bigpowers 2.15.0 → 2.16.0

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 (11) hide show
  1. package/.pi/package.json +1 -1
  2. package/.pi/prompts/assess-impact.md +14 -0
  3. package/.pi/prompts/build-epic.md +2 -1
  4. package/.pi/skills/assess-impact/SKILL.md +14 -0
  5. package/.pi/skills/build-epic/SKILL.md +2 -1
  6. package/CHANGELOG.md +7 -0
  7. package/SKILL-INDEX.md +1 -1
  8. package/assess-impact/SKILL.md +14 -0
  9. package/build-epic/SKILL.md +2 -1
  10. package/package.json +1 -1
  11. package/skills-lock.json +2 -2
package/.pi/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.15.0",
3
+ "version": "2.16.0",
4
4
  "description": "67 skills — 61 agent skills for spec-driven, test-first software development by solo developers",
5
5
  "keywords": [
6
6
  "pi-package"
package/.pi/prompts/assess-impact.md CHANGED
@@ -9,6 +9,11 @@ description: Analyze the blast radius of a proposed change before any code is wr
9
9
 
10
10
  Find the blast radius of the proposed change before a single line is written.
11
11
 
12
+ ## Modes
13
+
14
+ - Default: full impact analysis (dependents + affected stories + test coverage mapping)
15
+ - --lightweight: Fast fan-in/fan-out only (<10s). Maps callers and imports without test coverage mapping. Used by build-epic step 2 as a pre-plan gate. Risk score > 7 triggers a mandatory grill-me session before proceeding.
16
+
12
17
  ## Process
13
18
 
14
19
  ### 1. Identify the target
@@ -74,3 +79,12 @@ grep -rn "[symbol-name]" . --include="*.test.*" --include="*.spec.*"
74
79
  → verify: `grep "Risk:" specs/IMPACT.md`
75
80
 
76
81
  Suggest `plan-work` once risk is understood and any test gaps are noted.
82
+
83
+ ## Risk score gating
84
+
85
+ In `--lightweight` mode (used by build-epic step 2), assign a numeric risk score (1–10):
86
+ - Fan-in (how many callers): 0–4 points
87
+ - Fan-out (how many dependencies the module itself uses): 0–3 points
88
+ - Recent churn (git log --oneline -5 count): 0–3 points
89
+
90
+ **Risk score > 7**: Gate — require a `grill-me` session before proceeding to implementation. Document the grill-me result in the impact report at `specs/IMPACT-<epic>-<story>.md`.
package/.pi/prompts/build-epic.md CHANGED
@@ -29,7 +29,8 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
29
29
  ## Process
30
30
 
31
31
  1. Read `specs/state.yaml`, `specs/execution-status.yaml`, `specs/release-plan.yaml`, active `specs/epics/eNN-slug/epic.yaml`.
32
- 2. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
32
+ 2. **Assess Impact (Step 2):** Before writing tasks, run `assess-impact --lightweight` on the proposed change. If the risk score exceeds 7, gate — require a `grill-me` session. Write the impact report to `specs/IMPACT-<epic>-<story>.md`. For net-new code with no existing dependents, skip.
33
+ 3. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
33
34
  3. If `epic_cycle.step` missing, set to `1`.
34
35
  4. Run **only the current step** (resume mode) unless user asked for full auto-run.
35
36
  5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
package/.pi/skills/assess-impact/SKILL.md CHANGED
@@ -11,6 +11,11 @@ model: sonnet
11
11
 
12
12
  Find the blast radius of the proposed change before a single line is written.
13
13
 
14
+ ## Modes
15
+
16
+ - Default: full impact analysis (dependents + affected stories + test coverage mapping)
17
+ - --lightweight: Fast fan-in/fan-out only (<10s). Maps callers and imports without test coverage mapping. Used by build-epic step 2 as a pre-plan gate. Risk score > 7 triggers a mandatory grill-me session before proceeding.
18
+
14
19
  ## Process
15
20
 
16
21
  ### 1. Identify the target
@@ -76,3 +81,12 @@ grep -rn "[symbol-name]" . --include="*.test.*" --include="*.spec.*"
76
81
  → verify: `grep "Risk:" specs/IMPACT.md`
77
82
 
78
83
  Suggest `plan-work` once risk is understood and any test gaps are noted.
84
+
85
+ ## Risk score gating
86
+
87
+ In `--lightweight` mode (used by build-epic step 2), assign a numeric risk score (1–10):
88
+ - Fan-in (how many callers): 0–4 points
89
+ - Fan-out (how many dependencies the module itself uses): 0–3 points
90
+ - Recent churn (git log --oneline -5 count): 0–3 points
91
+
92
+ **Risk score > 7**: Gate — require a `grill-me` session before proceeding to implementation. Document the grill-me result in the impact report at `specs/IMPACT-<epic>-<story>.md`.
package/.pi/skills/build-epic/SKILL.md CHANGED
@@ -31,7 +31,8 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
31
31
  ## Process
32
32
 
