Borrowing it
Nothing to install: this file belongs to ericgandrade/claude-superskills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ericgandrade/claude-superskills/main/CLAUDE.mdgit clone --depth 1 https://github.com/ericgandrade/claude-superskillsWrote 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.
[](https://agentmods.dev/instructions/ericgandrade/claude-superskills/claude-md)<a href="https://agentmods.dev/instructions/ericgandrade/claude-superskills/claude-md"><img src="https://agentmods.dev/badge/instructions/ericgandrade/claude-superskills/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.
<a href="https://agentmods.dev/instructions/ericgandrade/claude-superskills/claude-md"><img src="https://agentmods.dev/badge/instructions/ericgandrade/claude-superskills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.08252 | $0.08252 |
| Opus 5 | $0.04126 | $0.04126 |
| Sonnet 5 | $0.01650 | $0.01650 |
| Haiku 4.5 | $0.00825 | $0.00825 |
Grade C, and why
claude-superskills CLAUDE.md scanned grade C with 2 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 10d 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.
rm -rf ~/.claude-superskills/cache/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
│ ├── install.sh # curl-based one-liner installer (remote) How it starts
The opening of the file, as written. The whole thing — 621 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.
Project Overview
claude-superskills is a reusable AI skills library for 8 AI platforms: GitHub Copilot CLI, Claude Code, OpenAI Codex, OpenCode, Gemini CLI, Antigravity, Cursor IDE, and AdaL CLI. Skills are Markdown-based workflow specifications (SKILL.md) that teach AI agents how to perform specific tasks.
- npm package:
claude-superskills(v2.0.8) —npx claude-superskills— 18 skills - Claude Code plugin:
claude --plugin-dir ./claude-superskills— native plugin, no npm needed - GitHub:
https://github.com/ericgandrade/claude-superskills - Old package
cli-ai-skillsis deprecated, redirects to this one
🚨 CRITICAL: VERSION CONSISTENCY RULE
You MUST keep the following files synchronized at all times when changing versions or adding skills. Failure to do so will result in deployment errors, stale marketplace metadata, and user confusion.
| File | What to Update | Authority |
|---|---|---|
cli-installer/package.json |
version field |
Source of Truth |
.claude-plugin/plugin.json |
version field |
Must match npm exactly |
README.md |
H1 Title, Version Badge, Footer | Visual confirmation |
CLAUDE.md |
Project Overview & Version Checklist | Guidance consistency |
CHANGELOG.md |
New version entry | History |
cli-installer/README.md |
Version, skill count, command examples, supported platforms | Installer docs must match current product |
cli-installer/package.json description |
Remove/add tool references when MCP servers or major features change | npm metadata is public |
.claude-plugin/marketplace.json |
Description, skill count, plugin positioning | Marketplace-facing metadata must match current product |
docs/guides/skill-anatomy.md |
Repository architecture and skill file structure | Must reflect current single-source-of-truth model |
GitHub About (gh repo edit) |
Description and topics on github.com | Public face of the repo — run gh repo edit --description "..." on every release |
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.
- 10d ago First seen · 621 lines · 8,252 tokens per session scan C db6f3388952d
claude-superskills CLAUDE.md is an instructions file published in the GitHub repository ericgandrade/claude-superskills (74 stars, last pushed 4mo ago), licensed MIT. It adds 8,252 tokens to every session, about $0.0413 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.
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).
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).
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.
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.