pactkit-auditlisted

# PactKit Audit H1-H7 AI Coding Harness readiness assessment. Scans project structure against a 7-layer model, produces a Harness Score (0-100), and identifies code hotspots. ## When Invoked - **Done Phase 8** (Harness Audit Refresh): Auto-invoked via `pactkit audit --append`. - **Standalone**: Ad-hoc project health assessment. - **Headless / Frontend integration**: Called as `/pactkit-audit` via Claude Code headless mode. ## The 7 Layers | Layer | Name | What It Checks | |-------|------|----------------| | H1 | Prompt Engineering | CLAUDE.md, rules, agents, commands | | H2 | Context Engineering | Specs, test cases, architecture graphs | | H3 | Process Governance | Sprint board, PDCA workflow artifacts | | H4 | Tool Governance | Skills, CLI tools, MCP integration | | H5 | Safety & Guardrails | Pre-commit hooks, security rules, credential guards | | H6 | Observability | Logging, cost tracking, lessons, self-audit rules | | H7 | Evolution | Version management, changelog, CI/CD publish | ## Scoring - Each layer scores **L0-L3** (None → Basic → Structured → Advanced). - **Harness Score** = sum(all 7 levels) / 21 × 100. - **AI Ready** = min(all 7 levels) ≥ L1. ## Protocol ### 1. Run Audit ```bash pactkit audit ``` - Outputs: scorecard + top hotspots (concise by default). - Output file: `docs/architecture/governance/harness_audit.json`. ### 2. Options | Flag | Purpose | |------|---------| | `--json` | JSON output only (machine-readable) | | `--layer H1-H7` | Check a single