({
-            path: 'devflow/changes/<change-key>/execution/tasks/<task-id>/checkpoint.json',
+            path: 'devflow/changes/<change-key>/execution/tasks/<task-id>/events.jsonl',
             durability: 'durable',
-            required: true
+            required: false
           })
         ])
       );