Borrowing it
Nothing to install: this file belongs to jaggederest/mcp_reviewer. 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/jaggederest/mcp_reviewer/main/CLAUDE.mdgit clone --depth 1 https://github.com/jaggederest/mcp_reviewerWrote 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/instructions/jaggederest/mcp_reviewer/claude-md)<a href="https://agentmods.dev/instructions/jaggederest/mcp_reviewer/claude-md"><img src="https://agentmods.dev/badge/instructions/jaggederest/mcp_reviewer/claude-md/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/instructions/jaggederest/mcp_reviewer/claude-md"><img src="https://agentmods.dev/badge/instructions/jaggederest/mcp_reviewer/claude-md.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 | $0.01020 | $0.01020 |
| Opus 5.5 | $0.00408 | $0.00408 |
| Sonnet 5.5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
mcp_reviewer CLAUDE.md 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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context for Claude
Project Overview
This is an MCP (Model Context Protocol) service called "reviewer-mcp" that provides AI-powered development workflow tools with pluggable AI providers (OpenAI and Ollama). It runs as a stateless stdio-based server that can be self-hosted in any project.
Key Features
- Spec Generation: Generate detailed technical specifications from prompts
- Spec Review: Review specifications for completeness and provide critical feedback
- Code Review: Analyze code changes with focus on security, performance, style, or logic
- Test Runner: Standardized test execution with consistent output formatting
- Linter: Standardized linting with consistent output formatting
- Music Control: Spotify integration with configurable playlists and safety features (macOS only)
- Notifications: Audio notifications for alerts and status updates (macOS only)
- Memory Storage: Temporary in-memory key-value storage for session context (data lost on restart)
Architecture
- Base Classes:
BaseAIToolfor AI-powered tools,BaseExecToolfor command execution - Common Utilities: Centralized error handling (
createErrorResult) and output formatting - Stateless Design: Each tool invocation reads config fresh, no persistent state
- Transport: Uses stdio for MCP communication (JSON-RPC)
Technical Stack
- TypeScript with strict type checking
- Node.js with ES modules
- MCP SDK for tool protocol
- Pluggable AI: OpenAI API or Ollama (local models)
- Vitest for testing with coverage reporting
- ESLint with TypeScript rules
Development Guidelines
- IMPORTANT: Use MCP tools for testing and linting - DO NOT run these commands manually via bash:
- Use
mcp__reviewer__run_testsfor running tests - Use
mcp__reviewer__run_linterfor linting - TypeScript checking can still be done manually
- Use
- Always verify code quality before committing using the MCP tools
- Maintain strict TypeScript types - no
anytypes allowed - Follow existing code patterns and conventions
- Test all new functionality with unit tests
- Handle errors gracefully with informative messages
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.
- 2mo ago First seen · 100 lines · 1,020 tokens per session scan A b606ecb0abb0
mcp_reviewer CLAUDE.md is an instructions file published in the GitHub repository jaggederest/mcp_reviewer (0 stars, last pushed 1y ago), licensed MIT. It adds 1,020 tokens to every session, about $0.0041 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.
mcp_reviewer CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp_reviewer CLAUDE.mdjaggederest/mcp_reviewer | Instructions file | 0 | 1y ago | MIT | A | 1,020 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |