cc-devflow 4.5.11 → 4.5.12

package/docs/commands/README.md

@@ -20,7 +20,7 @@ IDCA: cc-investigate -> cc-do -> cc-check -> cc-act
 
 Use maintenance skills separately when needed:
 
-- `cc-spec-init`: bootstrap or repair `devflow/specs/` and `change-meta.json`
+- `cc-spec-init`: bootstrap or repair `devflow/specs/` and ``
 - `cc-simplify`: cleanup pass before ship
 
 Use [skills.sh CLI](https://skills.sh/docs/cli) when you only want one skill:

package/docs/commands/README.zh-CN.md

@@ -20,7 +20,7 @@ IDCA: cc-investigate -> cc-do -> cc-check -> cc-act
 
 维护类动作按需单独调用：
 
-- `cc-spec-init`：初始化或修复 `devflow/specs/` 与 `change-meta.json`
+- `cc-spec-init`：初始化或修复 `devflow/specs/` 与 ``
 - `cc-simplify`：ship 前做清理和坏味道检查
 
 如果你只想安装单个 Skill，再使用 [skills.sh CLI](https://skills.sh/docs/cli)：

package/docs/examples/README.md

@@ -33,6 +33,6 @@ If you need to verify that examples still match the current skill contracts, use
 - Shows:
   - work that is truly verified
   - a case where remote / PR actions are intentionally skipped
-  - `cc-act` leaving exactly one final handoff file, with `resume-index.md` only for local-handoff
+  - `cc-act` leaving exactly one final `handoff/pr-brief.md` file for local handoff
 
 If you need symptom routing or artifact-based lookup, go back to [START-HERE.md](./START-HERE.md).

package/docs/examples/START-HERE.md

@@ -30,7 +30,7 @@ npm run verify:publish
 
 ## Fast Route
 
-### 1. Do you already have a `report-card.json` verdict?
+### 1. Do you already have a verification verdict?
 
 - If **no**, start with [the happy path example](./pdca-loop/README.md) to understand the full loop once.
 - If **yes**, continue below.
@@ -67,14 +67,13 @@ Use this when the only thing you know is the file in front of you.
 | `roadmap.json` | `cc-roadmap` editable machine truth source | [pdca-loop/roadmap.json](./pdca-loop/roadmap.json) |
 | `ROADMAP.md` | `cc-roadmap` generated human view | [pdca-loop/ROADMAP.md](./pdca-loop/ROADMAP.md) |
 | `BACKLOG.md` | deprecated `cc-roadmap` -> `cc-plan` projection | [pdca-loop/BACKLOG.md](./pdca-loop/BACKLOG.md) |
-| `tasks.md` | `cc-plan`, `cc-investigate`, or `cc-do` | [pdca-loop/tasks.md](./pdca-loop/changes/REQ-001-copy-invite-link/planning/tasks.md) |
-| `design.md` | legacy `cc-plan` fallback | [pdca-loop/design.md](./pdca-loop/changes/REQ-001-copy-invite-link/planning/design.md) or [full-design-blocked/design.md](./full-design-blocked/changes/REQ-002-bulk-invite-import/planning/design.md) |
-| `task-manifest.json` | `cc-do` | [pdca-loop/task-manifest.json](./pdca-loop/changes/REQ-001-copy-invite-link/planning/task-manifest.json) |
-| `report-card.json` | `cc-check` | [pdca-loop/report-card.json](./pdca-loop/changes/REQ-001-copy-invite-link/review/report-card.json), [full-design-blocked/report-card.json](./full-design-blocked/changes/REQ-002-bulk-invite-import/review/report-card.json), or [local-handoff/report-card.json](./local-handoff/changes/REQ-003-audit-log-export/review/report-card.json) |
+| `task.md` | `cc-plan`, `cc-investigate`, or `cc-do` | [pdca-loop/task.md](./pdca-loop/changes/REQ-001-copy-invite-link/task.md) |
+| Git diff / commit | `cc-do` or `cc-check` | current branch history and working tree |
+| current response verdict | `cc-check` | the verification summary from the latest run |
 | `pr-brief.md` | `cc-act` | [pdca-loop/pr-brief.md](./pdca-loop/changes/REQ-001-copy-invite-link/handoff/pr-brief.md) |
-| `resume-index.md` | `cc-act` with `local-handoff` | [local-handoff/resume-index.md](./local-handoff/changes/REQ-003-audit-log-export/handoff/resume-index.md) |
+| local `pr-brief.md` | `cc-act` with `local-handoff` | [local-handoff/pr-brief.md](./local-handoff/changes/REQ-003-audit-log-export/handoff/pr-brief.md) |
 
