cc-codeconductor 1.6.0 → 1.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (126) hide show
  1. package/README.md +22 -7
  2. package/dist/core/compilation/compile-checker.d.ts +3 -2
  3. package/dist/core/goal/goal-state.d.ts +1 -0
  4. package/dist/core/orchestrator/runtime-orchestrator.d.ts +1 -0
  5. package/dist/core/queue/lock.d.ts +3 -0
  6. package/dist/core/verification/rdd-receipt.d.ts +25 -0
  7. package/dist/core/verification/verification-runner.d.ts +27 -2
  8. package/dist/index.js +1501 -782
  9. package/dist/library.js +420 -142
  10. package/dist/validation/schemas.d.ts +65 -26
  11. package/docs/generated/cli.md +8 -0
  12. package/package.json +2 -1
  13. package/presets/agy/AGENTS.md +1 -1
  14. package/presets/agy/scripts/invoke-hook.cjs +43 -24
  15. package/presets/agy/skills/backlog/SKILL.md +1 -1
  16. package/presets/agy/skills/cc-feature/SKILL.md +17 -16
  17. package/presets/agy/skills/cc-fix/SKILL.md +28 -34
  18. package/presets/agy/skills/cc-spec-mutation/SKILL.md +1 -1
  19. package/presets/agy/skills/cc-tdd-cycle/SKILL.md +1 -1
  20. package/presets/agy/skills/evaluation/SKILL.md +1 -1
  21. package/presets/agy/skills/openspec/SKILL.md +10 -6
  22. package/presets/agy/skills/testing-tdd/SKILL.md +3 -3
  23. package/presets/agy/workflows/cc-api-contract.md +1 -1
  24. package/presets/agy/workflows/cc-ask.md +2 -2
  25. package/presets/agy/workflows/cc-council.md +2 -0
  26. package/presets/agy/workflows/cc-db-migration.md +1 -1
  27. package/presets/agy/workflows/cc-feature.md +1 -1
  28. package/presets/agy/workflows/cc-fix.md +1 -1
  29. package/presets/agy/workflows/cc-iterative.md +1 -1
  30. package/presets/agy/workflows/cc-odd.md +2 -2
  31. package/presets/agy/workflows/cc-openspec.md +1 -1
  32. package/presets/agy/workflows/cc-spec-mutation.md +2 -2
  33. package/presets/agy/workflows/cc-tdd-cycle.md +2 -2
  34. package/presets/claude/CLAUDE.md +1 -1
  35. package/presets/claude/commands/cc/api-contract.md +1 -1
  36. package/presets/claude/commands/cc/ask.md +2 -2
  37. package/presets/claude/commands/cc/council.md +2 -83
  38. package/presets/claude/commands/cc/db-migration.md +1 -1
  39. package/presets/claude/commands/cc/feature.md +1 -1
  40. package/presets/claude/commands/cc/fix.md +1 -1
  41. package/presets/claude/commands/cc/iterative.md +1 -1
  42. package/presets/claude/commands/cc/odd.md +2 -2
  43. package/presets/claude/commands/cc/openspec.md +5 -5
  44. package/presets/claude/commands/cc/spec-mutation.md +2 -2
  45. package/presets/claude/commands/cc/tdd-cycle.md +3 -3
  46. package/presets/claude/settings.json +6 -101
  47. package/presets/claude/skills/backlog/SKILL.md +1 -1
  48. package/presets/claude/skills/evaluation/SKILL.md +1 -1
  49. package/presets/claude/skills/openspec/SKILL.md +10 -6
  50. package/presets/claude/skills/testing-tdd/SKILL.md +3 -3
  51. package/presets/codex/AGENTS.md +1 -1
  52. package/presets/codex/commands/cc-ask.md +2 -2
  53. package/presets/codex/skills/backlog/SKILL.md +1 -1
  54. package/presets/codex/skills/cc-api-contract/SKILL.md +1 -1
  55. package/presets/codex/skills/cc-council/SKILL.md +2 -93
  56. package/presets/codex/skills/cc-db-migration/SKILL.md +1 -1
  57. package/presets/codex/skills/cc-feature/SKILL.md +1 -1
  58. package/presets/codex/skills/cc-fix/SKILL.md +1 -1
  59. package/presets/codex/skills/cc-iterative/SKILL.md +1 -1
  60. package/presets/codex/skills/cc-odd/SKILL.md +2 -2
  61. package/presets/codex/skills/cc-openspec/SKILL.md +10 -8
  62. package/presets/codex/skills/cc-spec-mutation/SKILL.md +2 -2
  63. package/presets/codex/skills/cc-tdd-cycle/SKILL.md +2 -2
  64. package/presets/codex/skills/django-testing/SKILL.md +1 -1
  65. package/presets/codex/skills/evaluation/SKILL.md +1 -1
