What is skills CLAUDE.md?

Instructions for a repository of Markdown guides that teach AI agents how to use the MoonPay command-line tool. The guides cover the repository layout, guide format, and how to add new guides.

Navigating the skills repository, writing new instruction guides, following naming conventions, and checking the required guide structure.

They explain the project’s conventions and make it easier to create or update guides that agents can load for specialized tasks.

How moonpay/skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to moonpay/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/moonpay/skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/moonpay/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/moonpay/skills/claude-md/github.svg)](https://agentmods.dev/instructions/moonpay/skills/claude-md)

Your own site

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

Per session 516 This file is loaded in full into every session.

When invoked 516 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	$0.00516	$0.00516
Opus 5.5	$0.00206	$0.00206
Sonnet 5.5	$0.00103	$0.00103
Haiku 4.5	$0.00052	$0.00052

Measured 2mo ago against content hash 5b94830513bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 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.

Overview

This is a repository of Agent Skills for crypto infrastructure. Skills are Markdown-based instruction files that AI agents (Claude Code, Claude API, MCP clients) load dynamically to perform specialized tasks via the MoonPay CLI (mp).

Skills are not code — they are instructional guides. All execution happens through the MoonPay CLI (@moonpay/cli). There is no build, test, or lint step.

Repository Structure

skills/ — All skill definitions (each skill is a directory with a SKILL.md)
.claude-plugin/marketplace.json — Plugin registry listing all skills
template/SKILL.md — Template for creating new skills

Skill Anatomy

Each skill is a directory under skills/ containing a single SKILL.md file with YAML frontmatter:

---
name: skill-name
description: When to use this skill and what it does
tags: [tag1, tag2]        # Optional
---

The body contains instructions for the agent: setup commands, workflows, configuration, and references to other skills. The repo-level LICENSE covers all skills.

Adding a New Skill

Create skills/{name}/SKILL.md using the template in template/SKILL.md
Add the skill entry to .claude-plugin/marketplace.json
The PR template (.github/PULL_REQUEST_TEMPLATE.md) defines the required checklist

Naming Convention

MoonPay skills: skills/moonpay-{name}/ (e.g., moonpay-swap-tokens)
Partner skills: skills/{partner}-{name}/ (e.g., corbits-marketplace, dune-analytics)

Key Conventions

The description field in YAML frontmatter should be specific about when Claude should trigger the skill — this is how agents decide which skill to load
Many skills reference each other (e.g., swap recommends check-wallet and discover-tokens) — maintain these cross-references when editing
Skills instruct agents to use config files under ~/.config/ (e.g., ~/.config/moonpay/, ~/.config/pump-fun-sniper/)
The MoonPay CLI binary is invoked as mp in skill instructions

Read the full file on GitHub · 46 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 · 46 lines · 516 tokens per session scan A 5b94830513bd

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository moonpay/skills (112 stars, last pushed 19d ago), licensed MIT. It adds 516 tokens to every session, about $0.0021 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 2026-08-30.

skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills CLAUDE.mdmoonpay/skills	Instructions file	112	19d ago	MIT	A	516	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

skills: Instructions file for Claude Code