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/jonusnattapong/mcpsearch/agents-mdgit clone --depth 1 https://github.com/JonusNattapong/MCPSearchWhat 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 | $0.01584 | $0.01584 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
MCPSearch AGENTS.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 2d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - MCPSearch Development Guide
Project Overview
MCPSearch is an AI-powered multi-source intelligence platform with MCP (Model Context Protocol) interface. It features hybrid crawling (httpx + Playwright + Camoufox), parallel search aggregation, social media scrapers, and advanced content extraction.
Build & Development Commands
# Using Makefile (recommended)
make install # pip install -e .
make dev # install with dev deps + playwright
make server # python -m mcp_server
# Or manual
pip install -e .
pip install -e ".[dev]"
playwright install chromium
# Run MCP server (stdio transport)
python -m mcp_server
# CLI commands
mcpsearch search -q "query"
mcpsearch crawl -u "https://example.com"
mcpsearch read -u "https://example.com"
# Docker
make docker-build
make docker-run
Version Management
Version is managed from single source: mcpspider/version.py
# Auto-release with changelog generation
make patch # 1.0.0 -> 1.0.1 (bug fixes)
make minor # 1.0.0 -> 1.1.0 (new features)
make major # 1.0.0 -> 2.0.0 (breaking changes)
# Or directly
python scripts/release.py patch
python scripts/release.py 1.2.3 # explicit version
Release process:
- Bumps version in
version.pyandpyproject.toml - Generates changelog from git commits (conventional commits)
- Updates
CHANGELOG.md - Creates git commit + tag
- Pushes to GitHub
- Creates GitHub release
Conventional commits for changelog:
feat:-> Addedfix:-> Fixedrefactor:,docs:,perf:-> Changedremove:,break:-> Removed
Testing
make test # all tests
make test-cov # with coverage
# Or manual
pytest
pytest --cov=.
pytest tests/test_crawler.py # single file
pytest -k "test_search" # by name
Linting & Formatting
make lint # ruff check .
make lint-fix # ruff check --fix .
make format # ruff format .
Code Style Guidelines
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.
- 2d ago First seen · 198 lines · 1,584 tokens per session scan A f93712f9c891
MCPSearch AGENTS.md is an instructions file published in the GitHub repository JonusNattapong/MCPSearch (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,584 tokens to every session, about $0.0079 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.