  66. package/presets/codex/skills/openspec/SKILL.md +10 -6
  67. package/presets/codex/skills/python-django-stack/SKILL.md +1 -1
  68. package/presets/codex/skills/testing-tdd/SKILL.md +3 -3
  69. package/presets/cursor/AGENTS.md +1 -1
  70. package/presets/cursor/commands/cc/api-contract.md +1 -1
  71. package/presets/cursor/commands/cc/ask.md +2 -2
  72. package/presets/cursor/commands/cc/council.md +2 -83
  73. package/presets/cursor/commands/cc/db-migration.md +1 -1
  74. package/presets/cursor/commands/cc/feature.md +1 -1
  75. package/presets/cursor/commands/cc/fix.md +1 -1
  76. package/presets/cursor/commands/cc/iterative.md +1 -1
  77. package/presets/cursor/commands/cc/odd.md +2 -2
  78. package/presets/cursor/commands/cc/openspec.md +10 -8
  79. package/presets/cursor/commands/cc/spec-mutation.md +2 -2
  80. package/presets/cursor/commands/cc/tdd-cycle.md +2 -2
  81. package/presets/cursor/skills/backlog/SKILL.md +1 -1
  82. package/presets/cursor/skills/evaluation/SKILL.md +1 -1
  83. package/presets/cursor/skills/openspec/SKILL.md +10 -6
  84. package/presets/cursor/skills/testing-tdd/SKILL.md +3 -3
  85. package/presets/gemini/GEMINI.md +1 -1
  86. package/presets/gemini/commands/cc/api-contract.toml +1 -1
  87. package/presets/gemini/commands/cc/ask.toml +2 -2
  88. package/presets/gemini/commands/cc/council.toml +2 -83
  89. package/presets/gemini/commands/cc/db-migration.toml +1 -1
  90. package/presets/gemini/commands/cc/feature.toml +1 -1
  91. package/presets/gemini/commands/cc/fix.toml +1 -1
  92. package/presets/gemini/commands/cc/iterative.toml +1 -1
  93. package/presets/gemini/commands/cc/odd.toml +2 -2
  94. package/presets/gemini/commands/cc/openspec.toml +10 -8
  95. package/presets/gemini/commands/cc/spec-mutation.toml +2 -2
  96. package/presets/gemini/commands/cc/tdd-cycle.toml +2 -2
  97. package/presets/muse/AGENTS.md +1 -1
  98. package/presets/opencode/agents/implementer.md +1 -1
  99. package/presets/opencode/agents/tester.md +1 -1
  100. package/presets/opencode/commands/cc-api-contract.md +1 -1
  101. package/presets/opencode/commands/cc-ask.md +2 -2
  102. package/presets/opencode/commands/cc-council.md +2 -83
  103. package/presets/opencode/commands/cc-db-migration.md +1 -1
  104. package/presets/opencode/commands/cc-feature.md +1 -1
  105. package/presets/opencode/commands/cc-fix.md +1 -1
  106. package/presets/opencode/commands/cc-iterative.md +1 -1
  107. package/presets/opencode/commands/cc-odd.md +2 -2
  108. package/presets/opencode/commands/cc-openspec.md +2 -2
  109. package/presets/opencode/commands/cc-spec-mutation.md +2 -2
  110. package/presets/opencode/commands/cc-tdd-cycle.md +2 -2
  111. package/presets/opencode/prompts/v1.0.0/implementer.md +1 -1
  112. package/presets/opencode/prompts/v1.0.0/tester.md +1 -1
  113. package/presets/opencode/skills/backlog/SKILL.md +1 -1
  114. package/presets/opencode/skills/django-testing/SKILL.md +1 -0
  115. package/presets/opencode/skills/evaluation/SKILL.md +1 -1
  116. package/presets/opencode/skills/openspec/SKILL.md +10 -6
  117. package/presets/opencode/skills/python-django-stack/SKILL.md +1 -0
  118. package/presets/opencode/skills/python-fastapi-stack/SKILL.md +1 -0
  119. package/presets/opencode/skills/spring-boot-kotlin/SKILL.md +1 -0
  120. package/presets/opencode/skills/sqlalchemy/SKILL.md +1 -0
  121. package/presets/opencode/skills/testing-tdd/SKILL.md +3 -3
  122. package/presets/pi/AGENTS.md +1 -1
  123. package/presets/shared/invoke-hook.cjs +43 -24
  124. package/src/presets/manifests/claude.yml +1 -1
  125. package/src/presets/shared-skills.yml +30 -0
  126. package/src/presets/targets/pi.yml +1 -1
@@ -2,89 +2,8 @@
2
2
  description: Council-driven workflow with CCEP-1 bootstrap
3
3
  ---
4
4
 