33
33
  1. Read `specs/state.yaml`, `specs/execution-status.yaml`, `specs/release-plan.yaml`, active `specs/epics/eNN-slug/epic.yaml`.
34
- 2. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
34
+ 2. **Assess Impact (Step 2):** Before writing tasks, run `assess-impact --lightweight` on the proposed change. If the risk score exceeds 7, gate — require a `grill-me` session. Write the impact report to `specs/IMPACT-<epic>-<story>.md`. For net-new code with no existing dependents, skip.
35
+ 3. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
35
36
  3. If `epic_cycle.step` missing, set to `1`.
36
37
  4. Run **only the current step** (resume mode) unless user asked for full auto-run.
37
38
  5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
package/CHANGELOG.md CHANGED
@@ -1,3 +1,10 @@
1
+ # [2.16.0](https://github.com/danielvm-git/bigpowers/compare/v2.15.0...v2.16.0) (2026-06-21)
2
+
3
+
4
+ ### Features
5
+
6
+ * **e18s03:** assess-impact --lightweight in build-epic step 2 ([eff1b3a](https://github.com/danielvm-git/bigpowers/commit/eff1b3a3dfa7677db8c525d6424147c08a9b4809))
7
+
1
8
  # [2.15.0](https://github.com/danielvm-git/bigpowers/compare/v2.14.0...v2.15.0) (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:** 2026-06-21T21:31:53Z
6
+ **Generated:** 2026-06-21T21:40:39Z
7
7
  **Skills:** 67
8
8
 
9
9
  ---
package/assess-impact/SKILL.md CHANGED
@@ -10,6 +10,11 @@ description: Analyze the blast radius of a proposed change before any code is wr
10
10
 
11
11
  Find the blast radius of the proposed change before a single line is written.
12
12
 
13
+ ## Modes
14
+
15
+ - Default: full impact analysis (dependents + affected stories + test coverage mapping)
16
+ - --lightweight: Fast fan-in/fan-out only (<10s). Maps callers and imports without test coverage mapping. Used by build-epic step 2 as a pre-plan gate. Risk score > 7 triggers a mandatory grill-me session before proceeding.
17
+
13
18
  ## Process
14
19
 
15
20
  ### 1. Identify the target
@@ -75,3 +80,12 @@ grep -rn "[symbol-name]" . --include="*.test.*" --include="*.spec.*"
75
80
  → verify: `grep "Risk:" specs/IMPACT.md`
76
81
 
77
82
  Suggest `plan-work` once risk is understood and any test gaps are noted.
83
+
84
+ ## Risk score gating
85
+
86
+ In `--lightweight` mode (used by build-epic step 2), assign a numeric risk score (1–10):
87
+ - Fan-in (how many callers): 0–4 points
88
+ - Fan-out (how many dependencies the module itself uses): 0–3 points
89
+ - Recent churn (git log --oneline -5 count): 0–3 points
90
+
91
+ **Risk score > 7**: Gate — require a `grill-me` session before proceeding to implementation. Document the grill-me result in the impact report at `specs/IMPACT-<epic>-<story>.md`.
package/build-epic/SKILL.md CHANGED
@@ -30,7 +30,8 @@ Orchestrates the **build** flow for a single epic: survey → plan tasks → kic
30
30
  ## Process
31
31
 
32
32
  1. Read `specs/state.yaml`, `specs/execution-status.yaml`, `specs/release-plan.yaml`, active `specs/epics/eNN-slug/epic.yaml`.
33
- 2. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
33
+ 2. **Assess Impact (Step 2):** Before writing tasks, run `assess-impact --lightweight` on the proposed change. If the risk score exceeds 7, gate — require a `grill-me` session. Write the impact report to `specs/IMPACT-<epic>-<story>.md`. For net-new code with no existing dependents, skip.
34
+ 3. **BCP Tracking (Step 2):** After `plan-work` completes, read the `bcps:` count (Business Complexity Points story size) from the epic capsule and carry it into `state.yaml` as `epic_cycle.story_bcps = N`.
34
35
  3. If `epic_cycle.step` missing, set to `1`.
35
36
  4. Run **only the current step** (resume mode) unless user asked for full auto-run.
36
37
  5. After step verify passes, increment `epic_cycle.step` in `state.yaml` (or `bash scripts/bp-yaml-set.sh` if available).
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.15.0",
3
+ "version": "2.16.0",
4
4
  "description": "61 agent skills for spec-driven, test-first software development by solo developers",
5
5
  "main": "index.js",
6
6
  "scripts": {
package/skills-lock.json CHANGED
@@ -8,7 +8,7 @@
8
8
  },
9
9
  "assess-impact": {
10
10
  "description": "Analyze the blast radius of a proposed change before any code is written. Maps dependents, affected stories, and test coverage. Produces specs/IMPACT.md. Use before plan-work on any non-trivial change, when touching a shared module, or when the user asks \"what does this break?\".",
11
- "sha256": "cad0c4534f31a207",
11
+ "sha256": "740925970c6cf9ce",
12
12
  "path": "assess-impact/SKILL.md"
13
13
  },
14
14
  "audit-code": {
@@ -18,7 +18,7 @@
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": "d33ba1c86463d91f",
21
+ "sha256": "3c1707cca32b24de",
22
22
  "path": "build-epic/SKILL.md"
23
23
  },
24
24
  "change-request": {