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
@@ -21,24 +21,17 @@ Provide the following information in $ARGUMENTS:
21
21
 
22
22
  ## Web interface scope
23
23
 
24
- When the task concerns web layout, component states, feedback, motion, or a
25
- requested UI audit, apply skill `web-design-engineering` from the installed skill
26
- library. Use it during intake/discovery, design, test/implement, and review as
27
- applicable; keep this workflow’s gates and TDD order. Framework presence alone
28
- does not activate it; backend-only and native mobile work are excluded. Record
29
- required visual checks as pending when unavailable. Keep findings in the existing
30
- Review Report: contract failures in Spec Axis, technical issues in existing
31
- subchecks, and aesthetic preferences as suggestions; do not add an axis.
24
+ Same web scope as `cc-feature`: when the fix concerns web layout, component
25
+ states, feedback, motion, or a requested UI audit, apply skill
26
+ `web-design-engineering` during test/implementation and review; keep this
27
+ workflow's gates and TDD order. See `cc-feature` for the full scope rule.
32
28
 
33
29
  ## Android phone interface scope
34
30
 
35
- When the task concerns concrete Jetpack Compose phone layout, component states,
36
- interaction, accessibility, visual behavior, or a requested UI audit, apply skill
37
- `android-ui-design`. Use it during design, test/implementation, and review as
38
- applicable while keeping this workflow's gates and TDD order. Kotlin, Compose,
39
- framework, or dependency presence alone does not activate it; non-UI Android work
40
- stays with the general `android` skill. Audit-only requests remain read-only, and
41
- unavailable visual or emulator checks remain pending rather than claimed complete.
31
+ Same Android scope as `cc-feature`: when the fix concerns concrete Jetpack
32
+ Compose phone UI or a requested UI audit, apply skill `android-ui-design`
33
+ during test/implementation and review; keep this workflow's gates and TDD
34
+ order. See `cc-feature` for the full scope rule.
42
35
 
43
36
 
44
37
  ## Step 1 — Task Card validation (task-coach)
@@ -71,7 +64,7 @@ the affected code, and no public API or shared state is involved.
71
64
 
72
65
  Route: `task-coach` → `tester` → `implementer`
73
66
 
74
- Proceed directly to Step 3a.
67
+ Proceed directly to Step 3.
75
68
 
76
69
  ### Medium or high-risk route
77
70
 
@@ -92,23 +85,37 @@ before continuing.**
92
85
 
93
86
  ---
94
87
 
95
- ## Step 3a — Implementation, low-risk (implementer)
88
+ ## Step 3 — Regression tests (tester)
96
89
 
97
- Invoke `implementer` with the Task Card.
90
+ Invoke `tester` for all risk levels.
91
+
92
+ tester must:
93
+
94
+ 1. Write a regression test that reproduces the original bug (fails before the
95
+ fix, passes after)
96
+ 2. Verify that existing tests still pass
97
+ 3. Produce a Coverage Summary: test added, case covered
98
+
99
+ ---
100
+
101
+ ## Step 4a — Implementation, low-risk (implementer)
102
+
103
+ Invoke `implementer` with the Task Card and the failing regression test from Step 3.
98
104
  Implementer creates a Git Worktree before touching any file; all edits happen inside it.
99
105
 
100
106
  implementer must:
101
107
 
102
108
  1. Locate the defect using the reproduction steps
103
- 2. Apply the minimal fix — no unrelated changes
109
+ 2. Apply the minimal fix to make the regression test pass — no unrelated changes
104
110
  3. Run the test suite
105
111
  4. Produce an Implementation Summary: root cause, fix applied, files changed
106
112
 
107
113
  ---
108
114
 
109
- ## Step 3b — Implementation, medium/high-risk (implementer)
115
+ ## Step 4b — Implementation, medium/high-risk (implementer)
110
116
 
111
- Invoke `implementer` with the approved Technical Plan and the Task Card.
117
+ Invoke `implementer` with the approved Technical Plan, the Task Card, and the
118
+ failing regression test from Step 3.
112
119
  Implementer creates a Git Worktree before touching any file; all edits happen inside it.
113
120
 