-### Read `report-card.json` Like This
+### Read The Verification Verdict Like This
 
 | Verdict | Reroute | Meaning |
 | --- | --- | --- |
@@ -83,7 +82,7 @@ Use this when the only thing you know is the file in front of you.
 | `blocked` | `cc-do` | proof or execution prerequisites are missing |
 | `blocked` | `cc-plan` | design or scope truth is broken; do not keep coding blindly |
 
-### Read `resume-index.md` Like This
+### Read Local Handoff Like This
 
 Ask only:
 
@@ -118,17 +117,17 @@ If both are true, you are usually in `cc-act` local handoff territory, not back
 
 ## Wrong Turns To Avoid
 
-- Do not jump from `tasks.md` straight to `cc-act`
-- Do not treat green tests as stronger than a `report-card.json` reroute
-- Do not treat `resume-index.md` as proof that planning failed; it may simply mean local handoff
+- Do not jump from `task.md` straight to `cc-act`
+- Do not treat green tests as stronger than a `cc-check` reroute
+- Do not treat `local-handoff` as proof that planning failed; it may simply mean remote actions are intentionally unavailable
 
 ## One-Minute Rule
 
 If you only have one minute, open these files in order:
 
 1. example `README.md`
-2. change `planning/tasks.md`
-3. `report-card.json` or the single final handoff file
+2. change `task.md`
+3. `handoff/pr-brief.md` when present; otherwise the latest Git commit and current verification response
 
 That should already tell you:
 
@@ -140,8 +139,8 @@ That should already tell you:
 
 `devflow/changes/<change>/` should stay lean.
 
-- Durable truth only: CLI-generated `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. Do not generate task `context.md`, `checkpoint.json`, or AI-written process files.
-- Machine JSON is CLI-owned: run `cc-devflow task-contract compile` / `validate`; do not handwrite `task-manifest.json` or `change-meta.json`.
+- Durable truth only: `task.md`, optional `handoff/pr-brief.md`, and incident postmortem files when a real recurring failure needs one. Do not generate process files.
+- Workflow state is Git-owned: keep `task.md` current and commit each completed stage.
 - Legacy `planning/design.md`, `planning/analysis.md`, and `cc-review-*.md` are readable fallback inputs for older examples, not new default writes.
 - Runtime scratch belongs in `devflow/workspaces/<change>/`, not beside the durable record.
 

package/docs/examples/example-bindings.json

@@ -2,17 +2,17 @@
   "updatedAt": "2026-05-13",
   "skills": {
     "cc-roadmap": "5.3.0",
-    "cc-next": "1.0.1",
-    "cc-dev": "1.0.2",
-    "cc-plan": "3.9.2",
-    "cc-investigate": "1.5.1",
-    "cc-do": "1.6.8",
-    "cc-review": "2.0.0",
-    "cc-pr-review": "1.0.0",
-    "cc-pr-land": "1.0.0",
-    "cc-check": "1.11.2",
-    "cc-act": "1.8.9",
-    "cc-spec-init": "1.1.0"
+    "cc-next": "1.1.1",
+    "cc-dev": "1.1.2",
+    "cc-plan": "3.10.1",
+    "cc-investigate": "1.6.1",
+    "cc-do": "1.7.1",
+    "cc-review": "2.1.2",
+    "cc-pr-review": "1.1.1",
+    "cc-pr-land": "1.1.0",
+    "cc-check": "1.12.1",
+    "cc-act": "1.9.1",
+    "cc-spec-init": "1.2.0"
   },
   "examples": [
     {

package/docs/examples/full-design-blocked/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@3.9.2`, `cc-do@1.6.8`, `cc-check@1.11.2`
+- Bound skills: `cc-roadmap@5.3.0`, `cc-plan@3.10.1`, `cc-do@1.7.1`, `cc-check@1.12.1`
 
 This example shows a requirement that **looked executable**, but `cc-check` correctly stopped it and sent it back to `cc-plan`.
 
