bigpowers 2.13.0 → 2.14.0
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.
- package/.pi/package.json +1 -1
- package/.pi/prompts/audit-code.md +14 -0
- package/.pi/prompts/build-epic.md +10 -1
- package/.pi/skills/audit-code/SKILL.md +14 -0
- package/.pi/skills/build-epic/SKILL.md +10 -1
- package/CHANGELOG.md +7 -0
- package/SKILL-INDEX.md +1 -1
- package/audit-code/SKILL.md +14 -0
- package/build-epic/SKILL.md +10 -1
- package/package.json +1 -1
- package/skills-lock.json +2 -2
package/.pi/package.json
CHANGED
|
@@ -15,6 +15,7 @@ Run this self-review before asking anyone else to look at the code. The goal is
|
|
|
15
15
|
|
|
16
16
|
- Default: full checklist
|
|
17
17
|
- --quick: Run only Supply Chain and Test Coverage. Use for changes under 50 LOC.
|
|
18
|
+
- --gate: Non-interactive mode for automated CI gating (used by build-epic step 6). Exit with non-zero status code (`exit 1`) on ANY checklist failure; `exit 0` only if ALL items pass. Produces a compact pass/fail summary to stderr. On failure, list every ✗ item with reason.
|
|
18
19
|
|
|
19
20
|
## Checklist
|
|
20
21
|
|
|
@@ -104,6 +105,19 @@ Report the checklist with ✓ / ✗ per item. For each ✗, describe what needs
|
|
|
104
105
|
If all items pass: suggest running `request-review` for an independent second opinion.
|
|
105
106
|
If any items fail: fix them before proceeding.
|
|
106
107
|
|
|
108
|
+
### Gate mode output (`--gate`)
|
|
109
|
+
|
|
110
|
+
In `--gate` mode, print one summary line per checklist section:
|
|
111
|
+
|
|
112
|
+
```
|
|
113
|
+
PASS Supply Chain & Security
|
|
114
|
+
FAIL Provenance & Metadata (2 items)
|
|
115
|
+
PASS Law of Demeter
|
|
116
|
+
...
|
|
117
|
+
```
|
|
118
|
+
|
|
119
|
+
Aggregate exit code: `0` if all sections PASS, `1` (non-zero) if any section FAILs. Write the full audit report to `specs/verifications/AUDIT-<epic>-<story>.md` as a permanent record.
|
|
120
|
+
|
|
107
121
|
## Handoff
|
|
108
122
|
|
|
109
123
|
Gate: READY -> next: commit-message
|
|
@@ -22,7 +22,7 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
22
22
|
| 3 | `kickoff-branch` — feature branch + clean baseline |
|
|
23
23
|
| 4 | `develop-tdd` — red-green per task |
|
|
24
24
|
| 5 | `verify-work` — UAT + mechanical gates |
|
|
25
|
-
| 6 | `audit-code` —
|
|
25
|
+
| 6 | `audit-code` — **non-optional gate** (pass/fail; fail → loop back to step 4) |
|
|
26
26
|
| 7 | `commit-message` — Conventional Commits draft |
|
|
27
27
|
| 8 | `release-branch` — PR or solo land |
|
|
28
28
|
|
|
@@ -35,6 +35,15 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
35
35
|
5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
|
|
36
36
|
6. On story complete, set `execution-status.yaml` story key to `done`; run `bash scripts/sync-status-from-epics.sh`.
|
|
37
37
|
|
|
38
|
+
### Step 6 — audit-code gate (non-optional)
|
|
39
|
+
|
|
40
|
+
After step 5 (verify-work) completes successfully, step 6 runs `audit-code` automatically in `--gate` mode:
|
|
41
|
+
|
|
42
|
+
1. **Run audit:** Invoke `audit-code --gate` on the complete diff for this story.
|
|
43
|
+
2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
|
|
44
|
+
3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
|
|
45
|
+
4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
|
|
46
|
+
|
|
38
47
|
## Handoff
|
|
39
48
|
|
|
40
49
|
Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mid-epic.
|
|
@@ -17,6 +17,7 @@ Run this self-review before asking anyone else to look at the code. The goal is
|
|
|
17
17
|
|
|
18
18
|
- Default: full checklist
|
|
19
19
|
- --quick: Run only Supply Chain and Test Coverage. Use for changes under 50 LOC.
