Borrowing it
Nothing to install: this file belongs to paulnsorensen/easy-cheese. 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/paulnsorensen/easy-cheese/main/.github/instructions/skills.instructions.mdgit clone --depth 1 https://github.com/paulnsorensen/easy-cheeseWrote 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/paulnsorensen/easy-cheese/skills)<a href="https://agentmods.dev/instructions/paulnsorensen/easy-cheese/skills"><img src="https://agentmods.dev/badge/instructions/paulnsorensen/easy-cheese/skills/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/paulnsorensen/easy-cheese/skills"><img src="https://agentmods.dev/badge/instructions/paulnsorensen/easy-cheese/skills.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 | $0.01020 | $0.01020 |
| Opus 5 | $0.00510 | $0.00510 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
easy-cheese skills.instructions.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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL.md review checklist
Review SKILL.md changes the way /skill-creator would. The validator
already checks that name matches the directory and that frontmatter parses.
Spend your review budget on the things linters cannot see.
Frontmatter
namematches the parent directory (validator catches mismatch).descriptionis the triggering mechanism. It must:- Say what the skill does and when to invoke it.
- Include realistic user phrases ("review this diff", "fix the conflicts", "shape this into a spec"), not abstract noun phrases ("code review operations").
- Lean slightly pushy. Skills under-trigger by default. A description like "Use even when the user says 'tighten things up' before review" is fine.
- Call out boundaries — what this skill does not do — when there's a
sibling skill it could be confused with (e.g.,
/agefinds vs/curefixes).
model,allowed-tools,licenseare optional but should be consistent across siblings unless a skill genuinely needs different values.
Body length and progressive disclosure
- Aim for
SKILL.mdunder ~500 lines. Going over is fine when justified, but if instructions repeat themselves, pull them intoreferences/<topic>.mdand link fromSKILL.mdwith a one-line "read this when …" pointer. - For skills that span multiple variants (per-language fixers, per-conflict
cascade stages, per-severity findings flows), keep the selection logic in
SKILL.mdand put the variant-specific detail inreferences/. Claude only loads what it needs. - Tables of contents only earn their place in reference files >300 lines.
Bundled resources must pay rent
- Every file under
scripts/,references/,assets/has at least one reference fromSKILL.mdsaying when to use it. - Scripts encode deterministic, repeated work — if every invocation of the skill would re-derive the same shell incantation, bundle it.
- Templates and static text live in
assets/, not inlined inSKILL.md.
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.
- 9d ago First seen · 88 lines · 1,020 tokens per session scan A 72a0fa0460ca
easy-cheese skills.instructions.md is an instructions file published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed today), licensed MIT. It adds 1,020 tokens to every session, about $0.0051 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.