@@ -13,7 +13,7 @@ The shape is intentional:
 - roadmap item is real enough to matter
 - design requires `full-design`
 - tasks were executed far enough to produce evidence
-- `report-card.json` is still `blocked`
+- the verification verdict is still `blocked`
 - reroute is `cc-plan`, not `cc-do`
 
 ## Scenario
@@ -43,10 +43,8 @@ The sample shows what happens when implementation moved before the integration d
 - `roadmap.json` (editable roadmap truth)
 - `ROADMAP.md` (generated view)
 - `BACKLOG.md` (deprecated projection)
-- `changes/REQ-002-bulk-invite-import/planning/tasks.md`
-- `changes/REQ-002-bulk-invite-import/planning/design.md` (legacy fallback sample)
-- `changes/REQ-002-bulk-invite-import/planning/task-manifest.json`
-- `changes/REQ-002-bulk-invite-import/review/report-card.json`
+- `changes/REQ-002-bulk-invite-import/task.md`
+- `changes/REQ-002-bulk-invite-import/task.md`
 
 ## Why There Is No `cc-act` Output
 

package/docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/{planning/tasks.md → task.md}

@@ -4,7 +4,7 @@
 
 - Requirement version: `REQ-002.v2`
 - Design version: `design.v2`
-- CC-Plan skill version: `3.9.2`
+- CC-Plan skill version: `3.10.1`
 - Work branch: `REQ/002-bulk-invite-import`
 - Source roadmap item: `RM-010`
 - Source roadmap version: `roadmap.v2`
@@ -43,20 +43,25 @@
 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.
+- CLI resolver: all workflow commands must run through `.claude/skills/cc-dev/scripts/resolve-cc-devflow.sh` or `.codex/skills/cc-dev/scripts/resolve-cc-devflow.sh`; if it cannot prove `query workflow-context` and `next-change-key`, stop blocked.
+- Context first: run resolved CLI `query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact` before opening deep sections.
+- Task selection: use `scripts/select-ready-tasks.sh --tasks devflow/changes/<change-key>/task.md`.
 - 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 review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
+- Completion rule: after verification and review gates pass, run `scripts/mark-task-complete.sh --tasks devflow/changes/<change-key>/task.md --task <task-id>`.
+- Runtime file ban: do not generate process files beyond this `task.md`.
 
 ```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"
+DEVFLOW=".claude/skills/cc-dev/scripts/resolve-cc-devflow.sh"
+if [[ ! -f "$DEVFLOW" && -f ".codex/skills/cc-dev/scripts/resolve-cc-devflow.sh" ]]; then
+  DEVFLOW=".codex/skills/cc-dev/scripts/resolve-cc-devflow.sh"
+fi
+bash "$DEVFLOW" require query workflow-context next-change-key
+bash "$DEVFLOW" query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compactSCRIPT_ROOT=".claude/skills/cc-do/scripts"
 if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then
   SCRIPT_ROOT=".codex/skills/cc-do/scripts"
 fi
-bash "$SCRIPT_ROOT/select-ready-tasks.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json
-bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task <task-id>
+bash "$SCRIPT_ROOT/select-ready-tasks.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/
+bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task <task-id>
 ```
 
