Health

Runs a tiered audit of your Claude Code setup when instructions stop working, MCP tools fail, or AI-generated code becomes hard to maintain. Checks agent config layers (AGENTS.md, config.toml, runtime files), verifier commands, hooks, and maintainability signals like hotspot ownership and wrapper patterns. Summary mode is cheap and fast. Deep mode spawns three inspector subagents for context, control, and code rot analysis, which burns tokens but catches instruction drift and missing verification surfaces. Flags findings by severity with copy-paste fixes. Good for debugging why Claude ignores your rules or when you suspect your setup has drifted. The multilingual trigger keywords and budget escalation logic show this was built by someone tired of configs quietly rotting.

skills.sh installs: 2.6K
GitHub stars: 6.4K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add tw93/claude-health --skill health --agent claude-code

Installs into .claude/skills of the current project.

Files

Health: Agent-Assisted Engineering Health

Prefix your first line with 🥷 inline, not as its own paragraph.

Audit the current project's agent setup and AI coding maintainability against this framework: agent config → instruction surfaces → tools/runtime → verifiers → maintainability

Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.

Outcome Contract

Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.
Output: prioritized findings with status, impact, and next action, or a clear clean bill with residual risk.

Two lanes share one report:

SKILL.md on GitHub

Details

Repository: github.com/tw93/claude-health