114
121
  implementer must follow the plan exactly. Any deviation requires a new Technical
@@ -116,19 +123,6 @@ Plan approval. After implementation, run the full test suite.
116
123
 
117
124
  ---
118
125
 
119
- ## Step 4 — Regression tests (tester)
120
-
121
- Invoke `tester` for all risk levels.
122
-
123
- tester must:
124
-
125
- 1. Write a regression test that reproduces the original bug (fails before the
126
- fix, passes after)
127
- 2. Verify that existing tests still pass
128
- 3. Produce a Coverage Summary: test added, case covered
129
-
130
- ---
131
-
132
126
  ## Step 5 — Review (reviewer) — medium/high-risk only
133
127
 
134
128
  Invoke `reviewer` with the diff and Task Card.
@@ -77,7 +77,7 @@ aborts the pipeline with scorecard 0 (Specification Gaming).
77
77
  ## Stage 3 — TDD under the three laws (`tdd_craftsman`)
78
78
 
79
79
  Delegates to the `/cc-tdd-cycle` state machine (`tddCycleStateMachine` in
80
- `domain/loop`). Evidence must be captured with `captureTddSuiteEvidence` — do
80
+ `domain/loop`). Evidence must be captured with `npx cc-codeconductor tdd capture` — do
81
81
  not hand-edit JSON under `.codeconductor/evidence/`.
82
82
 
83
83
  1. **Law 1 (RED):** no production code except to make a failing test pass. A
@@ -33,7 +33,7 @@ Mixing phases invalidates the cycle.
33
33
  ## Verifiable phase gates
34
34
 
35
35
  RED → GREEN and GREEN → REFACTOR are enforced by `tddCycleStateMachine` in
36
- `domain/loop`. Evidence must be captured with `captureTddSuiteEvidence` (verification
36
+ `domain/loop`. Evidence must be captured with `npx cc-codeconductor tdd capture` (verification
37
37
  runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
38
38
 
39
39
  - RED→GREEN requires runner evidence that the suite **failed**.
@@ -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`
@@ -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-api-contract`
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
 
@@ -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:
@@ -3,6 +3,8 @@ name: cc-council
3
3
  description: Run the full Council-Driven Development workflow — SDD spec creation, TDD enforcement, surgical implementation, and multi-perspective review.
4
4
  ---
5
5
 
6
+ <!-- Source of truth for the council workflow command. The cursor, claude and opencode copies are generated from this template by scripts/inject-ccep-bootstrap.ts; gemini and codex derive from the cursor copy via scripts/render-agent-commands.ts. Edit here, then regenerate. -->
7
+
6
8
  # Council-Driven Workflow
7
9
 
8
10
  Task request: $ARGUMENTS
@@ -30,7 +30,7 @@ If `openspec status` reports an active change folder:
30
30
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
31
31
  4. Next command spelling on this runner: `/cc-db-migration`
32
32
 
33
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
33
+ Run the CLI as `npx cc-codeconductor <same argv>`.
34
34
 
35
35
  ---
36
36
 
@@ -52,7 +52,7 @@ If `openspec status` reports an active change folder:
52
52
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
53
53
  4. Next command spelling on this runner: `/cc-feature`
54
54
 
55
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
55
+ Run the CLI as `npx cc-codeconductor <same argv>`.
56
56
 
57
57
  Skills: `using-cc-skills`, `openspec`, `testing-tdd`, `evaluation`.
58
58
  Do not skip `openspec analyze` when a change folder is active.
@@ -62,7 +62,7 @@ If `openspec status` reports an active change folder:
62
62
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
63
63
  4. Next command spelling on this runner: `/cc-fix`
64
64
 
65
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
65
+ Run the CLI as `npx cc-codeconductor <same argv>`.
66
66
 