5
- # Council-Driven Workflow
6
-
7
- Task request: $ARGUMENTS
5
+ <!-- GENERATED redirect to presets/agy/workflows/cc-council.md by scripts/inject-ccep-bootstrap.ts — DO NOT EDIT. -->
8
6
 
9
7
  ## Step 0 — CCEP Bootstrap
10
8
 
11
- Command: `council` (fixed for this workflow — do not infer from user text)
12
- command: council
13
-
14
- 1. Run: `npx cc-codeconductor ccep profile council --output json` to get the phases and their roles.
15
- 2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command council --phase <phase-id> "$ARGUMENTS" --view prompt --output json`
16
- 3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command council --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
17
- 4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `$ARGUMENTS` to planners.
18
-
19
- ---
20
-
21
- ## Step 1 — Wayfinding (repo-explorer)
22
-
23
- If `graphify-out/graph.json` exists, run `graphify query "$ARGUMENTS"` (and
24
- `graphify path` / `graphify explain` when needed). Then invoke `repo-explorer`
25
- to map impact radius before deliberation. Do not write code in this step.
26
-
27
- ---
28
-
29
- ## Step 2 — Deliberation & Specification (SDD)
30
-
31
- Invoke the `council` skill to analyze the request before writing any code. The council must act as a steering committee involving `task-coach` (Product), `architect`, and `devil`.
32
-
33
- The council must:
34
- 1. Clarify the prompt and define the absolute minimum scope (Simplicity Gate).
35
- 2. Explicitly document all assumptions and run the Grilling protocol on each one (Think Before Coding).
36
- 3. Draft a Task Card & Technical Plan (The Specification).
37
-
38
- **STOP here.** Unresolved grilling questions populate `questionsForUser` in the
39
- CCEP-1 `planner-output`; `ccep evaluate` (ConfirmationGate) halts until a human
40
- answers. Show the agreed Task Card & Technical Plan and wait for confirmation
41
- before continuing.
42
-
43
- ---
44
-
45
- ## Step 3 — Test Definition (TDD)
46
-
47
- Invoke `tester` with the approved Task Card & Technical Plan.
48
-
49
- tester must:
50
- 1. Write failing tests based on the Acceptance Criteria defined in the Task Card.
51
- 2. Confirm the tests fail as expected (Red state).
52
-
53
- **Goal-Driven Execution (Karpathy)**: Do not proceed until verifiable tests are written and fail for the correct reasons.
54
-
55
- ---
56
-
57
- ## Step 4 — Surgical Implementation
58
-
59
- Invoke `implementer` with the failing tests and the Technical Plan.
60
-
61
- implementer must:
62
- 1. Write the minimal code required to pass the tests.
63
- 2. Touch ONLY the files specified in the Technical Plan (Surgical Changes).
64
- 3. NOT refactor adjacent code, change existing styles, or build speculative features.
65
- 4. Run the tests. Loop `implementer` -> `tester` until all tests pass (Green state), at most 3 iterations -- then stop and report the failing tests instead of looping.
66
-
67
- ---
68
-
69
- ## Step 5 — Multi-Perspective Council Review
70
-
71
- Invoke the `council` skill on the generated diff to perform the final review phase.
72
-
73
- The council will evaluate the diff against the 6 axes (Architecture, Security, Product, Delivery, DataOps, Devil).
74
-
75
- If ANY agent votes CRITICAL (especially due to over-engineering, scope creep, or missing the verifiable goals):
76
- - The Review Report status is **BLOCKED**.
77
- - Return to Step 4 with the feedback (at most 3 review rounds in total -- then deliver the BLOCKED verdict with the unresolved findings instead of looping).
78
-
79
- If APPROVED (no CRITICAL findings):
80
- - Deliver the final Council Verdict and the diff summary.
81
-
82
- ---
83
-
84
- ## Completion
85
-
86
- Deliver the complete Council Verdict. The feature is only complete when tests pass and the council explicitly approves the implementation according to the specification.
87
-
88
- ## Next
89
-
90
- Approved: merge. Blocked: return the findings to `/cc:fix` or `/cc:feature`.
9
+ command: council. Read `presets/agy/workflows/cc-council.md`, then `ccep profile council` + `ccep compile --command council --view prompt`.
@@ -29,7 +29,7 @@ If `openspec status` reports an active change folder:
29
29
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
30
30
  4. Next command spelling on this runner: `/cc:db-migration`
31
31
 
32
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
32
+ Run the CLI as `npx cc-codeconductor <same argv>`.
33
33
 
34
34
  ---
35
35
 
@@ -53,7 +53,7 @@ If `openspec status` reports an active change folder:
53
53
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
54
54
  4. Next command spelling on this runner: `/cc:feature`
55
55
 
56
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
56
+ Run the CLI as `npx cc-codeconductor <same argv>`.
57
57
 
58
58
  Skills: `using-cc-skills`, `openspec`, `testing-tdd`, `evaluation`.
59
59
  Do not skip `openspec analyze` when a change folder is active.
@@ -61,7 +61,7 @@ If `openspec status` reports an active change folder:
61
61
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
62
62
  4. Next command spelling on this runner: `/cc:fix`
63
63
 
64
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
64
+ Run the CLI as `npx cc-codeconductor <same argv>`.
65
65
 
66
66
  ---
67
67
 
@@ -31,7 +31,7 @@ If `openspec status` reports an active change folder:
31
31
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
32
32
  4. Next command spelling on this runner: `/cc:iterative`
33
33
 
34
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
34
+ Run the CLI as `npx cc-codeconductor <same argv>`.
35
35
 
36
36
  ---
37
37
 
@@ -7,8 +7,8 @@ description: Create or resume an opt-in Delivery Ledger for substantial authoriz
7
7
  ## Step 0 — CCEP Bootstrap
8
8
 
9
9
  ```bash
10
- bun run dev ccep profile odd --output json
11
- bun run dev ccep compile --command odd --phase <phase-id> "$ARGUMENTS" --view prompt --output json
10
+ npx cc-codeconductor ccep profile odd --output json
11
+ npx cc-codeconductor ccep compile --command odd --phase <phase-id> "$ARGUMENTS" --view prompt --output json
12
12
  ```
13
13
 
