@event4u/agent-config 9.3.0 → 9.4.0

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 (72) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/CHANGELOG.md +78 -0
  3. package/CONTRIBUTING.md +14 -0
  4. package/README.md +12 -4
  5. package/dist/agent-src/commands/contribution-precheck.md +100 -0
  6. package/dist/agent-src/commands/team.md +4 -0
  7. package/dist/agent-src/contexts/model-recommendations.md +6 -0
  8. package/dist/agent-src/rules/token-efficiency.md +7 -0
  9. package/dist/agent-src/skills/adversarial-review/SKILL.md +5 -0
  10. package/dist/agent-src/skills/ai-council/SKILL.md +3 -0
  11. package/dist/agent-src/skills/build-buy-partner/SKILL.md +1 -0
  12. package/dist/agent-src/skills/decision-record/SKILL.md +35 -1
  13. package/dist/agent-src/skills/decision-record/evals/triggers.json +82 -12
  14. package/dist/agent-src/skills/decision-record/references/weighted-matrix.md +119 -0
  15. package/dist/agent-src/skills/evaluate-llm-feature/SKILL.md +142 -0
  16. package/dist/agent-src/skills/judge-synthesis/SKILL.md +1 -0
  17. package/dist/agent-src/skills/learning-tutor/SKILL.md +215 -0
  18. package/dist/agent-src/skills/rice-prioritization/SKILL.md +1 -0
  19. package/dist/agent-src/skills/stakeholder-tradeoff/SKILL.md +3 -1
  20. package/dist/agent-src/skills/subagent-orchestration/SKILL.md +2 -1
  21. package/dist/agent-src/templates/agents/agent-project-settings.example.yml +1 -1
  22. package/dist/discovery/deprecation-report.md +1 -1
  23. package/dist/discovery/discovery-manifest.json +94 -24
  24. package/dist/discovery/discovery-manifest.json.sha256 +1 -1
  25. package/dist/discovery/discovery-manifest.summary.md +4 -4
  26. package/dist/discovery/orphan-report.md +1 -1
  27. package/dist/discovery/packs.json +13 -10
  28. package/dist/discovery/trust-report.md +3 -3
  29. package/dist/discovery/workspaces.json +9 -6
  30. package/dist/mcp/registry-manifest.json +3 -3
  31. package/docs/CLAIMS.md +16 -2
  32. package/docs/announcements/2026-07-honest-cost-sweep-launch.md +84 -0
  33. package/docs/anti-reskin-gate.md +60 -0
  34. package/docs/architecture.md +2 -2
  35. package/docs/catalog.md +303 -278
  36. package/docs/command-flows.md +2 -1
  37. package/docs/comparison.yaml +10 -0
  38. package/docs/contracts/adoption-signal-floor.md +17 -0
  39. package/docs/contracts/ai-council-config.md +25 -0
  40. package/docs/contracts/mcp-tool-inventory.md +25 -22
  41. package/docs/contracts/tier-3-contrib-plugin.md +12 -4
  42. package/docs/featured-skills.md +2 -2
  43. package/docs/getting-started-by-role.md +1 -1
  44. package/docs/getting-started.md +1 -1
  45. package/docs/governance-advantage.md +1 -1
  46. package/docs/proof.md +10 -6
  47. package/docs/self-review-gate.md +14 -0
  48. package/docs/setup/per-ide/antigravity.md +8 -3
  49. package/docs/us-vs-the-category.md +38 -0
  50. package/docs/wedge/production-validator/README.md +24 -0
  51. package/docs/wedge/production-validator/first-run-check.sh +42 -0
  52. package/package.json +1 -1
  53. package/src/scripts/_lib/catalog_score.ts +64 -0
  54. package/src/scripts/_lib/shingle_similarity.ts +146 -0
  55. package/src/scripts/ai_council/clients.ts +50 -1
  56. package/src/scripts/ai_council/config.ts +28 -3
  57. package/src/scripts/ai_council/low_impact.ts +16 -0
  58. package/src/scripts/ai_council/necessity.ts +11 -0
  59. package/src/scripts/ai_council/orchestrator.ts +78 -26
  60. package/src/scripts/ai_council/pricing.ts +59 -0
  61. package/src/scripts/ai_council/stance_tally.ts +42 -5
  62. package/src/scripts/build_catalog_index.ts +188 -0
  63. package/src/scripts/council_cli.ts +56 -1
  64. package/src/scripts/generate_index.ts +6 -3
  65. package/src/scripts/lint_originality.ts +464 -0
  66. package/src/scripts/mcp_server/catalog_tools.ts +114 -0
  67. package/src/scripts/mcp_server/consumer_tool_catalog.json +46 -0
  68. package/src/scripts/schemas/flow.schema.json +17 -0
  69. package/src/scripts/schemas/skill.schema.json +166 -32
  70. package/src/scripts/self_review_gate.test.ts +48 -0
  71. package/src/scripts/self_review_gate.ts +73 -5
  72. package/src/scripts/validate_flow_teams.ts +127 -0
@@ -0,0 +1,60 @@
1
+ # Anti-reskin gate for your skills repo
2
+
3
+ If you maintain a catalog of AI-agent skills and accept community PRs, your
4
+ failure mode is the **find-replace re-skin**: an existing skill resubmitted
5
+ with "Laravel" → "Symfony", "Vietnam" → "Korea", new name, same substance.