67
67
  ---
68
68
 
@@ -30,7 +30,7 @@ If `openspec status` reports an active change folder:
30
30
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
31
31
  4. Next command spelling on this runner: `/cc-iterative`
32
32
 
33
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
33
+ Run the CLI as `npx cc-codeconductor <same argv>`.
34
34
 
35
35
  ---
36
36
 
@@ -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.
@@ -60,7 +60,7 @@ If `openspec status` reports an active change folder:
60
60
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
61
61
  4. Next command spelling on this runner: `/cc-openspec`
62
62
 
63
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
63
+ Run the CLI as `npx cc-codeconductor <same argv>`.
64
64
 
65
65
  ---
66
66
 
@@ -40,7 +40,7 @@ If `openspec status` reports an active change folder:
40
40
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
41
41
  4. Next command spelling on this runner: `/cc-spec-mutation`
42
42
 
43
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
43
+ Run the CLI as `npx cc-codeconductor <same argv>`.
44
44
 
45
45
  ---
46
46
 
@@ -102,7 +102,7 @@ aborts the pipeline with scorecard 0 (Specification Gaming).
102
102
  ## Stage 3 — TDD under the three laws (`tdd_craftsman`)
103
103
 
104
104
  Delegates to the `/cc-tdd-cycle` state machine (`tddCycleStateMachine` in
105
- `domain/loop`). Evidence must be captured with `captureTddSuiteEvidence` — do
105
+ `domain/loop`). Evidence must be captured with `npx cc-codeconductor tdd capture` — do
106
106
  not hand-edit JSON under `.codeconductor/evidence/`.
107
107
 
108
108
  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**.
@@ -804,7 +804,7 @@ extending capabilities, apply `.claude/skills/find-skills/SKILL.md`.
804
804
 
805
805
  ## Receipt integrity
806
806
 
807
- - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
807
+ - For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `npx cc-codeconductor rdd`.
808
808
  - A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
809
809
  - TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
810
810
 
@@ -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:
@@ -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.
@@ -100,7 +100,7 @@ If `openspec status` reports an active change folder:
100
100
  3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
101
101
  4. Next command spelling on this runner: `/cc:openspec`
102
102
 
103
- Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
103
+ Run the CLI as `npx cc-codeconductor <same argv>`.
104
104
 
105
105
  ---
106
106
 
@@ -168,7 +168,7 @@ npx cc-codeconductor openspec verify <itemId>
168
168
  npx cc-codeconductor openspec archive <itemId>
169
169
  ```
170
170
 
171
- `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/`.
171
+ `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/`.
172
172
 
173
173
  ---
174
174
 
@@ -205,9 +205,9 @@ After each phase:
205
205
 
206
206
  Implementer: create a Git worktree before editing (`git worktree add ../<branch>-session <branch>`).
207
207
 
208
- Discover is read-only: `repo-explorer` never writes code. The implementer ticks
209
- `tasks.md` boxes (`- [ ]` → `- [x]`) as each FR lands — only `x`/`X` counts as
210
- done. If implementation reveals a design problem, pause and reconcile the
208
+ Discover is read-only: `repo-explorer` never writes code. `openspec done` ticks the boxes tagged
209
+ with that card and keeps your edits; the implementer ticks any other `tasks.md` box
210
+ it adds (`- [ ]` → `- [x]`) — only `x`/`X` counts as done. If implementation reveals a design problem, pause and reconcile the
211
211
  planning artifacts first (any direction: a later artifact may force revising an
212
212
  earlier one). Planning artifacts only in that step — never code — and confirm
213
213
  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**.
@@ -289,4 +289,4 @@ If the behavior requires additional test cases, start a new `/tdd-cycle` with
289
289
  the next scenario. One cycle = one behavior.
290
290
 
291
291
  Skill: `testing-tdd`. Evidence from the verification runner only — handmade TDD
292
- JSON is rejected. Optional gate: `bun run dev scorecard suite-run --suite workflow-gates`.
292
+ JSON is rejected. Optional gate: `npx cc-codeconductor scorecard suite-run --suite workflow-gates`.