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/michoo/security_mcp/claude-mdgit clone --depth 1 https://github.com/michoo/security_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/michoo/security_mcp/claude-md)<a href="https://agentmods.dev/instructions/michoo/security_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/michoo/security_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 | $0.01871 | $0.01871 |
| Opus 5 | $0.00936 | $0.00936 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
security_mcp CLAUDE.md scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Guards empty input, runs via `subprocess.run(..., capture_output=True, text=True, timeout=TIMEOUT, check=False)`. How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — conventions for this repository
Guidance for working in the security MCP server. The goal of this file is that every scanner is wired the same way, so adding or changing one is a mechanical, predictable process. When you add a tool, follow the checklist at the bottom — touch every listed place, in the same style as the existing tools.
What this project is
A FastMCP server (server.py) plus a CLI (cli.py) that run a set of security
scanners over a target and produce SARIF 2.1.0 (or JSON for zaproxy), then
normalize, aggregate and deduplicate the findings into a consolidated report.
- Python 3.12+, package manager uv (
uv run python ...,uv sync). - Scanner binaries live under
tools/<family>/<tool>/and are referenced by relative paths (./tools/...). Therefore the server and CLI must run from the repo root —cli.pydoesos.chdir(REPO_ROOT)for this reason. - Generated reports go to
./reports/scan_<timestamp>_<mode>/(git-ignored).
Module map
| File | Role |
|---|---|
security/<tool>.py |
One module per scanner. Exposes a single async *_impl(project_dir) (or (target_url), or (project_dir, language)) returning List[types.TextContent] whose text is raw SARIF/JSON. |
scanners.py |
Single source of truth: the SCANNERS registry (Scanner dataclass) + scanners_for_mode(). Everything downstream is driven by this list. |
report.py |
extract_findings(tool, fmt, text) normalizes SARIF/JSON → flat findings; build_report() + render_json/md/html() produce the consolidated report. |
aggregate.py |
Runs all scanners of a mode, dedupes (deduplicate()), and run_and_persist() writes the report. Backs the aggregated MCP tools. |
config.py |
Loads .env and resolves per-scanner toggles (scanner_enabled(), env_var_for()). |
server.py |
FastMCP tool definitions — one per scanner + the aggregated static_scan/dynamic_scan. |
cli.py |
Command-line runner. Picks up scanners from the registry automatically. |
tests/test_scanners.py |
End-to-end harness: one fixture per family under tests/examples/, asserts each scanner emits valid SARIF/JSON. |
tools/<family>/<tool>/install.sh |
Per-tool installer (relative paths, run from its own dir). tools/install-all.sh runs them all; tools/uninstall.sh removes binaries. |
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 · 117 lines · 1,871 tokens per session scan A ccb37e3ea471
security_mcp CLAUDE.md is an instructions file published in the GitHub repository michoo/security_mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,871 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.