|
|
20
|
+
- --gate: Non-interactive mode for automated CI gating (used by build-epic step 6). Exit with non-zero status code (`exit 1`) on ANY checklist failure; `exit 0` only if ALL items pass. Produces a compact pass/fail summary to stderr. On failure, list every ✗ item with reason.
|
|
20
21
|
|
|
21
22
|
## Checklist
|
|
22
23
|
|
|
@@ -106,6 +107,19 @@ Report the checklist with ✓ / ✗ per item. For each ✗, describe what needs
|
|
|
106
107
|
If all items pass: suggest running `request-review` for an independent second opinion.
|
|
107
108
|
If any items fail: fix them before proceeding.
|
|
108
109
|
|
|
110
|
+
### Gate mode output (`--gate`)
|
|
111
|
+
|
|
112
|
+
In `--gate` mode, print one summary line per checklist section:
|
|
113
|
+
|
|
114
|
+
```
|
|
115
|
+
PASS Supply Chain & Security
|
|
116
|
+
FAIL Provenance & Metadata (2 items)
|
|
117
|
+
PASS Law of Demeter
|
|
118
|
+
...
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
Aggregate exit code: `0` if all sections PASS, `1` (non-zero) if any section FAILs. Write the full audit report to `specs/verifications/AUDIT-<epic>-<story>.md` as a permanent record.
|
|
122
|
+
|
|
109
123
|
## Handoff
|
|
110
124
|
|
|
111
125
|
Gate: READY -> next: commit-message
|
|
@@ -24,7 +24,7 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
24
24
|
| 3 | `kickoff-branch` — feature branch + clean baseline |
|
|
25
25
|
| 4 | `develop-tdd` — red-green per task |
|
|
26
26
|
| 5 | `verify-work` — UAT + mechanical gates |
|
|
27
|
-
| 6 | `audit-code` —
|
|
27
|
+
| 6 | `audit-code` — **non-optional gate** (pass/fail; fail → loop back to step 4) |
|
|
28
28
|
| 7 | `commit-message` — Conventional Commits draft |
|
|
29
29
|
| 8 | `release-branch` — PR or solo land |
|
|
30
30
|
|
|
@@ -37,6 +37,15 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
37
37
|
5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
|
|
38
38
|
6. On story complete, set `execution-status.yaml` story key to `done`; run `bash scripts/sync-status-from-epics.sh`.
|
|
39
39
|
|
|
40
|
+
### Step 6 — audit-code gate (non-optional)
|
|
41
|
+
|
|
42
|
+
After step 5 (verify-work) completes successfully, step 6 runs `audit-code` automatically in `--gate` mode:
|
|
43
|
+
|
|
44
|
+
1. **Run audit:** Invoke `audit-code --gate` on the complete diff for this story.
|
|
45
|
+
2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
|
|
46
|
+
3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
|
|
47
|
+
4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
|
|
48
|
+
|
|
40
49
|
## Handoff
|
|
41
50
|
|
|
42
51
|
Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mid-epic.
|
package/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
1
|
+
# [2.14.0](https://github.com/danielvm-git/bigpowers/compare/v2.13.0...v2.14.0) (2026-06-21)
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
### Features
|
|
5
|
+
|
|
6
|
+
* **e18s01:** audit-code as non-optional gate in build-epic step 6 ([48f08de](https://github.com/danielvm-git/bigpowers/commit/48f08de62952827966ace0ac9149cea882fa0ca5))
|
|
7
|
+
|
|
1
8
|
# [2.13.0](https://github.com/danielvm-git/bigpowers/compare/v2.12.1...v2.13.0) (2026-06-21)
|
|
2
9
|
|
|
3
10
|
|
package/SKILL-INDEX.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
> **DO NOT EDIT** — This file is auto-generated by `scripts/generate-skill-index.sh`.
|
|
4
4
|
> Edit `SKILL.md` source files or `skills-lock.json` instead. Run `bash scripts/sync-skills.sh` to regenerate.
|
|
5
5
|
|
|
6
|
-
**Generated:** 2026-06-
|
|
6
|
+
**Generated:** 2026-06-21T21:27:17Z
|
|
7
7
|
**Skills:** 67
|
|
8
8
|
|
|
9
9
|
---
|
package/audit-code/SKILL.md
CHANGED
|
@@ -16,6 +16,7 @@ Run this self-review before asking anyone else to look at the code. The goal is
|
|
|
16
16
|
|
|
17
17
|
- Default: full checklist
|
|
18
18
|
- --quick: Run only Supply Chain and Test Coverage. Use for changes under 50 LOC.
