What is skillz CLAUDE.md?

A set of repository instructions for Skillz, a TypeScript command-line tool that finds Claude Agent Skills and copies them into configured folders. It documents the project structure, commands, and tests.

Use it when developing, testing, linting, formatting, or operating Skillz commands such as init, sync, list, create, edit, and watch.

It gives a coding agent the project’s expected commands and working conventions, including which command must not be run. This reduces the chance of building or testing the CLI incorrectly.

How kevinslin/skillz configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinslin/skillz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kevinslin/skillz/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kevinslin/skillz

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kevinslin/skillz/claude-md/github.svg)](https://agentmods.dev/instructions/kevinslin/skillz/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kevinslin/skillz/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinslin/skillz/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kevinslin/skillz/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinslin/skillz/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,033 This file is loaded in full into every session.

When invoked 2,033 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02033	$0.02033
Opus 5.5	$0.00813	$0.00813
Sonnet 5.5	$0.00407	$0.00407
Haiku 4.5	$0.00203	$0.00203

Measured 2mo ago against content hash de0b29ea1c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skillz 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 2mo 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.

CLAUDE.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

Project Overview

Skillz is a TypeScript CLI that scans Claude Agent Skills (SKILL.md files) and copies them into configured target directories such as .skills. If a .skills/ directory exists in the repo, check it for additional local skills alongside configured skill directories.

Current commands include init, sync, list, create, edit, and watch.

Essential Commands

Development

npm run build          # Compile TypeScript and copy template assets to dist/
npm run dev            # Run the TypeScript compiler in watch mode
npm test               # Full build plus Jest test suite
npm run test:watch     # Jest in watch mode
npm test -- <file>     # Run a specific test file
npm run lint           # Run ESLint
npm run format         # Run Prettier

Never run npm run precommit.

Testing the CLI

node dist/cli.js init --preset agentsmd --no-sync
node dist/cli.js create test-skill "A test skill description"
node dist/cli.js sync --dry-run --verbose

Architecture

Data Flow

1. Config (skillz.json) -> targets and skill source directories
2. Scanner (skill-scanner.ts) -> finds all SKILL.md files
3. Parser (skill-parser.ts) -> extracts frontmatter and content
4. Cache (.skillz-cache.json) -> stores hashes for change detection
5. Change Detector -> compares current skills and config against cache
6. Native Target Manager -> validates target directories and copies skills
7. Cache Manager -> writes updated cache after successful sync

The sync command detects both skill-file changes and skillz.json changes. Config edits trigger a sync path without needing --force.

Core Modules

src/core/config.ts

Loads, saves, validates, and migrates skillz.json.
getDefaultConfig(preset) returns preset configs.
inferConfig(cwd) detects .skills and known skill source directories.
Legacy string targets and name targets migrate to { destination } targets.

Read the full file on GitHub · 278 lines

Changes

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.

2mo ago First seen · 278 lines · 2,033 tokens per session scan A de0b29ea1c9b

Subscribe to this mod's changes

skillz CLAUDE.md is an instructions file published in the GitHub repository kevinslin/skillz (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,033 tokens to every session, about $0.0081 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 2026-08-31.

skillz CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skillz CLAUDE.mdkevinslin/skillz	Instructions file	8	3mo ago	Apache-2.0	A	2,033	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

skillz: Instructions file for Claude Code