 ## Phase 1: Rule Matrix
@@ -68,7 +73,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-b
   Read first: `design.md`, `src/invite/bulk-import.ts`
   Verification: `npm test -- src/invite/bulk-import.test.ts`
   Evidence: failing output
-  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T001`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task T001`; do not hand-edit status.
   Test seam: bulk invite rules and admin upload UI behavior
   Public verification path: Run the bulk invite rule and admin panel tests through their public flows
   Allowed mocks: file upload boundary / billing / seat limit boundary
@@ -81,7 +86,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-b
   Read first: `design.md`, `src/invite/bulk-import.test.ts`
   Verification: `npm test -- src/invite/bulk-import.test.ts`
   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/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T002`; 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/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task T002`; do not hand-edit status.
   Test seam: bulk invite rules and admin upload UI behavior
   Public verification path: Run the bulk invite rule and admin panel tests through their public flows
   Allowed mocks: file upload boundary / billing / seat limit boundary
@@ -96,7 +101,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-b
   Read first: `design.md`, `src/admin/BulkInvitePanel.tsx`
   Verification: `npm test -- src/admin/BulkInvitePanel.test.tsx`
   Evidence: failing output
-  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T003`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task T003`; do not hand-edit status.
   Test seam: bulk invite rules and admin upload UI behavior
   Public verification path: Run the bulk invite rule and admin panel tests through their public flows
   Allowed mocks: file upload boundary / billing / seat limit boundary
@@ -109,7 +114,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-b
   Read first: `design.md`, `src/admin/BulkInvitePanel.test.tsx`
   Verification: `npm test -- src/admin/BulkInvitePanel.test.tsx`
   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/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T004`; 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/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task T004`; do not hand-edit status.
   Test seam: bulk invite rules and admin upload UI behavior
   Public verification path: Run the bulk invite rule and admin panel tests through their public flows
   Allowed mocks: file upload boundary / billing / seat limit boundary
@@ -121,12 +126,12 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-b
   Goal: 为 `cc-check` 准备 bulk invite 的新鲜证据。
   TDD phase: evidence
   Files: `src/admin/BulkInvitePanel.tsx`, `src/invite/bulk-import.ts`
-  Read first: `tasks.md`, `task-manifest.json`
+  Read first: `task.md`
   Verification:
   - `npm test -- src/invite/bulk-import.test.ts`
   - `npm test -- src/admin/BulkInvitePanel.test.tsx`
   Evidence: passing output + review notes
-  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T005`; do not hand-edit status.
+  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$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/full-design-blocked/changes/REQ-002-bulk-invite-import/ --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/task.md --task T005`; do not hand-edit status.
   Test seam: bulk invite rules and admin upload UI behavior
   Public verification path: Run the bulk invite rule and admin panel tests through their public flows
   Allowed mocks: file upload boundary / billing / seat limit boundary

package/docs/examples/local-handoff/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@3.9.2`, `cc-do@1.6.8`, `cc-check@1.11.2`, `cc-act@1.8.9`
+- Bound skills: `cc-roadmap@5.3.0`, `cc-plan@3.10.1`, `cc-do@1.7.1`, `cc-check@1.12.1`, `cc-act@1.9.1`
 
 This example shows verified work that is **ready to move forward**, but `cc-act` still chooses `local-handoff`.
 
@@ -32,25 +32,22 @@ But the current environment is local-only:
 
 1. Why `cc-check` is `pass`
 2. Why `cc-act` still does not choose `create-pr`
-3. How `resume-index.md` becomes the only final handoff file
+3. How `handoff/pr-brief.md` becomes the only final handoff file
 
 ## Artifact Map
 
 - `roadmap.json` (editable roadmap truth)
 - `ROADMAP.md` (generated view)
 - `BACKLOG.md` (deprecated projection)
-- `changes/REQ-003-audit-log-export/planning/tasks.md`
-- `changes/REQ-003-audit-log-export/planning/design.md` (legacy fallback sample)
-- `changes/REQ-003-audit-log-export/planning/task-manifest.json`
-- `changes/REQ-003-audit-log-export/review/report-card.json`
-- `changes/REQ-003-audit-log-export/handoff/resume-index.md`
+- `changes/REQ-003-audit-log-export/task.md`
+- `changes/REQ-003-audit-log-export/handoff/pr-brief.md`
 
-## Why There Is No `pr-brief.md`
+## Why There Is A Local `pr-brief.md`
 
 This sample intentionally chooses `local-handoff`.
 
-That mode needs:
+That mode still needs one durable PR/handoff file:
 
-- `resume-index.md`
+- `handoff/pr-brief.md`
 
-It does **not** require a PR brief yet.
+It does **not** require process files.

package/docs/examples/local-handoff/changes/REQ-003-audit-log-export/handoff/pr-brief.md

@@ -0,0 +1,31 @@
+# PR Brief
+
+## Change
+
+- Change key: REQ-003-audit-log-export
+- Branch: REQ/003-audit-log-export
+
+## Task Summary
+
+- Done: audit log export handoff example
+
+## Validation
+
+- Command: example binding check
+- Result: pass
+
+## PR Body Draft
+
+```markdown
+## Summary
+
+- Demonstrates local handoff with `task.md` and this PR brief.
+
+## Validation
+
+- Example files are checked by `docs/examples/scripts/check-example-bindings.sh`.
+
+## Risk / Rollback
+
+- Documentation-only example.
+```