14
14
  Pass each subagent only the compiled `prompt` for its phase.
@@ -57,7 +57,7 @@ If `openspec status` reports an active change folder:
57
57
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
58
58
  4. Next command spelling on this runner: `/cc:openspec`
59
59
 
60
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
60
+ Run the CLI as `npx cc-codeconductor <same argv>`.
61
61
 
62
62
  ---
63
63
 
@@ -141,11 +141,13 @@ npx cc-codeconductor openspec verify <itemId>
141
141
  npx cc-codeconductor openspec archive <itemId>
142
142
  ```
143
143
 
144
- `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `sync` merges delta specs into `openspec/specs/` without closing the item (optional before archive). `verify` is the advisory pre-archive checklist: exit 0 with `archiveReady` plus Completeness/Correctness/Coherence issues. `archive` requires all cards done (and review evidence when Global review is required), re-checks planning artifacts and analyze CRITICALs, warns on unchecked `tasks.md` boxes, then moves `openspec/changes/<slug>` to `archive/`.
144
+ `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `sync` merges delta specs into `openspec/specs/` without closing the item (optional before archive). `verify` is the advisory pre-archive checklist: exit 0 with `archiveReady` plus Completeness/Correctness/Coherence issues. `archive` requires all cards done (and review evidence when Global review is required), re-checks planning artifacts and analyze CRITICALs, fails on unchecked `tasks.md` boxes (override: `--allow-unchecked`), ticks the BACKLOG acceptance criteria, then moves `openspec/changes/<slug>` to `archive/`.
145
145
 
146
- For test and implementation cards, `done` also requires a current RDD-backed
147
- RED or GREEN receipt respectively. Do not reuse evidence after candidate files
148
- change; capture and verify the matching receipt again.
146
+ For test and implementation cards, `done` requires current runner-captured TDD
147
+ evidence: `npx cc-codeconductor tdd capture --task <cardId> --phase red|green --command "<test command>"`
148
+ (RED for the test card, GREEN for the implement card). It is `ev-tdd-*` evidence,
149
+ not an RDD receipt: do not pass it to `rdd verify`. Do not reuse evidence after
150
+ candidate files change; capture it again.
149
151
 
150
152
  ---
151
153
 
@@ -182,9 +184,9 @@ After each phase:
182
184
 
183
185
  Implementer: create a Git worktree before editing (`git worktree add ../<branch>-session <branch>`).
184
186
 
185
- Discover is read-only: `repo-explorer` never writes code. The implementer ticks
186
- `tasks.md` boxes (`- [ ]` → `- [x]`) as each FR lands — only `x`/`X` counts as
187
- done. If implementation reveals a design problem, pause and reconcile the
187
+ Discover is read-only: `repo-explorer` never writes code. `openspec done` ticks the boxes tagged
188
+ with that card and keeps your edits; the implementer ticks any other `tasks.md` box
189
+ it adds (`- [ ]` → `- [x]`) — only `x`/`X` counts as done. If implementation reveals a design problem, pause and reconcile the
188
190
  planning artifacts first (any direction: a later artifact may force revising an
189
191
  earlier one). Planning artifacts only in that step — never code — and confirm
190
192
  each edit. If the item's intent changed rather than its details, open a fresh
@@ -39,7 +39,7 @@ If `openspec status` reports an active change folder:
39
39
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
40
40
  4. Next command spelling on this runner: `/cc:spec-mutation`
41
41
 
42
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
42
+ Run the CLI as `npx cc-codeconductor <same argv>`.
43
43
 
44
44
  ---
45
45
 
@@ -101,7 +101,7 @@ aborts the pipeline with scorecard 0 (Specification Gaming).
101
101
  ## Stage 3 — TDD under the three laws (`tdd_craftsman`)
102
102
 
103
103
  Delegates to the `/cc:tdd-cycle` state machine (`tddCycleStateMachine` in
104
- `domain/loop`). Evidence must be captured with `captureTddSuiteEvidence` — do
104
+ `domain/loop`). Evidence must be captured with `npx cc-codeconductor tdd capture` — do
105
105
  not hand-edit JSON under `.codeconductor/evidence/`.
106
106
 
107
107
  1. **Law 1 (RED):** no production code except to make a failing test pass. A
@@ -39,7 +39,7 @@ If `openspec status` reports an active change folder:
39
39
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
40
40
  4. Next command spelling on this runner: `/cc:tdd-cycle`
41
41
 
42
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
42
+ Run the CLI as `npx cc-codeconductor <same argv>`.
43
43
 
44
44
  ---
45
45
 
@@ -59,7 +59,7 @@ Mixing phases invalidates the cycle.
59
59
  ## Verifiable phase gates
60
60
 
61
61
  RED → GREEN and GREEN → REFACTOR are enforced by `tddCycleStateMachine` in
62
- `domain/loop`. Evidence must be captured with `captureTddSuiteEvidence` (verification
62
+ `domain/loop`. Evidence must be captured with `npx cc-codeconductor tdd capture` (verification
63
63
  runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
64
64
 
65
65
  - RED→GREEN requires runner evidence that the suite **failed**.
@@ -29,7 +29,7 @@ the item here.
29
29
  4. Create `BACKLOG.md` from `presets/templates/BACKLOG.md` or append under
30
30
  `## Items`. Do not rewrite `## Global` or `## Archive`.
31
31
  5. Next ID = max numeric suffix in Items + Archive + 1, zero-padded (`BC-013`).
32
- 6. `bun run dev openspec validate` (or `npx cc-codeconductor`). Fix until valid.
32
+ 6. `npx cc-codeconductor openspec validate`. Fix until valid.
33
33
  7. `openspec plan BC-xxx` for each **new** item this run. Then tell the user
34
34
  to run `/cc-openspec`.
35
35
 
@@ -25,7 +25,7 @@ Pass threshold: weighted score >= 2.0 and no criterion at 0.
25
25
 
26
26
  ## Process
27
27
 
28
- Local: `bun run dev`. Published: `npx cc-codeconductor`.
28
+ The CLI is always `npx cc-codeconductor`.
29
29
 
30
30
  ```text
31
31
  scorecard create --task BC-001 --from-diff
@@ -24,7 +24,7 @@ coding rules.
24
24
 
