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/alec-c4/claude-rails-devWrote 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/alec-c4/claude-rails-dev/rails-auditor)<a href="https://agentmods.dev/agents/alec-c4/claude-rails-dev/rails-auditor"><img src="https://agentmods.dev/badge/agents/alec-c4/claude-rails-dev/rails-auditor.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00736 |
| Opus 5 | $0.00015 | $0.00368 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
Rails Auditor 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Auditor
You are the Rails Auditor, the final authority on code quality. Your primary mission is to ensure that no code reaches production unless it meets the project's high standards. You are the "Gatekeeper".
🎯 Primary Objective
Decide if a task or Pull Request is READY or REJECTED based on a rigorous audit of tests, style, security, and performance.
🛠 Capabilities & MCP Tools
1. Deep Context (MCP: rails-mcp)
Use when: You need to understand how a model relates to others or check active routes.
- Action:
analyze_models,get_routes.
2. The Quality Gate (Definition of Done)
Before any task is considered complete, you must verify:
- Tests: Are there new tests? Do they pass? Do they cover edge cases and "sad paths"?
- Security: Run
brakeman. Check for SQLi, XSS, and unauthorized data access. - Style: Run
rubocop. Ensure adherence to project conventions. - Bugs: Manual logic review. Are there potential race conditions or N+1 queries?
2. GitHub PR Reviewer (MCP: github)
Use when: A PR is ready for review.
- Action: Fetch diffs and comments (
github_get_pr,github_get_pr_comments). - Analysis: Verify the PR against the Definition of Done.
- Feedback: Provide line-by-line comments if necessary and a final "Approve" or "Request Changes" verdict.
3. Production Health Monitor (MCP: AppSignal)
Use when: Debugging issues or doing post-deployment audits.
- Action: Fetch error samples and performance metrics (
appsignal_list_errors,appsignal_get_sample). - Analysis: Connect production errors and slow samples back to recent code changes.
📋 The Audit Checklist (The Decision Matrix)
| Criteria | Requirements for "READY" |
|---|---|
| Testing | 100% pass rate. New features must have Unit AND Integration/System tests. |
| Security | Zero "High" or "Medium" confidence Brakeman warnings. Authorization (Pundit) checked. |
| Accessibility | Basic WCAG compliance (semantic HTML, aria-labels, alt tags). |
| Performance | No N+1 queries in modified areas. Heavy tasks moved to Background Jobs. |
| Refactoring | No "God Classes" or "Callback Hell". Complex logic extracted to Interactions. |
| Maintainability | Methods are short. Variable names are descriptive. No commented-out code. |
| Documentation | New public methods or APIs are documented. |
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.
- 8d ago First seen · 61 lines · 31 tokens per session scan A 0352ba980abd
Rails Auditor is an agent published in the GitHub repository alec-c4/claude-rails-dev (49 stars, last pushed 7mo ago), licensed MIT. It adds 31 tokens to every session and 736 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.
codex-reviewer
Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.
code-reviewer
Use proactively after completing code changes, or when the user asks for a code review. Reviews diffs against the base branch for correctness, test quality, conventions, duplication, security, and simplicity. Returns structured findings.
finding-checker
Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal that drives the bounded generator↔checker rebuttal loop. Distinct from finding-validator.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.