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/mlzoo/mcp_forge/agents-mdgit clone --depth 1 https://github.com/mlzoo/mcp_forgeWhat 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 | $0.00420 | $0.00420 |
| Opus 5 | $0.00210 | $0.00210 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
mcp_forge 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.
What it actually says
AGENTS.md
Cursor Cloud specific instructions
This is a Python 3.12 FastAPI + FastAPI-MCP service (a parking-lot lookup example).
It is managed with the uv package manager. Standard
commands live in the Makefile and README.md; prefer those.
Service overview
- Single service:
main.pystarts a Uvicorn server on0.0.0.0:5000.- REST docs (Swagger UI):
http://localhost:5000/docs - MCP endpoint (SSE):
http://localhost:5000/mcp - Endpoints:
POST /parking/nearbyandPOST /parking/info(mock data, no external services or secrets needed).
- REST docs (Swagger UI):
Run / lint / test
- Run dev server:
make dev(equivalentlyuv run python main.py). It is NOT a hot-reload server; restart the process after code changes. - Lint:
uv run ruff check .anduv run ruff format --check .(themake checktarget also runsuv lock --lockedand fullpre-commit, which needs network to install hook envs). - Tests:
make test/uv run python -m pytest. There is currently notests/directory, so pytest exits with code 5 ("no tests collected") — this is expected, not a failure.
Non-obvious gotchas
pyproject.tomldeclares a heavy, unused dependencyttt-video(git) that transitively pullstorch,torchvision,xformers,triton,transformers, etc.uv syncinstalls all of it (multi-GB), even thoughmain.pynever imports it. Do not be surprised by the large.venv.- The app code uses Traditional Chinese strings; ensure UTF-8 output when inspecting responses.
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 · 23 lines · 420 tokens per session scan A 155a9a15777d
mcp_forge AGENTS.md is an instructions file published in the GitHub repository mlzoo/mcp_forge (208 stars, last pushed 2mo ago), licensed MIT. It adds 420 tokens to every session, about $0.0021 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 2026-08-30.
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.