bigpowers 2.91.1 → 2.93.0

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 (36) hide show
  1. package/.gemini/extensions/bigpowers/gemini-extension.json +1 -1
  2. package/.pi/package.json +1 -1
  3. package/AGENTS.md +98 -0
  4. package/CHANGELOG.md +14 -0
  5. package/CONVENTIONS.md +47 -427
  6. package/package.json +1 -1
  7. package/scripts/ab-sandbox.sh +3 -3
  8. package/scripts/adapters/agy.sh +1 -1
  9. package/scripts/adapters/cursor.sh +1 -1
  10. package/scripts/adapters/gemini.sh +1 -1
  11. package/scripts/adapters/mimo.sh +1 -1
  12. package/scripts/adapters/pi.sh +1 -1
  13. package/scripts/adapters/zcode.sh +1 -1
  14. package/scripts/generate-context-bundle.sh +2 -1
  15. package/scripts/lib/__pycache__/atomic_write.cpython-310.pyc +0 -0
  16. package/scripts/lib/__pycache__/link_utils.cpython-310.pyc +0 -0
  17. package/scripts/lib/__pycache__/srp_engine_links.cpython-310.pyc +0 -0
  18. package/scripts/lib/__pycache__/srp_engine_okf.cpython-310.pyc +0 -0
  19. package/scripts/lib/ab-eval.py +19 -5
  20. package/scripts/lib/ab_lean.py +116 -0
  21. package/scripts/lib/ab_metrics.py +8 -0
  22. package/scripts/lib/ab_progress.py +3 -1
  23. package/scripts/lib/ab_report.py +15 -4
  24. package/scripts/lib/ab_vsm.py +122 -0
  25. package/scripts/lib/ab_waste.py +173 -0
  26. package/scripts/test-adapter-render.sh +1 -1
  27. package/scripts/test-test-lock-hook.sh +7 -7
  28. package/scripts/verify-adversarial.sh +8 -1
  29. package/tests/test_ab_eval.py +0 -44
  30. package/tests/test_ab_lean.py +81 -0
  31. package/tests/test_ab_score.py +12 -2
  32. package/tests/test_ab_tasks.py +75 -0
  33. package/tests/test_ab_vsm.py +109 -0
  34. package/tests/test_ab_waste.py +106 -0
  35. package/CLAUDE.md +0 -400
  36. package/GEMINI.md +0 -75
package/.gemini/extensions/bigpowers/gemini-extension.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.91.1",
3
+ "version": "2.93.0",
4
4
  "description": "80 skills — 73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
5
5
  "keywords": [
6
6
  "gemini-extension"
package/.pi/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.91.1",
3
+ "version": "2.93.0",
4
4
  "description": "80 skills — 73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
5
5
  "keywords": [
6
6
  "pi-package"
package/AGENTS.md ADDED
@@ -0,0 +1,98 @@
1
+ # story: e38s08
2
+ # story: e51s05
3
+ # story: e45s22
4
+ # story: e45s23
5
+ # story: e55s03
6
+ # story: e84s01
7
+
8
+ # bigpowers — Agent Instructions
9
+
10
+ Read CONVENTIONS.md before any GitHub or git operation.
11
+ [`constitution.md`](constitution.md) synthesizes this project's doctrine (this file, CONVENTIONS.md, docs/PRINCIPLES.md, docs/references/*.md). This file remains fully authoritative.
12
+
13
+ <!-- BEGIN bigpowers:context-routing -->
14
+ ## Context Routing
15
+
16
+ Load subdirectory context by file glob — do not read the full doc tree up front.
