Anthropic Cybersecurity Skills is a library of structured cybersecurity procedures for AI agents, covering security domains and mappings to established security frameworks. It is for authorized security analysis, penetration testing, incident response, research, defense, and education across compatible AI platforms. The catalogue entries package parts of this library as agent skills, instructions, or a plugin.
Borrowing it
Nothing to install: this file belongs to mukul975/Anthropic-Cybersecurity-Skills. 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/mukul975/Anthropic-Cybersecurity-Skills/main/AGENTS.mdgit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-SkillsWrote 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/mukul975/anthropic-cybersecurity-skills/agents-md)<a href="https://agentmods.dev/instructions/mukul975/anthropic-cybersecurity-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/mukul975/anthropic-cybersecurity-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mukul975/anthropic-cybersecurity-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/mukul975/anthropic-cybersecurity-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
Anthropic-Cybersecurity-Skills AGENTS.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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents working in this repository.
What this repository is
A library of 817 cybersecurity skills. Each skill is a directory under skills/ containing a SKILL.md — YAML frontmatter plus a Markdown procedure — following the agentskills.io standard.
The layout is flat: skills/<skill-name>/SKILL.md. Do not nest skills by domain; agents discover them by scanning skills/*/SKILL.md.
Reading a skill
Only name and description load at discovery time. The body loads once the description matches the request; references/, scripts/ and assets/ load only when referenced.
Read the description first. If it carries a negative trigger — "Do not use for X — use other-skill" — honour it. Those exist because two skills would otherwise compete for the same request.
Changing a skill
Frontmatter is parsed by tools/skill_frontmatter.py, which uses PyYAML. Do not write a regex frontmatter parser; CI fails the build if it detects one. Three hand-rolled parsers previously truncated 604 of 817 descriptions to their first line.
After changing any SKILL.md:
pip install pyyaml
python tools/validate-skill.py --all
python tools/validate-agentskills.py --strict
python tools/generate-index.py # regenerate index.json
python tools/lint-descriptions.py --all
python tools/detect-collisions.py
All five run in CI. index.json is generated — never edit it by hand.
Writing a description
The description is the only signal another agent sees when deciding whether to load the skill. It needs four things:
- What it does, concretely.
Use when …— the phrasings a user would actually type.Keywords:— tool names, event IDs, CVEs, API calls.Do not use for X — use other-skill.— the negative trigger.
Keep it under 1024 characters. Keep the body under 500 lines; depth belongs in references/.
Constraints
namemust equal the directory name, lowercase-kebab, ≤64 characters.domainis alwayscybersecurity.subdomainmust be one the validator accepts — see CONTRIBUTING.md.- Scripts must run. No placeholders, no invented API endpoints, no fabricated CVE numbers.
- Framework IDs must be real and current. A wrong mapping sends an investigation the wrong way; omit rather than guess.
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.
- 10d ago First seen · 55 lines · 578 tokens per session scan A 851e17c2effb
Anthropic-Cybersecurity-Skills AGENTS.md is an instructions file published in the GitHub repository mukul975/Anthropic-Cybersecurity-Skills (32,457 stars, last pushed 9d ago), licensed Apache-2.0. It adds 578 tokens to every session, about $0.0029 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
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.