Borrowing it
Nothing to install: this file belongs to sinewaveai/agent-security-scanner-mcp. 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/sinewaveai/agent-security-scanner-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/sinewaveai/agent-security-scanner-mcpWrote 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/sinewaveai/agent-security-scanner-mcp/claude-md)<a href="https://agentmods.dev/instructions/sinewaveai/agent-security-scanner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sinewaveai/agent-security-scanner-mcp/claude-md.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 5.1 | $0.01918 | $0.01918 |
| Opus 5 | $0.00959 | $0.00959 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
agent-security-scanner-mcp CLAUDE.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 8d 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 — 172 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.
Build and Development Commands
# Install dependencies
npm install
# Run all tests (28 test files, 420+ tests, ~4.5 min)
npm test
# Run specific test file
npx vitest run tests/scan-security.test.js
# Run Python tests
python -m pytest test_ast_engine.py -v
python -m pytest src/test_semgrep_rules.py -v
# Run analyzer on a file
python3 analyzer.py <file_path>
# Run CLI commands
node index.js --help
node index.js scan-security <file>
node index.js scan-prompt <text>
node index.js scan-skill <path>
node index.js audit
node index.js doctor
Architecture Overview
This is an MCP (Model Context Protocol) server that provides security scanning tools for AI coding agents. It also serves as an OpenClaw plugin via the SKILL.md format.
Directory Structure
agent-security-scanner-mcp/
├── index.js # Entry point: MCP server, tool registration, CLI routing
├── package.json # npm package manifest (v4.0.0, ESM)
├── vitest.config.js # Test config (60s timeout, sequential)
├── openclaw.plugin.json # OpenClaw plugin metadata
├── server.json # MCP server manifest
│
├── src/
│ ├── utils.js # Shared: detectLanguage, runAnalyzer, extractImports, toSarif
│ ├── fix-patterns.js # 165 security fix templates
│ ├── config.js # .scannerrc config loading
│ ├── context.js # Context-aware filtering, isTestFile
│ ├── daemon-client.js # Python daemon lifecycle (DaemonClient)
│ ├── dedup.js # Cross-engine deduplication
│ ├── history.js # Scan history tracking
│ ├── typosquat.js # Typosquatting detection
│ ├── plugin-config.js # Plugin configuration loader
│ ├── plugin-health.js # Plugin health endpoint
│ ├── tools/
│ │ ├── scan-security.js # scan_security — file vulnerability scanning
│ │ ├── fix-security.js # fix_security — auto-fix generation
│ │ ├── check-package.js # check_package — hallucination detection
│ │ ├── scan-packages.js # scan_packages — bulk import scanning
│ │ ├── scan-prompt.js # scan_agent_prompt — prompt injection detection
│ │ ├── scan-action.js # scan_agent_action — pre-execution safety
│ │ ├── scan-project.js # scan_project — directory scanning
│ │ ├── scan-diff.js # scan_git_diff — git diff scanning
│ │ ├── scan-mcp.js # scan_mcp_server — MCP server audit
│ │ ├── scan-skill.js # scan_skill — OpenClaw skill scanning
│ │ ├── import-resolver.js # Import graph resolution
│ │ └── project-context.js # Project context detection
│ └── cli/
│ ├── init.js # init — MCP config setup (9 clients incl. OpenClaw)
│ ├── doctor.js # doctor — environment diagnostics
│ ├── demo.js # demo — generate vulnerable files
│ ├── init-hooks.js # init-hooks — git hook installation
│ ├── report.js # report — HTML/JSON security reports
│ ├── audit.js # audit — OpenClaw config audit
│ └── harden.js # harden — auto-hardening
│
├── analyzer.py # Python analysis engine (AST + taint + regex)
├── ast_parser.py # tree-sitter AST wrapper (11 languages)
├── generic_ast.py # Generic AST converter
├── pattern_matcher.py # Semgrep-style pattern matching
├── regex_fallback.py # Line-based regex scanner
├── semgrep_loader.py # YAML rule loader
├── taint_analyzer.py # Dataflow/taint analysis
├── cross_file_analyzer.py # Cross-file taint tracking
├── daemon.py # JSONL daemon wrapping analyzer
│
├── rules/ # 1700+ YAML security rules
├── packages/ # Bloom filters for 4.3M+ packages
├── skills/ # OpenClaw and Claude Code skills
├── tests/ # Vitest test suite (28 files)
├── benchmarks/ # Accuracy benchmarks
├── templates/ # CI/CD templates
└── scripts/ # Build/install scripts
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.
- 8d ago First seen · 172 lines · 1,918 tokens per session scan A 995740ccc4f1
agent-security-scanner-mcp CLAUDE.md is an instructions file published in the GitHub repository sinewaveai/agent-security-scanner-mcp (121 stars, last pushed 4d ago), licensed MIT. It adds 1,918 tokens to every session, about $0.0096 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
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
md-feedback copilot-instructions.md
Copilot instructions for yeominux/md-feedback, covering plan review workflow, before implementing any plan, annotation types and mcp setup.
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.
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.
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.