openskill: Instructions file for Claude Code

CLAUDE.md

openskill CLAUDE.md is an instructions file for Claude Code from vudknguyen/openskill. It costs 2,033 tokens per session, scanned A, original, MIT.

Repository instructions for OpenSkill, a command-line tool that manages skills for several AI coding assistants. They describe the project layout, commands, architecture, and how to add commands or agents.

In plain words
What is it for?
Use them when building, testing, or extending OpenSkill, including adding CLI commands or agents and running its TypeScript development commands.
Why use it?
They give an AI coding assistant the project context needed to work in the repository without guessing where code, tests, and documentation belong.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is vudknguyen/openskill's own configuration. It tells Claude Code how to work on openskill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openskill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vudknguyen/openskill. 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/vudknguyen/openskill/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vudknguyen/openskill

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.

agentmods badge for openskill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vudknguyen/openskill/claude-md/github.svg)](https://agentmods.dev/instructions/vudknguyen/openskill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vudknguyen/openskill/claude-md"><img src="https://agentmods.dev/badge/instructions/vudknguyen/openskill/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.

agentmods 80×15 button for openskill CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vudknguyen/openskill/claude-md"><img src="https://agentmods.dev/badge/instructions/vudknguyen/openskill/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 1 finding. 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.

ModelPer sessionOnce 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 a46b1196ac5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openskill 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

│ ├── git.ts # Git operations via Node child_process
CLAUDE.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 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 (claude.ai/code) when working with code in this repository.

Quick Reference for AI Agents

  • Entry point: src/cli/index.ts
  • Add new commands: Create file in src/cli/, register in index.ts
  • Add new agents: Implement Agent interface in src/agents/, register in src/agents/index.ts
  • Tests: src/__tests__/*.test.ts (run with npm test)
  • Full architecture docs: docs/architecture.md

Project Overview

OpenSkill (osk) is a lightweight, agent-agnostic CLI for managing AI coding agent skills. Supports Claude Code, Antigravity, OpenAI Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Windsurf, Kiro, Warp, OpenClaw, and the generic Agents spec.

Build Commands

npm install          # Install dependencies
npm run build        # Compile TypeScript to dist/
npm run dev          # Watch mode for development
npm test             # Run tests with vitest

Running the CLI

node dist/cli/index.js <command>   # Run locally
osk <command>                      # After npm link

Architecture

src/
├── cli/           # Command handlers (commander.js)
│   ├── index.ts   # Entry point
│   ├── install.ts # Install with interactive agent/skill selection
│   └── ...        # list, uninstall, update, search, browse, repo, config, etc.
├── core/          # Business logic
│   ├── config.ts  # JSON config (~/.openskill/config.json)
│   ├── git.ts     # Git operations via Node child_process
│   ├── skill.ts   # Skill parsing/validation
│   ├── registry.ts # Git repository cache operations
│   └── manifest.ts # Installed skills tracking (~/.openskill/manifest.json)
├── agents/        # Agent adapters (strategy pattern)
│   ├── types.ts   # Agent interface
│   └── *.ts       # claude, antigravity, codex, cursor, gemini, copilot, opencode, windsurf, kiro, warp, openclaw, agents
└── utils/
    ├── logger.ts  # ANSI colors (no deps)
    ├── prompt.ts  # Interactive prompts (@inquirer/prompts)
    ├── markdown.ts # Frontmatter parsing (gray-matter)
    └── fs.ts      # File helpers

Read the full file on GitHub · 186 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.

  1. 2mo ago First seen · 186 lines · 2,033 tokens per session scan A a46b1196ac5e

Subscribe to this mod's changes

openskill CLAUDE.md is an instructions file published in the GitHub repository vudknguyen/openskill (10 stars, last pushed 6mo ago), licensed MIT. 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 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

openskill CLAUDE.md compared with instructions from other repositories

openskill CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openskill CLAUDE.mdvudknguyen/openskillInstructions file106mo agoMITA2,033Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot