Borrowing it
Nothing to install: this file belongs to skilletmd/skillet. 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/skilletmd/skillet/main/CLAUDE.mdgit clone --depth 1 https://github.com/skilletmd/skilletWrote 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/skilletmd/skillet/claude-md)<a href="https://agentmods.dev/instructions/skilletmd/skillet/claude-md"><img src="https://agentmods.dev/badge/instructions/skilletmd/skillet/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 5.1 | $0.02686 | $0.02686 |
| Opus 5 | $0.01343 | $0.01343 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
skillet CLAUDE.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
alone — curl the endpoint with the client's real `Accept` header. How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for agents (and humans) working in this repo. Conventions, setup, and commit format live in CONTRIBUTING.md; domain vocabulary in docs/CONCEPTS.md; review guidance in docs/REVIEW.md. This file holds what you'd otherwise learn the hard way.
Skillet is a registry + sync system for agent skills: publish a skill once, run it in every agent runtime. Monorepo (pnpm workspaces):
| Package | What it is |
|---|---|
packages/web |
Next.js app (skillet.md) — profiles, kits, feed, updates |
packages/registry |
Fastify + Prisma/MySQL API (:3481 in dev) |
packages/cli |
skilletmd — the skillet command |
packages/core |
Sync engine shared by CLI + desktop sidecar |
packages/protocol |
Wire types, signatures, covers — shared by everything |
packages/desktop |
Tauri tray app; bundles the CLI as a sidecar |
packages/adapters/* |
Per-runtime install adapters |
packages/mcp |
MCP server surface |
Build reality (read before trusting failures)
Workspace packages resolve through gitignored dist/ directories. A fresh
clone, a fresh worktree, or a rebase that touched packages/protocol or
packages/core leaves stale or missing dist, which produces phantom failures:
"Failed to resolve entry for package @skillet/protocol", missing-export runtime
errors, or test failures unrelated to your diff.
pnpm build orders the workspace correctly, so building from the repo root is
enough:
pnpm install
pnpm build
Ordering used to be unreliable: core devDepended on registry for its e2e
suites, closing a core → registry → mcp → core cycle. pnpm cannot sort a cycle
topologically and ran those packages concurrently, so mcp could compile before
core emitted its dist. Those suites now live in @skillet/core-e2e, which
nothing depends on, and the graph is acyclic — if you see a build-order failure
again, check whether a new edge has re-closed the loop.
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.
- 8d ago First seen · 182 lines · 2,686 tokens per session scan A c33b9f69f3bb
skillet CLAUDE.md is an instructions file published in the GitHub repository skilletmd/skillet (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,686 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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).
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.
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.