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/mctar/skill-check/claude-mdgit clone --depth 1 https://github.com/mctar/skill-checkWrote 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/mctar/skill-check/claude-md)<a href="https://agentmods.dev/instructions/mctar/skill-check/claude-md"><img src="https://agentmods.dev/badge/instructions/mctar/skill-check/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 | $0.00881 | $0.00881 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
skill-check 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 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.
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 — 91 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
Skill Check is a security analysis tool for Claude skills (SKILL.md-based prompt extensions). It runs seven static-analysis checks against a skill's files to detect known threat patterns. Ships as two artifacts with identical detection logic: a standalone Python script (zero dependencies, Python 3.8+) and a Claude skill wrapper.
Repository: gervilabs/skill-check Authors: Gervi Labs (Thordur Arnason & Lena Thorsmæhlum)
Architecture
scanner/skill_check.py # Single-file standalone scanner (zero external deps)
rules/threat_rules.json # Detection rules (human-readable JSON, separate from code)
tests/malicious/ # 7 red-team test skills (one per check)
tests/benign/ # 3 false-positive verification skills
tests/test_skill_check.py # Automated test runner
SKILL.md # Claude skill wrapper
CAPABILITY.md # Honest limitations document
docs/threat_model.md # Detailed threat model
Key design decision: one Python file + one JSON rules file. Rules are separate so they can be audited without reading code. This separation is a trust signal.
The Seven Checks
Each check is independent (pass/fail on its own). Ordered by detection confidence:
- Arcana (Remote Code Execution) — highest confidence
- Perception (Exfiltration)
- Sleight of Hand (Credential Harvesting)
- Survival (Filesystem Overreach)
- Investigation (Obfuscation)
- History (Dependency Risk)
- Insight (Behavioral Manipulation) — lowest confidence
Names reference tabletop RPG ability checks; each is always paired with a plain-language label.
Scanner Core Classes
Finding— single detected issue (file, line, rule_id, check, severity, matched content)CheckResult— result of one check (name, pass/fail, list of Findings)ScanResult— all seven CheckResults + summaryRuleEngine— loads rules from threat_rules.json, applies by checkSkillScanner— orchestrates the seven checks against a skill directory
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 · 91 lines · 881 tokens per session scan A 57009b308e55
skill-check CLAUDE.md is an instructions file published in the GitHub repository mctar/skill-check (2 stars, last pushed 6mo ago), licensed MIT. It adds 881 tokens to every session, about $0.0044 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 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.