25
25
  ## Process
26
26
 
27
- Local CLI is `bun run dev`. Published package is `npx cc-codeconductor`.
27
+ The CLI is always `npx cc-codeconductor`.
28
28
 
29
29
  1. `openspec validate` — must pass before delivery. If you reached this
30
30
  workflow on your own (the user did not ask for OpenSpec) and there is no
@@ -40,9 +40,13 @@ Local CLI is `bun run dev`. Published package is `npx cc-codeconductor`.
40
40
  5. Phases: discover (`repo-explorer`) → design (`architect`) → test (`tester`) →
41
41
  implement (`implementer`) → review (`reviewer`). If Global `TDD required: yes`,
42
42
  test runs before implement. Discover is read-only: it never writes code.
43
- 6. `openspec done` on test/implement requires `captureTddSuiteEvidence`. Handmade
44
- evidence JSON is rejected. The implementer ticks `tasks.md` boxes
45
- (`- [ ]` → `- [x]`) as each FR lands; only `x`/`X` counts as done.
43
+ 6. `openspec done` on test/implement needs runner evidence: run
44
+ `npx cc-codeconductor tdd capture --task <cardId> --phase red|green --command "<test command>"`
45
+ first (RED on the test card, GREEN on the implement card). Handmade evidence JSON is
46
+ rejected. It is `ev-tdd-*` evidence, not an RDD receipt (`ev-rdd-*`, `rdd verify`).
47
+ `done` ticks that card's `tasks.md` boxes and keeps your edits; the implementer ticks
48
+ any other box it adds (`- [ ]` → `- [x]`, only `x`/`X` counts). `archive` fails while
49
+ boxes stay unchecked (override: `--allow-unchecked`).
46
50
  7. When implementation reveals a design problem, pause and reconcile the planning
47
51
  artifacts first — in any direction (a later artifact may force revising an
48
52
  earlier one). Planning artifacts only in that step, never code; confirm each
@@ -54,7 +58,7 @@ Local CLI is `bun run dev`. Published package is `npx cc-codeconductor`.
54
58
  9. `scorecard create --task BC-xxx --from-diff` then record a verdict.
55
59
  10. `openspec archive` only after human review when `Review required: yes` and
56
60
  the scorecard is PASS. Archive re-checks planning artifacts and analyze
57
- CRITICALs, and warns on unchecked `tasks.md` boxes.
61
+ CRITICALs, and fails on unchecked `tasks.md` boxes (override: `--allow-unchecked`), ticks the BACKLOG acceptance criteria.
58
62
 
59
63
  Status machine: `TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE`
60
64
  → Archive. `BLOCKED` returns to `READY`. Reviewer rejection: `REVIEW` →
@@ -111,4 +115,4 @@ delivery read-only and record unavailable visual or emulator evidence as pending
111
115
  - [ ] `tasks.md` boxes ticked as FRs land
112
116
  - [ ] `openspec verify --output json` checked before archive
113
117
  - [ ] `scorecard create --from-diff` recorded
114
- - [ ] Suite check (optional): `bun run dev scorecard suite-run --suite workflow-gates`
118
+ - [ ] Suite check (optional): `npx cc-codeconductor scorecard suite-run --suite workflow-gates`
@@ -11,7 +11,7 @@ description:
11
11
  ## Overview
12
12
 
13
13
  Red (failing test) → Green (minimal code) → Refactor. Evidence comes from
14
- `captureTddSuiteEvidence`, not handmade JSON.
14
+ `npx cc-codeconductor tdd capture`, not handmade JSON.
15
15
 
16
16
  ## When to Use
17
17
 
@@ -29,7 +29,7 @@ Red (failing test) → Green (minimal code) → Refactor. Evidence comes from
29
29
  when TDD is required).
30
30
  5. Cover happy path, edge, and error for each behavior.
31
31
 
32
- Local: `bun run dev`. Pyramid default: many unit, fewer integration, rare E2E.
32
+ Pyramid default: many unit, fewer integration, rare E2E.
33
33
 