17
+
18
+ | Glob / trigger | Load first | Fallback |
19
+ |----------------|------------|----------|
20
+ | `skills/**` | Active skill `SKILL.md` + sibling `REFERENCE.md` | `SKILL-INDEX.md` |
21
+ | `specs/epics/**` | Capsule `epic.yaml` + active story `-tasks.yaml` | `specs/release-plan.yaml` |
22
+ | `specs/product/**` | `SCOPE_LATEST.yaml`, `VISION_LATEST.yaml` | `specs/README.md` |
23
+ | `specs/tech-architecture/**` | `tech-stack.md` + epic `eNN-TEST_PLAN_LATEST.md` | `CONVENTIONS.md` |
24
+ | `scripts/**` | `CONVENTIONS.md` § Generated targets | Commands table below |
25
+ | `website/**` | `website/README.md` | Never edit generated docs in `website/src/content/docs/` |
26
+ | `docs/**` | Matching doc under `docs/` | `docs/references/` |
27
+ | Default / session start | This file → `CONVENTIONS.md` → `specs/state.yaml` | `survey-context` |
28
+ <!-- END bigpowers:context-routing -->
29
+
30
+ <!-- BEGIN bigpowers:learned-preferences -->
31
+ ## Learned User Preferences
32
+
33
+ - Prefer `rtk`-prefixed shell commands for git, test, and build output (token savings).
34
+ - Run Preflight before forward work; never dismiss red gates as pre-existing.
35
+ - Edit `skills/*/SKILL.md` sources only — never `.cursor/rules/` or `.gemini/` artifacts.
36
+
37
+ ## Workspace Facts
38
+
39
+ - Stack: Markdown / Bash documentation project; skills sync via `bash scripts/sync-skills.sh`.
40
+ - Planning SoT: `specs/state.yaml`, `specs/release-plan.yaml`, `specs/execution-status.yaml`.
41
+ - Story traceability: `# story: eNNsNN` tags in implementing files; `bash scripts/trace-stories.sh --strict` in CI.
42
+ - Rule matrix: `bash scripts/compile-rule-matrix.sh` → `specs/rule-matrix.json` (P0–P3 tiers from CONVENTIONS.md).
43
+ <!-- END bigpowers:learned-preferences -->
44
+
45
+ ## Project
46
+
47
+ bigpowers — agent skills for spec-driven, test-first software development by solo developers (catalog in `SKILL-INDEX.md`).
48
+ Stack: Markdown / Bash (documentation-based; skills integrate with Claude Code, Cursor, Gemini CLI)
49
+
50
+ ## Commands
51
+
52
+ | Action | Command |
53
+ |--------|---------|
54
+ | Install | `npm install -g bigpowers && bigpowers setup` |
55
+ | Run / Lint | `bash scripts/sync-skills.sh` |
56
+ | Test | `npm run compliance` |
57
+ | Build | `bash scripts/install.sh` (from source) |
58
+ | Validate specs YAML | `bash scripts/validate-specs-yaml.sh` |
59
+ | Compliance | `npm run compliance` |
60
+ | Verification Gates | `bash scripts/run-verification-gates.sh` |
61
+ | Traceability | `bash scripts/trace-stories.sh --strict` |
62
+ | Preflight | `npm run compliance && bash scripts/run-verification-gates.sh && bash scripts/sync-skills.sh && bash scripts/trace-stories.sh --strict` |
63
+ | CI | `gh pr checks` |
64
+
65
+ Pre-merge: `npm run compliance && bash scripts/run-verification-gates.sh`. If BCP Plus sized, see `docs/references/bcp-plus.md`.
66
+
67
+ ## Architecture & Conventions
68
+
69
+ - Collection of verb-noun skills under `skills/`, each with a single `SKILL.md` source of truth.
70
+ - Runtime specs in `specs/state.yaml`, `specs/release-plan.yaml`, and `specs/execution-status.yaml`; intent in `specs/product/`; epics in `specs/epics/`.
71
+ - Generated targets: `.cursor/rules/`, `.gemini/extensions/bigpowers/`, `.pi/skills/`, and `website/src/content/docs/`. Run `bash scripts/sync-skills.sh` after any changes.
72
+ - **Never** edit generated targets directly. Never create a skill without a `SKILL.md` file. Never push without running `sync-skills.sh`.