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

@@ -4,7 +4,7 @@
 
 - Requirement version: `REQ-003.v1`
 - Design version: `design.v1`
-- CC-Plan skill version: `3.9.2`
+- CC-Plan skill version: `3.10.1`
 - Work branch: `REQ/003-audit-log-export`
 - Source roadmap item: `RM-020`
 - Source roadmap version: `roadmap.v3`
@@ -42,20 +42,25 @@
 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.
+- CLI resolver: all workflow commands must run through `.claude/skills/cc-dev/scripts/resolve-cc-devflow.sh` or `.codex/skills/cc-dev/scripts/resolve-cc-devflow.sh`; if it cannot prove `query workflow-context` and `next-change-key`, stop blocked.
+- Context first: run resolved CLI `query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact` before opening deep sections.
+- Task selection: use `scripts/select-ready-tasks.sh --tasks devflow/changes/<change-key>/task.md`.
 - 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 review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
+- Completion rule: after verification and review gates pass, run `scripts/mark-task-complete.sh --tasks devflow/changes/<change-key>/task.md --task <task-id>`.
+- Runtime file ban: do not generate process files beyond this `task.md`.
 
 ```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"
+DEVFLOW=".claude/skills/cc-dev/scripts/resolve-cc-devflow.sh"
+if [[ ! -f "$DEVFLOW" && -f ".codex/skills/cc-dev/scripts/resolve-cc-devflow.sh" ]]; then
+  DEVFLOW=".codex/skills/cc-dev/scripts/resolve-cc-devflow.sh"
+fi
+bash "$DEVFLOW" require query workflow-context next-change-key
+bash "$DEVFLOW" query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compactSCRIPT_ROOT=".claude/skills/cc-do/scripts"
 if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then
   SCRIPT_ROOT=".codex/skills/cc-do/scripts"
 fi
-bash "$SCRIPT_ROOT/select-ready-tasks.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/task-manifest.json
-bash "$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 <task-id>
+bash "$SCRIPT_ROOT/select-ready-tasks.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/
+bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/ --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/task.md --task <task-id>
 ```
 
 ## Phase 1: Foundation
@@ -67,7 +72,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   Read first: `design.md`, `src/admin/AuditSummaryPanel.tsx`
   Verification: `npm test -- src/admin/AuditSummaryPanel.test.tsx`
   Evidence: failing output
-  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$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 "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff/changes/REQ-003-audit-log-export/ --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/task.md --task T001`; do not hand-edit status.
   Test seam: admin audit panel UI behavior
   Public verification path: Run the audit summary panel test and observe CSV export through visible rows
   Allowed mocks: download / blob boundary
@@ -80,7 +85,7 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   Read first: `design.md`, `src/admin/AuditSummaryPanel.test.tsx`
   Verification: `npm test -- src/admin/AuditSummaryPanel.test.tsx`
   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.
+  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/ --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/task.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
@@ -92,12 +97,12 @@ bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/local-handoff
   Goal: 为 `cc-check` 和 `cc-act` 留下这次导出改动的真实证据。
   TDD phase: evidence
   Files: `src/admin/AuditSummaryPanel.tsx`, `src/admin/AuditSummaryPanel.test.tsx`
-  Read first: `tasks.md`, `task-manifest.json`
+  Read first: `task.md`
   Verification:
   - `npm test -- src/admin/AuditSummaryPanel.test.tsx`
   - `npm run lint -- src/admin/AuditSummaryPanel.tsx`
   Evidence: passing output + clean lint output
-  Completion: after verification evidence and required review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$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/ --tasks docs/examples/local-handoff/changes/REQ-003-audit-log-export/task.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/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@3.9.2`, `cc-do@1.6.8`, `cc-check@1.11.2`, `cc-act@1.8.9`
+- Bound skills: `cc-roadmap@5.3.0`, `cc-plan@3.10.1`, `cc-do@1.7.1`, `cc-check@1.12.1`, `cc-act@1.9.1`
 
 This folder shows one minimal but complete `cc-roadmap -> cc-plan -> cc-do -> cc-check -> cc-act` loop.
 
