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/patrickkoss/docsearch-mcp/claude-mdgit clone --depth 1 https://github.com/PatrickKoss/docsearch-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/patrickkoss/docsearch-mcp/claude-md)<a href="https://agentmods.dev/instructions/patrickkoss/docsearch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/patrickkoss/docsearch-mcp/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 | $0.03445 | $0.03445 |
| Opus 5 | $0.01723 | $0.01723 |
| Sonnet 5 | $0.00689 | $0.00689 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade A, and why
docsearch-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 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.
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 — 263 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.
Pre-commit Verification
Always run make lint before considering changes complete. The repository has a husky pre-commit hook that runs pnpm format:check, pnpm lint, and pnpm typecheck:src. All three must pass before committing.
Always verify the Docker build works by running docker build -t docsearch-mcp:test . after making changes to build configuration, TypeScript config, dependencies, or Dockerfile-related files.
Project Overview
This is a local-first document search and indexing system with both a CLI tool and MCP server that provides hybrid semantic+keyword search across local files (including PDFs) and Confluence pages. The system chunks documents, creates embeddings, stores them in SQLite with vector search capabilities, and exposes search functionality through both a command-line interface and the Model Context Protocol.
Development Commands
# Setup
make setup # Install dependencies and setup .env
make install # Install dependencies only
pnpm i # Install dependencies only (alternative)
cp .env.example .env # Set up environment variables
# Development Servers
make dev # Start MCP development server
make dev-cli # Start CLI in development mode
pnpm dev:cli # Start CLI in development mode (alternative)
pnpm dev:mcp # Start MCP server in development (alternative)
# Build Commands
make build # Build the project
make clean # Clean all generated files (node_modules, data, dist)
make clean-dist # Clean build directory only
pnpm build # Build TypeScript (alternative)
# Production
make start # Start production MCP server
make start-cli # Start CLI in production mode
pnpm start:mcp # Start built MCP server (alternative)
pnpm start:cli # Run built CLI (alternative)
# Quality Assurance
make test # Run tests
make test-run # Run tests once
make test-ui # Run tests with UI
make test-coverage # Run tests with coverage
make test-unit # Run unit tests only
make test-integration # Run integration tests (requires Docker)
make lint # Run linter, formatter, and typecheck (source only)
make lint-fix # Run linter with auto-fix
make format # Format code with Prettier
make format-check # Check code formatting
make typecheck # Run TypeScript type checking (all files)
make typecheck-src # Run TypeScript type checking (source only)
make check-all # Run all quality checks (lint, typecheck, unit tests)
# Data Management
make ingest-files # Ingest local files
make ingest-files-incremental # Ingest local files with incremental indexing
make ingest-confluence # Ingest Confluence pages
make ingest-all # Ingest all sources (files and confluence)
make ingest-all-incremental # Ingest all sources with incremental indexing
make watch # Watch for file changes and re-index
make watch-incremental # Watch for file changes with incremental re-indexing
make search QUERY="text" # Search documents
make search-json QUERY="text" # Search documents with JSON output
make clean-data # Clean data directory
# Incremental Indexing (Performance Optimized)
make incremental-files # Alias for incremental file indexing
make incremental-all # Alias for incremental indexing of all sources
make incremental-watch # Alias for incremental file watching
make incremental-benchmark # Compare full vs incremental indexing performance
# Ansible Deployment (deploy/ansible/)
make ansible-test # Run Molecule tests for Ansible deployment (requires Docker)
make ansible-lint # Lint Ansible playbook with ansible-lint
# Alternative pnpm commands
pnpm test # Run tests in watch mode
pnpm test:run # Run tests once
pnpm test:ui # Run tests with UI
pnpm test:coverage # Run tests with coverage
pnpm lint # Run ESLint
pnpm lint:fix # Run ESLint with auto-fix
pnpm format # Format code with Prettier
pnpm typecheck # Run TypeScript type checking
# CLI Tool (direct pnpm usage)
pnpm dev:cli ingest files # Index local files via CLI
pnpm dev:cli ingest confluence # Index Confluence pages via CLI
pnpm dev:cli ingest all --watch # Index all sources with file watching
pnpm dev:cli search "query" # Search documents via CLI
pnpm dev:cli search "test" --output json # Search with JSON output
# Help
make help # Show all available make commands
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 · 263 lines · 3,445 tokens per session scan A f250f98815a3
docsearch-mcp CLAUDE.md is an instructions file published in the GitHub repository PatrickKoss/docsearch-mcp (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,445 tokens to every session, about $0.0172 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.