34
34
  ## Common Rationalizations
35
35
 
@@ -50,4 +50,4 @@ Local: `bun run dev`. Pyramid default: many unit, fewer integration, rare E2E.
50
50
  - [ ] Suite failed before implement
51
51
  - [ ] Suite passed after implement
52
52
  - [ ] Runner evidence exists (not handmade)
53
- - [ ] Optional: `bun run dev scorecard suite-run --suite workflow-gates`
53
+ - [ ] Optional: `npx cc-codeconductor scorecard suite-run --suite workflow-gates`
@@ -37,7 +37,7 @@ intent to the right slash command.
37
37
 
38
38
  ## Receipt integrity
39
39
 
40
- - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
40
+ - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `npx cc-codeconductor rdd`.
41
41
  - A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
42
42
  - TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
43
43
 
@@ -25,7 +25,7 @@ If `openspec status` reports an active change folder:
25
25
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
26
26
  4. Next command spelling on this runner: `/cc:api-contract`
27
27
 
28
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
28
+ Run the CLI as `npx cc-codeconductor <same argv>`.
29
29
 
30
30
  ---
31
31
 
@@ -12,10 +12,10 @@ Do **not** run the recommended `/cc:` command unless the human confirms.
12
12
 
13
13
  ## Step 1 — Recommend (deterministic)
14
14
 
15
- Run (local repo: `bun run dev`; published package: `npx cc-codeconductor`):
15
+ Run `npx cc-codeconductor`:
16
16
 
17
17
  ```bash
18
- bun run dev ask "{{args}}" --output json
18
+ npx cc-codeconductor ask "{{args}}" --output json
19
19
  ```
20
20
 
21
21
  or:
@@ -1,90 +1,9 @@
1
1
  description = "Council-driven workflow with CCEP-1 bootstrap"
2
2
 
3
3
  prompt = """
4
- # Council-Driven Workflow
5
-
6
- Task request: {{args}}
4
+ <!-- GENERATED redirect to presets/agy/workflows/cc-council.md by scripts/render-agent-commands.ts — DO NOT EDIT. -->
7
5
 
8
6
  ## Step 0 — CCEP Bootstrap
9
7
 
10
- Command: `council` (fixed for this workflow — do not infer from user text)
11
- command: council
12
-
13
- 1. Run: `npx cc-codeconductor ccep profile council --output json` to get the phases and their roles.
14
- 2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command council --phase <phase-id> "{{args}}" --view prompt --output json`
15
- 3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command council --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
16
- 4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
17
-
18
- ---
19
-
20
- ## Step 1 — Wayfinding (repo-explorer)
21
-
22
- If `graphify-out/graph.json` exists, run `graphify query "{{args}}"` (and
23
- `graphify path` / `graphify explain` when needed). Then invoke `repo-explorer`
24
- to map impact radius before deliberation. Do not write code in this step.
25
-
26
- ---
27
-
28
- ## Step 2 — Deliberation & Specification (SDD)
29
-
30
- Invoke the `council` skill to analyze the request before writing any code. The council must act as a steering committee involving `task-coach` (Product), `architect`, and `devil`.
31
-
32
- The council must:
33
- 1. Clarify the prompt and define the absolute minimum scope (Simplicity Gate).
34
- 2. Explicitly document all assumptions and run the Grilling protocol on each one (Think Before Coding).
35
- 3. Draft a Task Card & Technical Plan (The Specification).
36
-
37
- **STOP here.** Unresolved grilling questions populate `questionsForUser` in the
38
- CCEP-1 `planner-output`; `ccep evaluate` (ConfirmationGate) halts until a human
39
- answers. Show the agreed Task Card & Technical Plan and wait for confirmation
40
- before continuing.
41
-
42
- ---
43
-
44
- ## Step 3 — Test Definition (TDD)
45
-
46
- Invoke `tester` with the approved Task Card & Technical Plan.
47
-
48
- tester must:
49
- 1. Write failing tests based on the Acceptance Criteria defined in the Task Card.
50
- 2. Confirm the tests fail as expected (Red state).
51
-
52
- **Goal-Driven Execution (Karpathy)**: Do not proceed until verifiable tests are written and fail for the correct reasons.
53
-
54
- ---
55
-
56
- ## Step 4 — Surgical Implementation
57
-
58
- Invoke `implementer` with the failing tests and the Technical Plan.
59
-
60
- implementer must:
61
- 1. Write the minimal code required to pass the tests.
62
- 2. Touch ONLY the files specified in the Technical Plan (Surgical Changes).
63
- 3. NOT refactor adjacent code, change existing styles, or build speculative features.
64
- 4. Run the tests. Loop `implementer` -> `tester` until all tests pass (Green state), at most 3 iterations -- then stop and report the failing tests instead of looping.
65
-
66
- ---
67
-
68
- ## Step 5 — Multi-Perspective Council Review
69
-
70
- Invoke the `council` skill on the generated diff to perform the final review phase.
71
-
72
- The council will evaluate the diff against the 6 axes (Architecture, Security, Product, Delivery, DataOps, Devil).
73
-
74
- If ANY agent votes CRITICAL (especially due to over-engineering, scope creep, or missing the verifiable goals):
75
- - The Review Report status is **BLOCKED**.
76
- - Return to Step 4 with the feedback (at most 3 review rounds in total -- then deliver the BLOCKED verdict with the unresolved findings instead of looping).
77
-
78
- If APPROVED (no CRITICAL findings):
79
- - Deliver the final Council Verdict and the diff summary.
80
-
81
- ---
82
-
83
- ## Completion
84
-
85
- Deliver the complete Council Verdict. The feature is only complete when tests pass and the council explicitly approves the implementation according to the specification.
86
-
87
- ## Next
88
-
89
- Approved: merge. Blocked: return the findings to `/cc:fix` or `/cc:feature`.
8
+ command: council. Read `presets/agy/workflows/cc-council.md`, then `ccep profile council` + `ccep compile --command council --view prompt`.
90
9
  """
@@ -26,7 +26,7 @@ If `openspec status` reports an active change folder:
26
26
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
27
27
  4. Next command spelling on this runner: `/cc:db-migration`
28
28
 
