What is skills CLAUDE.md?

Repository instructions for a marketplace of reusable instruction packages, called skills, for AI coding agents. They explain the required SKILL.md format, repository layout, testing, and evaluation materials.

Adding or updating skills, using the starter template, organizing scripts and reference files, and working with the marketplace's specifications and benchmarks.

They help contributors create skills that follow the marketplace's structure and can be used consistently by different coding agents.

How bmad-labs/skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bmad-labs/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/bmad-labs/skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bmad-labs/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bmad-labs/skills/claude-md/github.svg)](https://agentmods.dev/instructions/bmad-labs/skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bmad-labs/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/bmad-labs/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.

Your own site · 80×15

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

Per session 635 This file is loaded in full into every session.

When invoked 635 The same file — it is already loaded in full.

Security scan C 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.

Model	Per session	Once invoked
Fable 5.1	$0.00635	$0.00635
Opus 5.5	$0.00254	$0.00254
Sonnet 5.5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured 2d ago against content hash 742c16d5472f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

skills CLAUDE.md scanned grade C 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. Clear cache: `rm -rf ~/.claude/plugins/cache`

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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.

Repository Purpose

This is the BMAD Skills Marketplace — a collection of skills for Claude Code and other AI agents (Cursor, Codex, OpenCode, etc.). Skills are self-contained instruction sets defined in SKILL.md files that extend agent capabilities.

Architecture

skills/[skill-name]/
├── SKILL.md         # Required: YAML frontmatter + instruction content
├── scripts/         # Optional: helper scripts
├── references/      # Optional: reference documentation
└── assets/          # Optional: images, resources

Key directories:

skills/ — all skill implementations (20+ skills)
template/ — starter template for new skills
spec/ — skills specification documentation
_bmad/ — BMAD workflow automation framework (roles, phases, orchestration)
.claude/skills/ — installed BMAD skills for Claude Code
books/ — source books used by book-related skills

SKILL.md Format

Every skill requires a SKILL.md with YAML frontmatter:

---
name: skill-name          # lowercase, hyphenated, unique
description: >            # Complete description of what the skill does
  and when Claude should use it. This drives auto-invocation.
---

Content guidelines: specific and actionable instructions, real examples, under 500 lines, link to scripts/docs instead of inlining large content.

Evaluations and Benchmarks

!IMPORTANT: Evaluation and benchmark results for each skill are stored in evaluations/skills/<skill-name>/:

Testing a Skill Locally

Install a skill by adding it to .claude/settings.json:

{
  "skills": ["/absolute/path/to/skills/your-skill-name"]
}

Then verify in Claude Code: ask "What skills are available?" or run /plugin.

Validating Plugin Structure

claude plugin validate .

Creating a New Skill

Copy the template: cp -r template/ skills/your-skill-name/
Edit SKILL.md frontmatter and content
Update the skills table in README.md
Test locally, then submit a PR from branch skill/your-skill-name

Read the full file on GitHub · 89 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.

2d ago Changed 742c16d5472f
2mo ago First seen · 89 lines · 635 tokens per session scan C 32c3e53810f4

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository bmad-labs/skills (19 stars, last pushed yesterday), licensed MIT. It adds 635 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills CLAUDE.mdbmad-labs/skills	Instructions file	19	yesterday	MIT	C	635	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

skills: Instructions file for Claude Code