Borrowing it
Nothing to install: this file belongs to ommakes/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/ommakes/Skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/ommakes/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/ommakes/skills/claude-md)<a href="https://agentmods.dev/instructions/ommakes/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ommakes/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/ommakes/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ommakes/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 | $0.01184 | $0.01184 |
| Opus 5.5 | $0.00474 | $0.00474 |
| Sonnet 5.5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00118 | $0.00118 |
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 6d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repo
Short notes for anyone (human or agent) changing validators, detectors, or the rule data. They come from review findings we have already had to fix once.
Before every push
Run what CI runs:
node scripts/check-rule-sync.mjs
python3 scripts/check-routing.py
bash scripts/validate-skills.sh
node vois-tokens/scripts/detect.test.mjs
node vois-teams/scripts/validate.test.mjs
node vois-teams/scripts/validate.mjs all
node vois-eval/check-scenarios.mjs
node vois-eval/lookalike-pass/scan.test.mjs
node vois-components/scripts/motion-logic.test.mjs
node vois-dataviz/scripts/dataviz.test.mjs
node scripts/check-mirror.mjs --private <path to a checkout of ommakes/vois-skills>
motion-logic.test.mjs needs Node 22.13 or newer.
Then read your own diff as if someone else wrote it, looking for the classes below. For anything that touches a validator, detector or regex, get a second set of eyes (a /code-review run or a fresh subagent that has not seen your reasoning) before pushing. Every Bugbot round so far found things the author could have found by reading the diff once more.
Checklist for a validator, detector or regex
- Equality. What does "equal" mean for each value? Sets are unordered (
[4,8]equals[8,4]). Compare a canonical form, not raw JSON. - Identity. Which fields identify something, and is each one checked for uniqueness? Every id field, not just the first one you thought of, and across files as well as inside one.
- Matching text. A match string must hit exactly once, and must not hit inside a longer number or word (
8inside80,2 to 5inside a rationale). - Patterns. Does each pattern match where intended and nowhere else? Try a different order, separator, casing, empty value, null, and a very long input.
[^>]*stops at the>in=>. A substring test like "contains load" also matchessetUploadSuccess. A name test liketitle=also matchesdata-title=. - Paths and globs. Test root-relative,
./, leading/, absolute and Windows (\) paths. If a validator and a hook both read the same globs, they must share one definition (braces, folder-covers-contents, case). A change to one means a change to the other. - Bad config fails closed. A malformed scope, schema or value must make the rule stricter or skipped, never wider. Never let a wrong type turn into "applies everywhere".
- Guards need a test from the other side. For each guard, write the input that tries to get past it from an unexpected direction, and watch the test fail without the guard.
- Claims in docs and rule text. Counts, version numbers and "the check does X" sentences must be checked against the code. If the row says it flags
x, run it onx.
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.
- 6d ago Changed · +62 tokens per session 540b283dd89f
- 7d ago Changed · +3 lines · +29 tokens per session b0315dd79e7f
- 8d ago Changed · +4 lines · +225 tokens per session 44381fd96b58
- 9d ago First seen · 44 lines · 868 tokens per session scan A 2e375fb08efa
Skills CLAUDE.md is an instructions file published in the GitHub repository ommakes/Skills (21 stars, last pushed 7d ago), licensed MIT. It adds 1,184 tokens to every session, about $0.0047 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 2026-10-08.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).