agent-skills: Instructions file for Claude Code

CLAUDE.md

agent-skills CLAUDE.md is an instructions file for Claude Code from jasonkneen/agent-skills. It costs 2,764 tokens per session, scanned B, original, MIT.

A repository guide for agent-skills, a pnpm monorepo—a single repository containing several related packages—for Claude Code extensions.

In plain words
What is it for?
Use it when working on the TypeScript MCP servers, agent skills, or Node.js hooks, including building, testing, linting, type-checking, and development mode.
Why use it?
It gives agents the project layout, build and test commands, and the conventions for its tools, skills, and hooks.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is jasonkneen/agent-skills's own configuration. It tells Claude Code how to work on agent-skills 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 agent-skills configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/specific/path.

Reuse

Borrowing it

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

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 agent-skills CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jasonkneen/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jasonkneen/agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,764 This file is loaded in full into every session.
When invoked 2,764 The same file — it is already loaded in full.
Security scan B 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 $0.02764 $0.02764
Opus 5 $0.01382 $0.01382
Sonnet 5 $0.00553 $0.00553
Haiku 4.5 $0.00276 $0.00276

Measured 9d ago against content hash b577ede04583, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

agent-skills CLAUDE.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

7. Test by adding to `~/.claude/settings.json` mcpServers config
CLAUDE.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 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.

Build Commands

  • Build all packages: pnpm build
  • Build specific package: cd packages/<name> && pnpm build
  • Dev mode (watch): pnpm dev or cd packages/<name> && pnpm dev
  • Type check: pnpm typecheck
  • Lint: pnpm lint
  • Test: pnpm test
  • Clean: pnpm clean

Project Structure

This is a pnpm monorepo containing Claude Code extensions:

claude-skills/
├── packages/          # MCP servers (TypeScript, builds to dist/)
│   ├── mcp-github-issues/
│   └── mcp-debug-cycle/
├── skills/           # Agent Skills (SKILL.md format)
│   └── code-review/
└── hooks/            # Claude Code hooks (Node.js scripts)
    ├── cost-monitor/
    ├── notify-complete/
    └── tdd-enforcement/

Architecture

MCP Servers (packages/)

TypeScript packages following MCP SDK patterns:

  • Entry: src/index.ts exports Server from @modelcontextprotocol/sdk/server/index.js
  • Tools: src/tools/*.ts export Tool definitions and implementation functions
  • Utils: src/utils/*.ts for shared logic (e.g., gh-cli.ts wraps GitHub CLI)
  • Build: TypeScript compiles src/dist/, using tsconfig.base.json + package-level tsconfig.json
  • Execution: dist/index.js is the MCP server entry point (runs via node)

Tool implementations follow this pattern:

export const toolName: Tool = {
  name: "mcp_tool_name",
  description: "...",
  inputSchema: { /* Zod or JSON Schema */ }
}

export async function toolName(args: ArgsType): Promise<ToolResponse> {
  // Implementation
}

Agent Skills (skills/)

Agent Skills Specification (agentskills.io) compliant format:

  • Structure: Each skill is a directory with SKILL.md as the manifest
  • Frontmatter: YAML with required fields name (lowercase-hyphen only) and description
  • Content: Markdown body with skill instructions, using XML-style tags for structure:
    • <essential_principles> - Core philosophy and rules
    • <intake> - User-facing prompt for skill invocation
    • <routing> - Pattern matching to workflow files
    • <reference_index> - Links to reference docs
    • <workflows_index> - Available workflow files
  • Supporting files:
    • references/ - On-demand docs (e.g., checklists, common issues)
    • workflows/ - Step-by-step procedures (e.g., review-diff.md)
    • scripts/ - Executable code (if needed)
    • assets/ - Templates, data files

Read the full file on GitHub · 319 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. 9d ago First seen · 319 lines · 2,764 tokens per session scan B b577ede04583

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository jasonkneen/agent-skills (20 stars, last pushed 8mo ago), licensed MIT. It adds 2,764 tokens to every session, about $0.0138 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens