Borrowing it
Nothing to install: this file belongs to luw2007/skim-mcp. 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/luw2007/skim-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/luw2007/skim-mcpWrote 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/luw2007/skim-mcp/claude-md)<a href="https://agentmods.dev/instructions/luw2007/skim-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/luw2007/skim-mcp/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/luw2007/skim-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/luw2007/skim-mcp/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 | $0.01519 | $0.01519 |
| Opus 5.5 | $0.00608 | $0.00608 |
| Sonnet 5.5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
skim-mcp 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is the Skim MCP Server - a production-ready Model Context Protocol (MCP) server that exposes the Skim code transformation CLI to AI agents. It intelligently compresses code (60-95% token reduction) while preserving structure for LLM context optimization.
Note: This project (luw2007/skim-mcp) wraps the upstream Skim project by dean0x.
Key Dependencies
- External CLI: Requires the
skimRust binary (rskimpackage) - originally by dean0x, automatically installed viascripts/install-skim.js - MCP SDK:
@modelcontextprotocol/sdkfor MCP server implementation - Logging: Winston for structured logging
- Testing: Node.js built-in test runner with c8 for coverage
Development Commands
Build and Run
npm run build # Copy src/index.js to dist/ and make executable
npm run dev # No hot-reload - must rebuild manually
npm run install-skim # Manual installation of skim CLI
Testing
npm test # Run all tests
npm run test:coverage # Run tests with c8 coverage report
npm run test:watch # Watch mode for development
Code Quality
npm run lint # Check ESLint issues
npm run lint:fix # Auto-fix ESLint issues
npm run format # Check Prettier formatting
npm run format:fix # Auto-fix formatting
All tests must pass before committing. The project uses ESLint with Prettier integration.
Architecture
Single-Server Design
The entire MCP server is implemented in src/index.js (697 lines) with a monolithic architecture:
-
Configuration & Constants (lines 28-39)
- Hardcoded limits: 10MB input, 50MB buffer, 10 requests/minute rate limit
- Default allowed base path:
process.cwd()
-
Security Layer (lines 67-220)
RateLimiterclass: Per-tool rate limiting to prevent DoSvalidatePath(): Absolute path requirement, anti-traversal, symlink resolutionvalidateSource(): Size limits, null byte detectionvalidateLanguage()/validateMode(): Whitelist validation
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 · 160 lines · 1,519 tokens per session scan A 4ce25d7dc924
skim-mcp CLAUDE.md is an instructions file published in the GitHub repository luw2007/skim-mcp (0 stars, last pushed 11mo ago), licensed MIT. It adds 1,519 tokens to every session, about $0.0061 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.
skim-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skim-mcp CLAUDE.mdluw2007/skim-mcp | Instructions file | 0 | 11mo ago | MIT | A | 1,519 | 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 |