Stack doctor

Skill drmahdikazempour/agent-stack/skills/stack-doctor

One command to make any repo token-efficient for Claude Code & Cursor. Built-in code map, output compression, skills & hooks, savings measured with ccusage.

Install

npx -y skills add drmahdikazempour/agent-stack --skill stack-doctor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Lint the agent-stack setup — CLAUDE.md token budget (≤800), each SKILL.md description (≤1024 chars) and body (≤500 lines), hook conflicts in settings.json, frontmatter validity, and adapter availability. Use when something feels off, before committing config changes, or to confirm a healthy setup. Wraps `agent-stack doctor`; exit code 1 means there are issues to fix.

SKILL.md

1.3 KB, as published. Nobody here has run it

stack-doctor

Lint the optimization layer and report problems with exact files and limits.

Checks performed

CLAUDE.md ≤ 800 tokens (startup-load budget).
Each SKILL.md description ≤ 1024 chars (Agent Skills hard limit).
Each SKILL.md body ≤ 500 lines.
Combined skill metadata ≤ 500 tokens.
Zero hook conflicts in .claude/settings.json.
Valid frontmatter (name + description) on every skill.
Every adapter binary callable, or clearly flagged as config-only.

What to do

Run npx @drmahdikazempour/agent-stack doctor.
If it exits non-zero, surface each failure with the file and the limit it broke.
For auto-fixable issues (e.g. CLAUDE.md over budget), offer npx @drmahdikazempour/agent-stack optimize.
For hook conflicts, never hand-edit settings.json — re-run init/profile use so the merger reconciles them.