73
+
74
+ ## Token Management & Toolchain
75
+
76
+ - Context discipline: Write (short functions 4-20 lines), Select (`bts map`, `survey-context`), Compress (`sqz compress`, `rtk`), Isolate (`kickoff-branch`, `dispatch-agents`). See `docs/references/context-engineering.md`.
77
+ - Auto-Terse: Switch to `terse-mode` when session exceeds ~20 turns or context is heavy.
78
+ - Context compaction: Summarize state every 10 turns into a short, high-density note.
79
+ - Stream stability: Continuous output in chunks of ~200 lines without pausing.
80
+ - Mechanical backstop (e45s03): `scripts/hooks/token-mgmt-pre-tool-use.sh` blocks oversized tool calls.
81
+ - **Toolchain (bts, sqz, rtk):** Syntax tables, compression rules, MCP tools, and commands live in [docs/references/agent-tooling.md](docs/references/agent-tooling.md).
82
+ - Search: `bts find --print <pattern>` | Map: `bts map` | Docs: `bts docs <lib>`
83
+ - Compression: pipe through `sqz compress` (MCP: `sqz_read_file`, `sqz_grep`, `sqz_list_dir`)
84
+ - RTK: prefix commands with `rtk` (e.g. `rtk git status`, `rtk cargo test`, `rtk gh pr view`)
85
+
86
+ ## Session Start
87
+
88
+ Before any task, run this sequence — not optional:
89
+ 1. Read `CLAUDE.md` (or `AGENTS.md`)
90
+ 2. Read `CONVENTIONS.md`
91
+ 3. Read `specs/state.yaml` if it exists — current session and active epic
92
+ 4. Read `specs/release-plan.yaml` if it exists — active release context
93
+
94
+ ## Agent Rules
95
+
96
+ - **Workflow Mandate:** You MUST use the bigpowers skills (e.g., `plan-work`, `develop-tdd`, `craft-skill`) to perform tasks. DO NOT write code directly in response to a user prompt like "build this feature".
97
+ - **Always Green / fix-or-log:** Preflight and CI must be green before forward work. Any reproducible gate failure during unrelated work requires `quick-fix` or `fix-bug` (CONVENTIONS § Discovered Defects). Never dismiss failures as pre-existing or out of scope.
98
+ - Read specs/ and CONVENTIONS.md before writing code. Write minimum code that solves the stated problem. Run tests after every change. All written output in specs/.
package/CHANGELOG.md CHANGED
@@ -1,3 +1,17 @@
1
+ # [2.93.0](https://github.com/danielvm-git/bigpowers/compare/v2.92.0...v2.93.0) (2026-11-03)
2
+
3
+
4
+ ### Features
5
+
6
+ * **context:** shave always-loaded context in AGENTS.md and CONVENTIONS.md to <=150 lines (e84s01) ([#197](https://github.com/danielvm-git/bigpowers/issues/197)) ([34f6366](https://github.com/danielvm-git/bigpowers/commit/34f6366d481fc582e7d556148870298811a5d0ff))
7
+
8
+ # [2.92.0](https://github.com/danielvm-git/bigpowers/compare/v2.91.1...v2.92.0) (2026-11-03)
9
+
10
+
11
+ ### Features
12
+
13
+ * **benchmarks:** lean value-stream and waste metrics for the A/B eval, via pi in the Docker sandbox (e58s05–e58s11) ([#195](https://github.com/danielvm-git/bigpowers/issues/195)) ([11f5c8f](https://github.com/danielvm-git/bigpowers/commit/11f5c8f4b6407c67c4131620861345b49fce6193)), closes [#191](https://github.com/danielvm-git/bigpowers/issues/191)
14
+
1
15
  ## [2.91.1](https://github.com/danielvm-git/bigpowers/compare/v2.91.0...v2.91.1) (2026-11-03)
2
16
 
3
17