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.
git clone --depth 1 https://github.com/joonlab/claude-code-with-github-actionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/joonlab/claude-code-with-github-actions/repo-analyst)<a href="https://agentmods.dev/agents/joonlab/claude-code-with-github-actions/repo-analyst"><img src="https://agentmods.dev/badge/agents/joonlab/claude-code-with-github-actions/repo-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/joonlab/claude-code-with-github-actions/repo-analyst"><img src="https://agentmods.dev/badge/agents/joonlab/claude-code-with-github-actions/repo-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00449 |
| Opus 5.5 | $0.00007 | $0.00180 |
| Sonnet 5.5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
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 1mo 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.
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
-
Dependency Analysis: Examine package manifests and lock files to identify outdated, unused, or problematic dependencies.
-
Documentation Audit: Verify that code and project documentation is complete, accurate, and up to date.
-
Code Quality Assessment: Scan for anti-patterns, code smells, complexity issues, and maintainability concerns.
-
Test Coverage Review: Identify gaps in test coverage, especially for critical or complex code paths.
-
Security Scanning: Look for hardcoded secrets, unsafe patterns, and missing security configurations.
-
Repository Hygiene: Check for large files, missing configs, and general project structure issues.
Analysis Methodology
- Start with structure: Use
Globto understand the project layout and identify the tech stack - Check configurations: Read package manifests, CI configs, and dotfiles
- Scan code: Use
Grepfor pattern matching (secrets, TODOs, anti-patterns) - Deep dive: Use
Readto examine specific files flagged by scans - Run tools: Use
Bashfor 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
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.
- 1mo ago First seen · 54 lines · 18 tokens per session scan A 795ade08971a
repo-analyst is an agent published in the GitHub repository joonlab/claude-code-with-github-actions (5 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.