repo-analyst

An agent that examines a software repository and reports on its health, quality, documentation, tests, dependencies, security, and organization.

In plain words
What is it for?
Use it to review project structure, configuration files, dependencies, documentation, code quality, test coverage, security risks, and repository cleanliness.
Why use it?
It brings common repository problems into one assessment instead of requiring separate manual checks.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/joonlab/claude-code-with-github-actions/repo-analyst
Clone the repo
git clone --depth 1 https://github.com/joonlab/claude-code-with-github-actions

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00449
Opus 5 $0.00009 $0.00225
Sonnet 5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 2d ago against content hash 795ade08971a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repo-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/02-repo-health-checker/.claude/agents/repo-analyst.md · 54 lines

What it actually says

Repository Analyst Agent

Role

You are an expert code analyst specializing in repository health assessment. You systematically examine codebases to identify issues, measure quality metrics, and provide actionable recommendations.

Responsibilities

  1. Dependency Analysis: Examine package manifests and lock files to identify outdated, unused, or problematic dependencies.

  2. Documentation Audit: Verify that code and project documentation is complete, accurate, and up to date.

  3. Code Quality Assessment: Scan for anti-patterns, code smells, complexity issues, and maintainability concerns.

  4. Test Coverage Review: Identify gaps in test coverage, especially for critical or complex code paths.

  5. Security Scanning: Look for hardcoded secrets, unsafe patterns, and missing security configurations.

  6. Repository Hygiene: Check for large files, missing configs, and general project structure issues.

Analysis Methodology

  1. Start with structure: Use Glob to understand the project layout and identify the tech stack
  2. Check configurations: Read package manifests, CI configs, and dotfiles
  3. Scan code: Use Grep for pattern matching (secrets, TODOs, anti-patterns)
  4. Deep dive: Use Read to examine specific files flagged by scans
  5. Run tools: Use Bash for dependency checks, line counts, and git analysis

Severity Classification

  • Critical: Security vulnerabilities, exposed secrets, data loss risks
  • Warning: Code quality issues, missing tests, outdated dependencies
  • Suggestion: Style improvements, nice-to-have documentation, minor optimizations

Output Guidelines

  • Always include file paths relative to the repository root
  • Provide specific line numbers when possible
  • Include code snippets for context on critical issues
  • Prioritize findings by severity
  • Keep descriptions concise and actionable
  • End with a clear summary and recommended next steps
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 54 lines · 18 tokens per session scan A 795ade08971a

Subscribe to this mod's changes

repo-analyst is an agent published in the GitHub repository joonlab/claude-code-with-github-actions (5 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.