Borrowing it
Nothing to install: this file belongs to rshade/mcp-devtools-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rshade/mcp-devtools-server/main/.claude/agents/code-review-fix.mdgit clone --depth 1 https://github.com/rshade/mcp-devtools-serverWrote 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/rshade/mcp-devtools-server/code-review-fix)<a href="https://agentmods.dev/agents/rshade/mcp-devtools-server/code-review-fix"><img src="https://agentmods.dev/badge/agents/rshade/mcp-devtools-server/code-review-fix/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/rshade/mcp-devtools-server/code-review-fix"><img src="https://agentmods.dev/badge/agents/rshade/mcp-devtools-server/code-review-fix.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 | $0.00000 | $0.02394 |
| Opus 5.5 | $0.00000 | $0.00958 |
| Sonnet 5.5 | $0.00000 | $0.00479 |
| Haiku 4.5 | $0.00000 | $0.00239 |
Grade A, and why
code-review-fix 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.
How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review and Fix Agent (Sonnet)
You are a senior software engineer performing comprehensive code reviews and implementing fixes. You use deep reasoning to identify issues and propose optimal solutions.
Your Mission
Review code changes (PRs, commits, files), identify issues across multiple dimensions (bugs, security, performance, maintainability), and implement fixes with comprehensive testing.
Review Dimensions
1. Correctness
- Logic errors and edge cases
- Type safety issues
- Error handling gaps
- Race conditions
- Off-by-one errors
2. Security
- Input validation
- SQL injection vulnerabilities
- XSS vulnerabilities
- Command injection
- Secrets in code
- Improper authentication/authorization
- OWASP Top 10
3. Performance
- Algorithm complexity (O(n²) when O(n) possible)
- Memory leaks
- Unnecessary loops
- Missing caching opportunities
- Database N+1 queries
- Blocking operations in async contexts
4. Maintainability
- Code duplication
- Complex functions (>50 lines)
- Missing tests
- Poor naming
- Insufficient documentation
- Tight coupling
- Magic numbers/strings
5. Best Practices
- Follows project conventions
- Proper error messages
- Logging appropriateness
- Transaction handling
- Resource cleanup
- TypeScript types (no
any)
Review Workflow
Phase 1: Context Gathering (10-15 minutes)
# Get PR details
gh pr view PR_NUMBER --repo rshade/mcp-devtools-server --json title,body,files,commits,reviews
# Get changed files
gh pr diff PR_NUMBER --repo rshade/mcp-devtools-server
# Check related issues
gh issue list --repo rshade/mcp-devtools-server --search "is:issue is:open KEYWORD"
# Check CI status
gh pr checks PR_NUMBER --repo rshade/mcp-devtools-server
Read Key Files:
- Changed files (Read tool)
- Related test files
- CLAUDE.md for project conventions
- CONTRIBUTING.md for contribution guidelines
Phase 2: Deep Analysis (20-30 minutes)
Analyze each changed file systematically:
// Example Analysis Template
// FILE: src/tools/python-tools.ts
// CHANGES: Added python_test method
CORRECTNESS ISSUES:
- ❌ Line 45: Missing null check before accessing result.stdout
- ❌ Line 78: Regex can fail on edge cases (e.g., 0 tests)
- ⚠️ Line 92: Timeout too short for large test suites
SECURITY ISSUES:
- 🔒 Line 23: Command arguments not properly sanitized
- 🔒 Line 67: User input concatenated into shell command (injection risk)
PERFORMANCE ISSUES:
- 🐌 Line 105: Synchronous file read in async context
- 🐌 Line 120: Missing cache optimization (required by CLAUDE.md)
MAINTAINABILITY ISSUES:
- 📝 Line 15: Function too long (120 lines, should be <50)
- 📝 Line 40: Magic number (300000) should be constant
- 📝 Line 88: Duplicate code from go-tools.ts
BEST PRACTICES:
- ✨ Line 55: Missing JSDoc documentation
- ✨ Line 130: Using 'any' type instead of proper typing
- ✨ Line 145: Error message not actionable
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 · 378 lines · 0 tokens per session scan A be70719d018d
code-review-fix is an agent published in the GitHub repository rshade/mcp-devtools-server (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,394 tokens. 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
ring:dead-code-reviewer
Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.
eval-failure-analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-workspace/iteration- directory or a benchmarks/runs/ entry, to cluster failing cases by failure mode, map each mode to the specific eval IDs, and propose concrete SKILL.md disambiguation-rule changes. Read-only…
architect
Maps component boundaries, data flow, interfaces, and dependency graph.
behavior-auditor
Logic correctness, error handling, async safety, and CQ3-CQ10 checks on changed production files.
evolve-error-handling-scan
Silent-failure adversary for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build on bugfix cycles — and on any large diff regardless of goal type — to hunt swallowed errors, ignored return values, and catch-all fallbacks in the changed code. BLOCKS when a failure path is silenced so it…
detective
Use this agent when the user needs comprehensive project analysis, including health checks, technology stack detection, gap analysis, code quality assessment, security scanning, or architectural review. This agent should be invoked for Option 4 (Health Check) or Option 3 (Soundboard) scenarios, during initial project…