Borrowing it
Nothing to install: this file belongs to revenantworks/claude-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/revenantworks/claude-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/revenantworks/claude-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/revenantworks/claude-skills/claude-md)<a href="https://agentmods.dev/instructions/revenantworks/claude-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/revenantworks/claude-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/revenantworks/claude-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/revenantworks/claude-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 | $0.00986 | $0.00986 |
| Opus 5 | $0.00493 | $0.00493 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
claude-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 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — claude-skills
The canonical home of every Revenantworks Agent Skill (repository
revenantworks/claude-skills, renamed from citadel 2026-08-17). Two packs live under
packs/: foundation (ten -wright members, standalone profile) and gamedev
(since 2026-08-29; -smith motif, standard profile; first member pixelsmith). The
foundation pack has its own router CLAUDE.md that loads when you work under it. This root file exists because the repo's top level,
tools/, and audit/ previously loaded no standing context at all (audit
finding citadel-no-root-claude-md, 2026-08-15).
Layout
packs/<pack>/skills/<member>/— SKILL.md + references + evals; the pack's.claude-plugin/plugin.jsoncarries the pack version, which must equal its entry in.claude-plugin/marketplace.json(the build check enforces it)tools/—build.py,release.py(the whole close-of-pass loop), and the tests;audit/— COLLISION.md and audit recordsRUNBOOK.md·NEXT.md·CHANGELOG.md— operations, backlog, history
Commands
python tools/build.py --check # read-only gate: versions, counts, seams
python tools/build.py --parity # read-only: installed-copy parity
python -m unittest discover -s tools -p "test_*.py"
python tools/build.py # REAL build — regenerates references/pack.md manifests
python tools/release.py <pack>=X.Y.Z -m "..." # bump, build, check, tests, commit, tag, push, brand copies
(python on the rig, python3 on Linux clones. A bare build.py and
--footprint can WRITE manifest drift — the read-only pair above is what
report-only passes are allowed to run.)
The one arming step
The brand firewall (.claude/hooks/firewall.py, PreToolUse) fails closed:
with its gitignored blocklist.txt absent, every Write/Edit/Bash/PowerShell
call is blocked. On a fresh clone, recreate .claude/hooks/blocklist.txt
(one regex-pattern<TAB>label per line, work-identity tokens only — never a
name), then verify: python .claude/hooks/firewall.py --selftest.
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 · 66 lines · 986 tokens per session scan A aa704938a774
claude-skills CLAUDE.md is an instructions file published in the GitHub repository revenantworks/claude-skills (3 stars, last pushed today), licensed MIT. It adds 986 tokens to every session, about $0.0049 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
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).
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.
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.