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/trymightyai/mighty-security/claude-mdgit clone --depth 1 https://github.com/TryMightyAI/mighty-securityWhat 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 | $0.02216 | $0.02216 |
| Opus 5 | $0.01108 | $0.01108 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade B, and why
mighty-security CLAUDE.md scanned grade B with 1 finding 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 3d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- NEVER NEVER EVER delete files with `rm` or `rm -rf` without permissions. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 271 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.
Project Overview
MCP Security Suite - A unified security framework for Model Context Protocol (MCP) servers. This is a defensive security tooling project for analyzing and detecting vulnerabilities in MCP implementations.
Main entry point: mighty_mcp.py - ALL functionality goes through this single CLI.
Essential Commands
Setup & Installation
# Python 3.13+ required
# Using uv (recommended)
uv sync -p 3.13
# Alternative: pip with venv
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
# Optional ML features (for semantic analysis)
pip install transformers torch sentence-transformers scikit-learn networkx gitpython
# Optional LLM features (Cerebras GPT-OSS-120B)
pip install cerebras-cloud-sdk
echo "CEREBRAS_API_KEY=your_api_key" > .env
Core Analysis Commands
# IMPORTANT: Always activate virtual environment first
source .venv/bin/activate # On macOS/Linux
# or
.venv\Scripts\activate # On Windows
# Main entry point - comprehensive analysis
python3 mighty_mcp.py check [target]
# Alternative direct analyzer
python3 src/analyzers/comprehensive_mcp_analyzer.py [target]
# Analyze GitHub repository
python3 src/analyzers/comprehensive_mcp_analyzer.py https://github.com/example/mcp-tool
# Analyze with LLM enhancement
python3 src/analyzers/comprehensive_mcp_analyzer.py [target] --llm
# Start web dashboard
python3 mighty_mcp.py web
Testing
# IMPORTANT: Always activate virtual environment first
source .venv/bin/activate
# Run comprehensive test suite
python3 tests/comprehensive_test_suite.py
# Test context-aware filtering
python3 tests/test_context_filtering.py
# Test integration with context-aware scanning
python3 tests/test_integration_context_aware.py
# Create test cases
python3 tests/create_test_cases.py
# Test ML integration (requires ML deps)
python3 tests/demo_ml_integration.py
# Test real MCP servers
python3 tests/test_real_mcp_servers.py --test-all
# CRITICAL: Test attack vector categorization accuracy
python3 tests/test_categorization_fix.py
# CRITICAL: Test fingerprint integrity (security-critical)
python3 tests/test_fingerprint_integrity.py
# CRITICAL: Test parallel processing functionality
python3 tests/test_parallel_processing.py
# CRITICAL: Test security is not compromised by optimizations
python3 tests/test_security_not_compromised.py
# Performance benchmarking
python3 tests/benchmark_performance.py
# FAST DEVELOPMENT TESTING (recommended for dev)
bash tests/run_dev_tests.sh # Runs core tests in ~1 second
# Git hooks setup (ensures tests pass before commit/push)
git config core.hooksPath .githooks # Enable commit hooks
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.
- 3d ago First seen · 271 lines · 2,216 tokens per session scan B 1836300d6c26
mighty-security CLAUDE.md is an instructions file published in the GitHub repository TryMightyAI/mighty-security (97 stars, last pushed 1y ago), licensed MIT. It adds 2,216 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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.