6
+ Keyword-cosine and token-Jaccard checks miss it; manual review does not scale
7
+ past a handful of PRs per month.
8
+
9
+ This package ships the gate that catches it: `lint_originality` — an
10
+ entity-neutralized shingle-overlap linter. Framework / vendor / region proper
11
+ nouns are neutralized before comparing 8-word shingles, so the swap does not
12
+ move the score: a re-skin scores ~100 % overlap while the worst legitimate
13
+ pair in a 496-artifact corpus scores 40 %. Class templates and
14
+ document-frequency boilerplate are subtracted, so shared scaffolding never
15
+ scores. The `--changed` mode is batch-masking-hardened: a batch of
16
+ near-identical submissions cannot classify its own shared shingles as
17
+ boilerplate (regression-locked in `tests/scripts/lint_originality.test.ts`).
18
+
19
+ It runs as a blocking PR gate on this repo (`originality-gate` job in
20
+ [`.github/workflows/skill-lint.yml`](../.github/workflows/skill-lint.yml)).
21
+
22
+ ## Run it on your own catalog — today
23
+
24
+ The tool is not yet a standalone package; it runs from a clone. The corpus
25
+ roots are fixed (`src/skills/*/SKILL.md`), so you stage your skills into one:
26
+
27
+ ```bash
28
+ git clone --depth 1 https://github.com/event4u-app/agent-config
29
+ cd agent-config && npm ci
30
+
31
+ # Stage your catalog into the skills corpus root (one dir per skill):
32
+ for f in /path/to/your-repo/skills/*/SKILL.md; do
33
+ d="src/skills/ext-$(basename "$(dirname "$f")")"
34
+ mkdir -p "$d" && cp "$f" "$d/SKILL.md"
35
+ done
36
+
37
+ # Compare your skills against each other (and this corpus) in one pass:
38
+ ./scripts-run src/scripts/lint_originality --changed src/skills/ext-*/SKILL.md
39
+ ```
40
+
41
+ Exit `1` with an offending pair + overlap % means a re-skin; exit `0` means no
42
+ same-class pair exceeds the 40 % warn floor. Thresholds are env-overridable
43
+ (`ORIGINALITY_FAIL`, `ORIGINALITY_WARN`).
44
+
45
+ ## Want this as a zero-config `npx` tool?
46
+
47
+ We will extract `lint_originality` as a standalone zero-config package
48
+ (`--changed` mode for PR CI, no repo coupling, regression suite included) **if
49
+ there is real demand** — the bet is settled by a measured floor, not opinion:
50
+
51
+ - **Signal:** open an issue on this repo titled `anti-reskin gate: standalone
52
+ request` (or reference `lint_originality` in an issue/PR about your own
53
+ catalog).
54
+ - **Floor:** ≥ 3 distinct external maintainers signal within 90 days of this
55
+ page landing on `main` → we ship the extraction.
56
+ - **Kill criterion:** floor missed → extraction is cancelled and recorded;
57
+ this page stays as the run-from-clone recipe.
58
+
59
+ Contract: [`docs/contracts/adoption-signal-floor.md` § Extraction demand
60
+ gate](contracts/adoption-signal-floor.md#extraction-demand-gate--lint_originality-standalone-probe).
@@ -146,9 +146,9 @@ note, package-internal path-swap, description budget, and the
146
146
 
147
147
  | Layer | Count | Purpose |
148
148
  |---|---|---|
149
- | **Skills** | 276 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
149
+ | **Skills** | 278 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
150
150
  | **Rules** | 105 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
151
- | **Commands** | 189 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/condense`, … |
151
+ | **Commands** | 190 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/condense`, … |
152
152
  | **Guidelines** | 101 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
153
153
  | **Templates** | 7 | Scaffolds for features, roadmaps, contexts, skills, overrides |
154
154
  | **Contexts** | 5 | Shared knowledge about the system itself |