29
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
29
+ Run the CLI as `npx cc-codeconductor <same argv>`.
30
30
 
31
31
  ---
32
32
 
@@ -50,7 +50,7 @@ If `openspec status` reports an active change folder:
50
50
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
51
51
  4. Next command spelling on this runner: `/cc:feature`
52
52
 
53
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
53
+ Run the CLI as `npx cc-codeconductor <same argv>`.
54
54
 
55
55
  Skills: `using-cc-skills`, `openspec`, `testing-tdd`, `evaluation`.
56
56
  Do not skip `openspec analyze` when a change folder is active.
@@ -58,7 +58,7 @@ If `openspec status` reports an active change folder:
58
58
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
59
59
  4. Next command spelling on this runner: `/cc:fix`
60
60
 
61
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
61
+ Run the CLI as `npx cc-codeconductor <same argv>`.
62
62
 
63
63
  ---
64
64
 
@@ -28,7 +28,7 @@ If `openspec status` reports an active change folder:
28
28
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
29
29
  4. Next command spelling on this runner: `/cc:iterative`
30
30
 
31
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
31
+ Run the CLI as `npx cc-codeconductor <same argv>`.
32
32
 
33
33
  ---
34
34
 
@@ -6,8 +6,8 @@ prompt = """
6
6
  ## Step 0 — CCEP Bootstrap
7
7
 
8
8
  ```bash
9
- bun run dev ccep profile odd --output json
10
- bun run dev ccep compile --command odd --phase <phase-id> "{{args}}" --view prompt --output json
9
+ npx cc-codeconductor ccep profile odd --output json
10
+ npx cc-codeconductor ccep compile --command odd --phase <phase-id> "{{args}}" --view prompt --output json
11
11
  ```
12
12
 
13
13
  Pass each subagent only the compiled `prompt` for its phase.
@@ -54,7 +54,7 @@ If `openspec status` reports an active change folder:
54
54
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
55
55
  4. Next command spelling on this runner: `/cc:openspec`
56
56
 
57
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
57
+ Run the CLI as `npx cc-codeconductor <same argv>`.
58
58
 