@@ -13,7 +13,7 @@ The example is intentionally small:
 - product context is fake
 - requirement scope is real enough to feel concrete
 - the chosen ship mode is `create-pr`
-- optional artifacts such as `release-note.md` are intentionally omitted when the mode does not require them
+- process files are intentionally omitted
 
 ## Scenario
 
@@ -30,13 +30,10 @@ 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/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/task.md`: executable task handoff
 - `changes/REQ-001-copy-invite-link/handoff/pr-brief.md`: ship-ready PR handoff
 
-## Why There Is No `release-note.md`
+## Why There Are No Process Files
 
 This sample chooses `create-pr`.
 
@@ -45,7 +42,7 @@ That mode needs:
 - `pr-brief.md`
 - synced docs if behavior changed
 
-It does **not** need a public release note yet, so the example intentionally stops there.
+It does **not** need process files, so the example intentionally stops there.
 
 ## What To Look For
 
@@ -55,4 +52,4 @@ When reading the sample, check whether you can answer these in under a minute:
 2. Why does the requirement stay `tiny-design` instead of `full-design`?
 3. Which task proved the missing behavior first?
 4. What fresh evidence let `cc-check` say `pass`?
-5. Why does `cc-act` choose `create-pr` and omit `release-note.md`?
+5. Why does `cc-act` choose `create-pr` and omit process files?

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#Contract Summary`; `planning/tasks.md#T001-T003`
+- Review packet: `task.md#Contract Summary`; `task.md#T001-T003`
 - Finding triage: no findings
 - QA / claim evidence: `qa=pass`, `tests-pass=pass`, `requirements-met=pass`
 
@@ -41,14 +41,14 @@
 - Browser QA: `skipped`, example fixture uses targeted component evidence instead of a live browser
 - Failure ownership: no open failures recorded
 - Documentation release: README and CLAUDE unchanged for this scoped example
-- PR body accuracy: regenerate the PR body from this brief, current report-card, and current diff
+- PR body accuracy: regenerate the PR body from this brief, current validation evidence, and current diff
 
 ## Pull Request Body Contract
 
 - Language source: `Output language: en`
 - PR body language: English
 - Title rule: use English after the Conventional Commits `type(scope)` prefix; keep identifiers, paths, commands, and issue keys unchanged.
-- Body source: current `pr-brief.md`, current diff, current `review/report-card.json`, doc sync output, and roadmap/backlog writeback.
+- Body source: current `pr-brief.md`, current diff, current verification response, and roadmap/backlog writeback.
 - Required sections: summary, problem, changes, validation, review/gate evidence, risk/rollback, docs/writeback, and follow-ups.
 - Completeness gate: no empty headings, no stale inherited PR body, no generic "tests passed" without commands or evidence, and no `<placeholder>` text before `gh pr create`.
 
@@ -74,7 +74,7 @@
 
 ## Validation
 
-- `report-card.json` verdict: `pass`
+- Verification verdict: `pass`
 - `npm test -- src/features/share/ShareDialog.test.tsx`
 - `npm run lint -- src/features/share/ShareDialog.tsx`
 
@@ -82,7 +82,7 @@
 
 - Reviewed base SHA: `example-base`
 - Reviewed head SHA: `example-head`
-- Review packet: `planning/tasks.md#Contract Summary`; `planning/tasks.md#T001-T003`
+- Review packet: `task.md#Contract Summary`; `task.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.
@@ -117,7 +117,7 @@
 
 ## Verification Evidence
 
-- `report-card.json` verdict: `pass`
+- Verification verdict: `pass`
 - Merged-result verification: not applicable before merge
 - Fresh evidence:
   - `npm test -- src/features/share/ShareDialog.test.tsx`
@@ -127,17 +127,15 @@
 
 - `CLAUDE.md`: unchanged
 - `README.md`: unchanged
-- `release-note.md`: intentionally omitted for this mode
-- `resume-index.md`: not needed because the change is ready for PR handoff
+- process files: intentionally omitted
 
 ## Minimum Landing Pack
 
 - Required for this mode:
   - `pr-brief.md`
-  - fresh `report-card.json`
+  - fresh verification response
 - Intentionally omitted:
-  - `release-note.md`
-  - `resume-index.md`
+  - process files
 
 ## How To Verify