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.
npx agentmods add instructions/sapientpants/deepsource-mcp-server/claude-mdgit clone --depth 1 https://github.com/sapientpants/deepsource-mcp-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/instructions/sapientpants/deepsource-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/sapientpants/deepsource-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sapientpants/deepsource-mcp-server/claude-md.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 | $0.03103 | $0.03103 |
| Opus 5 | $0.01551 | $0.01551 |
| Sonnet 5 | $0.00621 | $0.00621 |
| Haiku 4.5 | $0.00310 | $0.00310 |
Grade C, and why
deepsource-mcp-server CLAUDE.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules pnpm-lock.yaml && pnpm install How it starts
The opening of the file, as written. The whole thing — 441 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.
Repository Overview
This repository is a Model Context Protocol (MCP) server that integrates with DeepSource's code quality analysis platform. It serves as a bridge between DeepSource's GraphQL API and MCP-compatible AI assistants like Claude, providing access to code quality metrics and analysis results.
Development Commands
Understanding MCP Servers
MCP servers are not standalone services - they communicate via stdio with MCP clients (like Claude Desktop). The server cannot be run directly with node or npm start in a meaningful way. Instead, use:
- Production: Configure in Claude Desktop or use
npx deepsource-mcp-server - Development: Use
pnpm run inspectwith the MCP Inspector tool - Testing: Run the test suite with
pnpm test
Quick Start
# Install dependencies
pnpm install
# Build the server
pnpm run build
# Debug with MCP Inspector (recommended for development)
pnpm run inspect
Building & Debugging
pnpm run build # Compile TypeScript to JavaScript
pnpm run watch # Watch mode - rebuild on changes
pnpm run clean # Remove build artifacts (dist/)
# Debugging with MCP Inspector
pnpm run inspect # Launch MCP Inspector to test the server interactively
Testing
# Basic testing
pnpm run test # Run all tests
pnpm run test:watch # Run tests in watch mode
pnpm run test:coverage # Run tests with coverage report
# Run specific tests
pnpm test -- src/__tests__/specific-test.test.ts
pnpm test -- --testNamePattern="should handle errors"
pnpm test -- --verbose src/__tests__/specific-test.test.ts
# Run tests for a specific file pattern
pnpm test -- client # Test all client files
pnpm test -- handler # Test all handler files
Code Quality
# Type checking
pnpm run check-types # Type check without building
# Linting
pnpm run lint # Run ESLint
pnpm run lint:fix # Auto-fix ESLint issues
# Formatting
pnpm run format # Check if code is formatted
pnpm run format:fix # Format all code with Prettier
# Full CI pipeline
pnpm run ci # Run format, lint, type check, build, and test coverage
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.
- 4d ago First seen · 441 lines · 3,103 tokens per session scan C 58465de82383
deepsource-mcp-server CLAUDE.md is an instructions file published in the GitHub repository sapientpants/deepsource-mcp-server (7 stars, last pushed 10mo ago), licensed MIT. It adds 3,103 tokens to every session, about $0.0155 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
XcodeBuildMCP AGENTS.md
AGENTS.md instructions for getsentry/XcodeBuildMCP, covering development rules, build & test, architecture, contributing workflow and code quality.
XcodeBuildMCP CLAUDE.md
Claude Code instructions for getsentry/XcodeBuildMCP, covering development rules, code quality, test conventions, commands and github.
quip-mcp-server-typescript CLAUDE.md
Claude Code instructions for zxkane/quip-mcp-server-typescript, covering claude.md, common development commands, build and development, testing and code quality.
excel-mcp CLAUDE.md
Claude Code instructions for ASH1998/excel-mcp, covering claude.md, project overview, architecture, current implementation status and ✅ completed: file operations (phase 1).
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.