Borrowing it
Nothing to install: this file belongs to kumekay/skiletto. 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/kumekay/skiletto/main/CLAUDE.mdgit clone --depth 1 https://github.com/kumekay/skilettoWrote 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/kumekay/skiletto/claude-md)<a href="https://agentmods.dev/instructions/kumekay/skiletto/claude-md"><img src="https://agentmods.dev/badge/instructions/kumekay/skiletto/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/kumekay/skiletto/claude-md"><img src="https://agentmods.dev/badge/instructions/kumekay/skiletto/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 | $0.00692 | $0.00692 |
| Opus 5 | $0.00346 | $0.00346 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
skiletto 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skiletto
Package manager for agent skills: manifest (skiletto.toml) for user intent,
lockfile (skiletto.lock) pinned to commit SHAs, reproducible installs.
The design doc lives in the GitHub wiki and is the source of truth for behavior, file formats, CLI semantics, and architecture: https://github.com/kumekay/skiletto/wiki. Read it before changing anything substantial.
Development rules
- Red-green TDD, no exceptions. Write a failing test first, run it and watch it fail, then write the minimum code to make it pass, then refactor. No production code without a failing test that demanded it.
- Hooks: run
lefthook installonce after cloning. Pre-commit runs gofmt and golangci-lint; pre-push runsgo test ./.... CI runs the same hooks plus tests, so if hooks fail locally, CI fails too. - Thin CLI layer:
internal/clionly parses flags/args, callsinternal/engine, and formats output. Business logic never lives in command handlers. - Commit messages and PR bodies: imperative, describe the change, nothing else. No tool attribution, no generated-by lines, no co-author trailers.
Releases
- To release: confirm CI is green on main, then push a version tag
(
git tag vX.Y.Z && git push origin vX.Y.Z). Never tag ahead of green CI. - The tag triggers the release workflow: goreleaser builds the binaries and creates the GitHub release, then the wrappers publish to PyPI and npm, both via trusted publishing (OIDC) — no registry secrets. Every release must end with all three verified: the GitHub release exists and the new version is live on PyPI and npm.
Easy to miss
- Never merge PRs unless the user explicitly says so. Open the PR, wait for review; merging is the user's call.
- Keep the wiki in sync. Any change to file formats, CLI behavior, the
install model, or architecture must be reflected in the wiki design doc as
part of the same piece of work
(
git clone [email protected]:kumekay/skiletto.wiki.git, editHome.md, push). - Keep README.md honest. It must describe the actually-implemented CLI — never planned-but-unbuilt features.
syncnever moves locked versions; onlyupdatere-resolves refs.syncprunes only entries it itself removes from the lock, and never deletes a drifted skill without--force.- Drifted skills (content hash mismatch): warn and skip, never overwrite silently.
skiletto.tomlandskiletto.lockcontain only canonical URLs — shorthands likeowner/repoare expanded ataddtime, in the CLI layer.- Editable (path) skills have no commit/hash in the lock and are excluded from drift checks.
- Every interactive prompt must have a flag equivalent. No TTY + ambiguous invocation = actionable error listing choices; never hang waiting for input.
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 · 56 lines · 692 tokens per session scan A 9303b3a53df9
skiletto CLAUDE.md is an instructions file published in the GitHub repository kumekay/skiletto (2 stars, last pushed 7d ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 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).
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.