Borrowing it
Nothing to install: this file belongs to flurdy/agent-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/flurdy/agent-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/flurdy/agent-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/flurdy/agent-skills/claude-md)<a href="https://agentmods.dev/instructions/flurdy/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/flurdy/agent-skills/claude-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/flurdy/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/flurdy/agent-skills/claude-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 | $0.00918 | $0.00918 |
| Opus 5.5 | $0.00367 | $0.00367 |
| Sonnet 5.5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
agent-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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo guide
Assembles Claude Code skills and agents from layered source dirs into
~/.claude/{skills,agents} as symlinks. See README.md for the full model (layers,
profiles, machines, clients) and make help for every target.
Also supports other LLMs and harnesses such as Codex, Gemini, Pi, and OpenRouter
that can use the same skills and agents. See README.md for the full model.
After changing skills or agents
The active dirs hold symlinks into this repo, so editing files inside an existing skill/agent is live immediately — no re-apply needed. But adding, renaming, or removing a skill/agent dir changes the set of symlinks, so re-apply:
make validate-skills— check skill metadata, catalog parity, and local referencesmake test-validate-skills— run the validator's fixture suite after validator changesmake dry-run— preview what would change (read-only)make apply— (re)create the symlinks; run after a new / renamed / removed unitmake doctor— check for broken or duplicate linksmake apply-codex— same for Codex (skips agents)
make apply cleans and re-applies all managed symlinks each run, leaving your own
non-managed skills/agents untouched. Options (PROFILE, MACHINE, CLIENTS, FORCE) are
in README.md.
Documentation placement
Keep public user, contributor, and component-contract documentation beside its component.
Keep generated or disposable output under ignored /.artifacts/; do not commit raw run output
without an explicit retention decision. Mark superseded durable records with their replacement,
not a generic archive folder.
Public repository: no client details
This repo is public. Never commit employer or client specifics in skills, examples, tests,
fixtures, or docs: Jira project keys, real ticket numbers or summaries, sprint or board names,
custom field values, branch names, hostnames, repo or service names, or people. Use neutral
placeholders (ABC-123, ABC Sprint 1, example.atlassian.net). Generic workflow terms such as
Ready for QA are fine. Real values belong in the private workspace config the skill reads, or in
the private client layer (agent-skills-private).
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.
- 7d ago Changed · +9 lines · +127 tokens per session 5209eba46b70
- 24d ago Changed · +3 lines · +64 tokens per session 4314dff8e610
- 1mo ago Changed · +5 tokens per session 14798e7a8dc7
- 2mo ago First seen · 54 lines · 722 tokens per session scan A 92527249326e
agent-skills CLAUDE.md is an instructions file published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 918 tokens to every session, about $0.0037 per session on Opus 5.5. 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.
agent-skills CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-skills CLAUDE.mdflurdy/agent-skills | Instructions file | 9 | 3d ago | MIT | A | 918 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |