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/ngmeyer/skills/claude-mdgit clone --depth 1 https://github.com/ngmeyer/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/ngmeyer/skills/claude-md)<a href="https://agentmods.dev/instructions/ngmeyer/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ngmeyer/skills/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 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
skills 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This repo is a published library of agent skills (ngmeyer/skills). It is distributed via skills.sh (npx skills add ngmeyer/skills) and as a Claude Code plugin marketplace (/plugin marketplace add ngmeyer/skills).
Layout
skills/<category>/<name>/SKILL.md— one skill per directory. Shipping categories:engineering,productivity.skills/<category>/<name>/references/— progressive-disclosure depth, loaded on demand.skills/<category>/<name>/scripts/— deterministic helpers (sort, validate, format) the model shouldn't reason through.skills/<category>/<name>/tests/eval.sh— structural eval asserting the SKILL.md's design contract. There is no CI — run it manually before pushing (see Releasing).- A skill dir holds only
SKILL.md(+ optionalreferences//scripts/) andtests/(withtests/README.mddocumenting the eval). No rootREADME.mdinside a skill dir —SKILL.mdis the doc. .claude-plugin/plugin.json— lists the shipped skills + marketplace metadata (description, version, author).
Only ship-ready skills appear in plugin.json — that file is the canonical list of what ships (don't hardcode a count here; it drifts). New candidates incubate in a separate workspace until validated.
Adding or editing a skill
- Author with the
skillforgeskill (it enforces frontmatter, progressive disclosure, mandatory Gotchas). - Frontmatter is
name+description(Matt-Pocock convention). Keep SKILL.md under Anthropic's 500-line bar; push detail intoreferences/. - Add
tests/eval.shwith structural assertions (heading shape, anti-pattern checks, portability — see existing skills for the pattern). - Add the path to
.claude-plugin/plugin.json. - Optimize to V2 with
skillforge optimize <skill>once it has a real outcome to measure; record the V1→V2 delta in the skill's## Changelog.
Public-repo hygiene
Every commit to main is public. No skill may contain:
- Hardcoded user paths (
/Users/<name>,/Volumes/...,~/.claude/projects/...). Use$HOME,~, or placeholders. - Private project names, internal product/repo references, or business metrics in examples.
- Secrets, secret locations, or credentials of any kind.
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 · 50 lines · 938 tokens per session scan A e6e67538fdf0
skills CLAUDE.md is an instructions file published in the GitHub repository ngmeyer/skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0047 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
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
cetus AGENTS.md
Instructions for drewnekota/cetus, covering repository instructions and releases.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
Product-Marketing-Skills CLAUDE.md
Instructions for stefanoskarakasis/Product-Marketing-Skills, covering claude.md, versioning & releases, release procedure (manual, until ci enforcement exists) and after any repo change.