lelandg

Repo Doctor — Security skill for Claude Code

Security community

Audit a repo's agent docs — AGENTS.md/CLAUDE.md topology, always-loaded token cost, CodeMap freshness and line-number accuracy, broken pointers, changelog drift.

How to install Repo Doctor

Installs to ~/.claude/commands/lelandg-.claude_code-repo-doctor.md

Terminal
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/lelandg/.claude_code/HEAD/.claude/commands/repo-doctor.md -o ~/.claude/commands/lelandg-.claude_code-repo-doctor.md

Restart Claude Code, or start a new session, for it to be picked up.

What Repo Doctor does

description: Audit a repo's agent docs — AGENTS.md/CLAUDE.md topology, always-loaded token cost, CodeMap freshness and line-number accuracy, broken pointers, changelog drift. Read-only; offers fixes in dependency order. argument-hint: [path | all] [--fix]

Invoke the `repo-doctor` skill.

Scope from `$ARGUMENTS`:

  • empty → audit the current repo.
  • a path → audit that repository.
  • all → audit every repository under your projects root, one audit.py run each, then present a single t

Alternatives in Security

  • FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
  • Skill Audit — Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review 2.8k ★
  • Cross-Pollinate Hex MCP Servers — Diff-driven audit: find real transferable changes across hex-line-mcp, hex-ssh-mcp, hex-graph-mcp 238 ★

Full documentation available on GitHub

View Source Repository

Related Skills

Claude Clean Context — Security skill for Claude Code

Claude Clean Context

Keep Claude Code's always-loaded context lean: deterministic memory guard-rail distiller + skills audit. Never

Security community
Claudemd Analyze — Security skill for Claude Code

Claudemd Analyze

Read-only spec ↔ implementation coherence audit. Cross-references core ↔ extended §EXT refs, Sizing line accur

Security community
OSS Audit — Security skill for Claude Code

OSS Audit

Audit the repo for open-source release across code quality, architecture, tech-stack hygiene, and GitHub colla

Security community
Doubleblind — Security skill for Claude Code

Doubleblind

Three layers that cannot see each other's mistakes: re-derive every number in prose from a file you committed,

Security community
Ssn — Security skill for Claude Code

Ssn

A System Security Number for every AI agent — its own Unix identity (private $HOME, workspace, scrubbed env, n

Security community
Code Review Feature — Security skill for Claude Code

Code Review Feature

Runs the security and quality reviewer subagents in parallel over a Spendly feature and produces a unified rep

Security community

Related Agents

Source Doctor — Development agent for Claude Code

Source Doctor

Diagnoses a job source that returns 0 offers, errors, or suddenly far fewer offers than usual, and repairs its

Development community
Devex Architect — Architecture agent for Claude Code

Devex Architect

Developer-experience architect owning the consumer install topology, doctor diagnostics, error-message shape,

Architecture community
Doc Quality Analyzer — Development agent for Claude Code

Doc Quality Analyzer

Use this agent to analyze documentation for freshness, accuracy, completeness,

Development community