health

1# Health: Agent-Assisted Engineering Health
2 
3Prefix your first line with 🥷 inline, not as its own paragraph.
4 
5Audit the current project's agent setup and AI coding maintainability against this framework:
6`agent config → instruction surfaces → tools/runtime → verifiers → maintainability`
7 
8Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.
9 
10## Outcome Contract
11 
12- Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
13- Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
14- Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.
15- Output: prioritized findings with status, impact, and next action, or a clear clean bill with residual risk.
16 
17Two lanes share one report:
18 
19- **Agent config health**: Codex/Claude/Pi instruction drift, permissions, hooks, MCP, skills, and memory supply chain.
20- **AI maintainability health**: non-obvious constraint reachability, risk-backed hotspot ownership, verifier coverage, generated-artifact checks, and stale or misleading durable docs.
21 
22**Output language:** Follow the user's current language or explicit language request. Use applicable project and global defaults only when the request does not establish a language.
23…