Borrowing it
Nothing to install: this file belongs to babywyrm/mcpnuke. 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/babywyrm/mcpnuke/main/AGENTS.mdgit clone --depth 1 https://github.com/babywyrm/mcpnukeWrote 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/babywyrm/mcpnuke/agents-md)<a href="https://agentmods.dev/instructions/babywyrm/mcpnuke/agents-md"><img src="https://agentmods.dev/badge/instructions/babywyrm/mcpnuke/agents-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/babywyrm/mcpnuke/agents-md"><img src="https://agentmods.dev/badge/instructions/babywyrm/mcpnuke/agents-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 | $0.01684 | $0.01684 |
| Opus 5.5 | $0.00674 | $0.00674 |
| Sonnet 5.5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
mcpnuke 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 14d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidance for AI Coding Agents
Read this before making any change to mcpnuke. It is the product truth for how this repo is built, tested, and kept safe.
What this is
mcpnuke is an MCP red teaming and security scanner. Python 3.11+, package
manager uv. It actively probes MCP servers, so all code and docs must
assume authorized-use context — never add exploit PoCs, live credentials,
or real target data to the repo.
mcpnuke and stoneburner meet at
the agent. mcpnuke scans the MCP server — whether the tools will do the
dangerous thing. stoneburner grades the model — whether the model will ask
them to. --chain-replay proves the server half; stoneburner's adversarial
/ toolcall suites measure the model half. A model-resistance idea belongs in
stoneburner, not in a new mcpnuke check.
Setup and verification
uv sync --all-extras # install everything including dev
uv run pytest tests/ -v # full suite must pass: 0 failed
uv run ruff check . # must be zero
uv run mypy mcpnuke/ # must stay at or below the CI ceiling
CI gates all four on every push and PR. mcpnuke/core/ additionally enforces
disallow_untyped_defs. If you edit pyproject.toml, run uv lock and
commit uv.lock — CI checks they are in sync.
Code conventions
- Strong typing throughout:
dict,list,frozenset,int,strhints on all functions. NoAnyto silence the checker. - Module-level constants:
UPPER_SNAKE_CASE, typed explicitly. - Check signatures:
check_name(result: TargetResult)for static checks;check_name(session: MCPSessionProtocol, result: TargetResult, probe_opts: dict | None = None)for behavioral checks. - Every check body wrapped in
with time_check("check_name", result):. - Findings via
result.add(check_name, severity, title, detail, evidence=...). Severities: CRITICAL, HIGH, MEDIUM, LOW. - Credential regexes live in
mcpnuke/patterns/credentials.pyonly, in the tier matching their false-positive risk — never inrules.py,probes.py, or a check module.
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.
- 14d ago Changed · +43 lines · +603 tokens per session fb37617b9ba9
- 29d ago Changed · -6 tokens per session f5c2d64718f3
- 1mo ago Changed e323fbd4d611
- 1mo ago First seen · 94 lines · 1,087 tokens per session scan A 4887b22e5adc
mcpnuke AGENTS.md is an instructions file published in the GitHub repository babywyrm/mcpnuke (3 stars, last pushed 3d ago), licensed MIT. It adds 1,684 tokens to every session, about $0.0067 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 2026-09-05.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.