59
59
  ---
60
60
 
@@ -138,11 +138,13 @@ npx cc-codeconductor openspec verify <itemId>
138
138
  npx cc-codeconductor openspec archive <itemId>
139
139
  ```
140
140
 
141
- `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `sync` merges delta specs into `openspec/specs/` without closing the item (optional before archive). `verify` is the advisory pre-archive checklist: exit 0 with `archiveReady` plus Completeness/Correctness/Coherence issues. `archive` requires all cards done (and review evidence when Global review is required), re-checks planning artifacts and analyze CRITICALs, warns on unchecked `tasks.md` boxes, then moves `openspec/changes/<slug>` to `archive/`.
141
+ `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `sync` merges delta specs into `openspec/specs/` without closing the item (optional before archive). `verify` is the advisory pre-archive checklist: exit 0 with `archiveReady` plus Completeness/Correctness/Coherence issues. `archive` requires all cards done (and review evidence when Global review is required), re-checks planning artifacts and analyze CRITICALs, fails on unchecked `tasks.md` boxes (override: `--allow-unchecked`), ticks the BACKLOG acceptance criteria, then moves `openspec/changes/<slug>` to `archive/`.
142
142
 
143
- For test and implementation cards, `done` also requires a current RDD-backed
144
- RED or GREEN receipt respectively. Do not reuse evidence after candidate files
145
- change; capture and verify the matching receipt again.
143
+ For test and implementation cards, `done` requires current runner-captured TDD
144
+ evidence: `npx cc-codeconductor tdd capture --task <cardId> --phase red|green --command "<test command>"`
145
+ (RED for the test card, GREEN for the implement card). It is `ev-tdd-*` evidence,
146
+ not an RDD receipt: do not pass it to `rdd verify`. Do not reuse evidence after
147
+ candidate files change; capture it again.
146
148
 
147
149
  ---
148
150
 
@@ -179,9 +181,9 @@ After each phase:
179
181
 
180
182
  Implementer: create a Git worktree before editing (`git worktree add ../<branch>-session <branch>`).
181
183
 
182
- Discover is read-only: `repo-explorer` never writes code. The implementer ticks
183
- `tasks.md` boxes (`- [ ]` → `- [x]`) as each FR lands — only `x`/`X` counts as
184
- done. If implementation reveals a design problem, pause and reconcile the
184
+ Discover is read-only: `repo-explorer` never writes code. `openspec done` ticks the boxes tagged
185
+ with that card and keeps your edits; the implementer ticks any other `tasks.md` box
186
+ it adds (`- [ ]` → `- [x]`) — only `x`/`X` counts as done. If implementation reveals a design problem, pause and reconcile the
185
187
  planning artifacts first (any direction: a later artifact may force revising an
186
188
  earlier one). Planning artifacts only in that step — never code — and confirm
187
189
  each edit. If the item's intent changed rather than its details, open a fresh
@@ -35,7 +35,7 @@ If `openspec status` reports an active change folder:
35
35
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
36
36
  4. Next command spelling on this runner: `/cc:spec-mutation`
37
37
 
38
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
38
+ Run the CLI as `npx cc-codeconductor <same argv>`.
39
39
 
40
40
  ---
41
41
 
@@ -97,7 +97,7 @@ aborts the pipeline with scorecard 0 (Specification Gaming).
97
97
  ## Stage 3 — TDD under the three laws (`tdd_craftsman`)
98
98
 
99
99
  Delegates to the `/cc:tdd-cycle` state machine (`tddCycleStateMachine` in
100
- `domain/loop`). Evidence must be captured with `captureTddSuiteEvidence` — do
100
+ `domain/loop`). Evidence must be captured with `npx cc-codeconductor tdd capture` — do
101
101
  not hand-edit JSON under `.codeconductor/evidence/`.
102
102
 
103
103
  1. **Law 1 (RED):** no production code except to make a failing test pass. A
@@ -35,7 +35,7 @@ If `openspec status` reports an active change folder:
35
35
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
36
36
  4. Next command spelling on this runner: `/cc:tdd-cycle`
37
37
 
38
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
38
+ Run the CLI as `npx cc-codeconductor <same argv>`.
39
39
 
40
40
  ---
41
41
 
@@ -55,7 +55,7 @@ Mixing phases invalidates the cycle.
55
55
  ## Verifiable phase gates
56
56
 
57
57
  RED → GREEN and GREEN → REFACTOR are enforced by `tddCycleStateMachine` in
58
- `domain/loop`. Evidence must be captured with `captureTddSuiteEvidence` (verification
58
+ `domain/loop`. Evidence must be captured with `npx cc-codeconductor tdd capture` (verification
59
59
  runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
60
60
 
61
61
  - RED→GREEN requires runner evidence that the suite **failed**.
@@ -39,7 +39,7 @@ Where a step says "adopt the `X` role", read the matching skill under
39
39
 
40
40
  ## Receipt integrity
41
41
 
42
- - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
42
+ - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `npx cc-codeconductor rdd`.
43
43
  - A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
44
44
  - TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
45
45
 
@@ -221,6 +221,6 @@ tests. On **REJECT**, stop and escalate to the orchestrator.
221
221
  Invoke via `/cc-feature`, `/cc-fix`, `/cc-tdd-cycle`, or the orchestrator.
222
222
  Do not invoke other agents. Invoke skill `testing-tdd`.
223
223
  Deliverable is incomplete without a passing suite and runner TDD evidence when
224
- TDD is required. Scorecard: `bun run dev scorecard create --from-diff`.
224
+ TDD is required. Scorecard: `npx cc-codeconductor scorecard create --from-diff`.
225
225
  Before handing work to review or delivery, verify the current RDD receipt. Do
226
226
  not rely on a test result if its candidate has changed.
@@ -290,6 +290,6 @@ and confirmed failing; list the failing test paths in `artifacts` so the
290
290
 
291
291
  Invoke via `/cc-tdd-cycle`, `/cc-feature`, or the orchestrator (test before
292
292
  implement). Do not invoke other agents. Invoke skill `testing-tdd`.
293
- Deliverable is incomplete without `captureTddSuiteEvidence` when TDD is required.
293
+ Deliverable is incomplete without `npx cc-codeconductor tdd capture` when TDD is required.
294
294
  Record the matching RDD receipt and report it with the test evidence. A changed
295
295
  candidate requires a new verification before handoff.
@@ -28,7 +28,7 @@ If `openspec status` reports an active change folder:
28
28
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
29
29
  4. Next command spelling on this runner: `/cc-api-contract`
30
30
 
31
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
31
+ Run the CLI as `npx cc-codeconductor <same argv>`.
32
32
 
33
33
  ---
34
34
 
@@ -15,10 +15,10 @@ Do **not** run the recommended `/cc-` command unless the human confirms.
15
15
 
16
16
  ## Step 1 — Recommend (deterministic)
17
17
 
18
- Run (local repo: `bun run dev`; published package: `npx cc-codeconductor`):
18
+ Run `npx cc-codeconductor`:
19
19
 
20
20
  ```bash
21
- bun run dev ask "$ARGUMENTS" --output json
21
+ npx cc-codeconductor ask "$ARGUMENTS" --output json
22
22
  ```
23
23
 
24
24
  or: