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 rules/babywyrm/mcpnuke/mcpnuke-developmentgit 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/rules/babywyrm/mcpnuke/mcpnuke-development)<a href="https://agentmods.dev/rules/babywyrm/mcpnuke/mcpnuke-development"><img src="https://agentmods.dev/badge/rules/babywyrm/mcpnuke/mcpnuke-development.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 | $0.01059 | $0.01059 |
| Opus 5 | $0.00530 | $0.00530 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
mcpnuke-development 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpnuke Development Standards
Project Identity
mcpnuke is an MCP red teaming and security scanner. Version 6.13.0. Python 3.11+.
Package manager: uv. Test runner: uv run pytest tests/ -v.
Superpowers Workflow (mandatory)
All development on mcpnuke follows the superpowers skills framework:
- brainstorming before any new feature, check, or transport
- writing-plans before multi-step implementation work
- test-driven-development for all check modules and pattern changes — RED-GREEN-REFACTOR, no exceptions
- systematic-debugging for any test failure or scan anomaly — form hypothesis before changing code
- verification-before-completion before claiming anything is done — run
uv run pytest tests/ -vand confirm output - requesting-code-review after completing a feature branch
Code Conventions
- Strong typing throughout: use
dict,list,frozenset,int,strtype hints on all functions - Module-level constants:
UPPER_SNAKE_CASE, typed explicitly (e.g._NAME_MULTIPLIER: int = 3) - Check functions signature:
check_name(result: TargetResult)for static,check_name(session: MCPSessionProtocol, result: TargetResult, probe_opts: dict | None = None)for behavioral - Credential regexes belong in
patterns/credentials.pyonly, in the tier that matches their false-positive risk — never inrules.py,probes.py, or a check module - Every check wrapped in
with time_check("check_name", result): - Findings via
result.add(check_name, severity, title, detail, evidence=...) - Severity levels: CRITICAL, HIGH, MEDIUM, LOW
Testing Requirements
- Every new check needs a dedicated
tests/test_<check_name>.py - Minimum 3 tests per check: positive detection, clean/negative, timing recorded
- Use
conftest.pyfixtures:result_with_tools([{...}]) - Full suite must pass before any commit: 1040+ passed, 37 skipped, 0 failed
- Also green before committing:
ruff check .at zero,mypy mcpnuke/at or below the CI ceiling.mcpnuke.core.*additionally enforcesdisallow_untyped_defs - DVMCP live tests gated behind
DVMCP_LIVE=1
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 · 83 lines · 1,059 tokens per session scan A 64b5715ac782
mcpnuke-development is a cursor rule published in the GitHub repository babywyrm/mcpnuke (2 stars, last pushed 5d ago), licensed MIT. It adds 1,059 tokens to every session, about $0.0053 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 cursor rules, from other repositories
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
cursorrules
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
nix-security
Nix Security and Sandboxing.
terminal-commands
Guidelines for generating terminal commands that ensure outputs are readable by Cursor agents.