|
|
19
|
+
- --gate: Non-interactive mode for automated CI gating (used by build-epic step 6). Exit with non-zero status code (`exit 1`) on ANY checklist failure; `exit 0` only if ALL items pass. Produces a compact pass/fail summary to stderr. On failure, list every ✗ item with reason.
|
|
19
20
|
|
|
20
21
|
## Checklist
|
|
21
22
|
|
|
@@ -105,6 +106,19 @@ Report the checklist with ✓ / ✗ per item. For each ✗, describe what needs
|
|
|
105
106
|
If all items pass: suggest running `request-review` for an independent second opinion.
|
|
106
107
|
If any items fail: fix them before proceeding.
|
|
107
108
|
|
|
109
|
+
### Gate mode output (`--gate`)
|
|
110
|
+
|
|
111
|
+
In `--gate` mode, print one summary line per checklist section:
|
|
112
|
+
|
|
113
|
+
```
|
|
114
|
+
PASS Supply Chain & Security
|
|
115
|
+
FAIL Provenance & Metadata (2 items)
|
|
116
|
+
PASS Law of Demeter
|
|
117
|
+
...
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
Aggregate exit code: `0` if all sections PASS, `1` (non-zero) if any section FAILs. Write the full audit report to `specs/verifications/AUDIT-<epic>-<story>.md` as a permanent record.
|
|
121
|
+
|
|
108
122
|
## Handoff
|
|
109
123
|
|
|
110
124
|
Gate: READY -> next: commit-message
|
package/build-epic/SKILL.md
CHANGED
|
@@ -23,7 +23,7 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
23
23
|
| 3 | `kickoff-branch` — feature branch + clean baseline |
|
|
24
24
|
| 4 | `develop-tdd` — red-green per task |
|
|
25
25
|
| 5 | `verify-work` — UAT + mechanical gates |
|
|
26
|
-
| 6 | `audit-code` —
|
|
26
|
+
| 6 | `audit-code` — **non-optional gate** (pass/fail; fail → loop back to step 4) |
|
|
27
27
|
| 7 | `commit-message` — Conventional Commits draft |
|
|
28
28
|
| 8 | `release-branch` — PR or solo land |
|
|
29
29
|
|
|
@@ -36,6 +36,15 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
|
|
|
36
36
|
5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
|
|
37
37
|
6. On story complete, set `execution-status.yaml` story key to `done`; run `bash scripts/sync-status-from-epics.sh`.
|
|
38
38
|
|
|
39
|
+
### Step 6 — audit-code gate (non-optional)
|
|
40
|
+
|
|
41
|
+
After step 5 (verify-work) completes successfully, step 6 runs `audit-code` automatically in `--gate` mode:
|
|
42
|
+
|
|
43
|
+
1. **Run audit:** Invoke `audit-code --gate` on the complete diff for this story.
|
|
44
|
+
2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
|
|
45
|
+
3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
|
|
46
|
+
4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
|
|
47
|
+
|
|
39
48
|
## Handoff
|
|
40
49
|
|
|
41
50
|
Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mid-epic.
|
package/package.json
CHANGED
package/skills-lock.json
CHANGED
|
@@ -13,12 +13,12 @@
|
|
|
13
13
|
},
|
|
14
14
|
"audit-code": {
|
|
15
15
|
"description": "Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produces a pass/fail checklist. Use before request-review, before committing, or when user asks for a code quality check.",
|
|
16
|
-
"sha256": "
|
|
16
|
+
"sha256": "8192ebe6f66a9f91",
|
|
17
17
|
"path": "audit-code/SKILL.md"
|
|
18
18
|
},
|
|
19
19
|
"build-epic": {
|
|
20
20
|
"description": "Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of ad-hoc execute-plan for release work.",
|
|
21
|
-
"sha256": "
|
|
21
|
+
"sha256": "ac7c8fc9740c4beb",
|
|
22
22
|
"path": "build-epic/SKILL.md"
|
|
23
23
|
},
|
|
24
24
|
"change-request": {
|