agent-skills CLAUDE.md

A set of instructions for working on a repository of AI-agent skills and Claude Code commands. It explains the repository structure and how to create each format.

In plain words
What is it for?
Use it when adding skills, creating Claude Code slash commands, or understanding the purpose and layout of this repository.
Why use it?
It helps an agent follow the repository's conventions instead of guessing where skills and commands belong or how they should be written.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/arraydude/agent-skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/arraydude/agent-skills
Per session 417 This file is loaded in full into every session.
When invoked 417 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00417 $0.00417
Opus 5 $0.00209 $0.00209
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 3b7bca9bbbfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-skills 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 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.

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 · 51 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Purpose

This repository contains AI agent skills and commands in two formats:

  • Skills (skills.sh format): Auto-activate when relevant tasks detected, installed via npx skills add
  • Claude Code Commands: Explicit invocation via /command-name, installed by copying .claude/commands/

Repository Structure

skills/                          # skills.sh format skills
  <skill-name>/
    SKILL.md                     # Instructions for the agent (frontmatter + content)
    AGENTS.md                    # Full compiled document with all rules expanded
    rules/                       # Individual rule files with code examples
    metadata.json                # Version and reference information

.claude/commands/                # Claude Code native commands
  <command-name>.md              # Command file with frontmatter and instructions

Creating New Skills (skills.sh format)

Skills follow the skills.sh format:

  1. Create directory under skills/<skill-name>/
  2. SKILL.md - Main entry point with YAML frontmatter containing name, description, license, and metadata
  3. metadata.json - Version, organization, abstract, and reference URLs
  4. rules/ - Individual rule files with brief explanation + incorrect/correct code examples
  5. AGENTS.md - Compiled document containing all rules expanded (for distribution)

Creating New Claude Code Commands

Commands are Markdown files in .claude/commands/:

  1. Create .claude/commands/<command-name>.md
  2. Add YAML frontmatter with description field
  3. Use $ARGUMENTS placeholder for user input
  4. Include input validation and clear error messages
  5. Document prerequisites (e.g., required CLI tools)

Example frontmatter:

---
description: Brief description shown in command list
---
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. 2d ago First seen · 51 lines · 417 tokens per session scan A 3b7bca9bbbfe

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository arraydude/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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.