Borrowing it
Nothing to install: this file belongs to ivy00johns/Skill-Madness. 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/ivy00johns/Skill-Madness/main/CLAUDE.mdgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/claude-md)<a href="https://agentmods.dev/instructions/ivy00johns/skill-madness/claude-md"><img src="https://agentmods.dev/badge/instructions/ivy00johns/skill-madness/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/ivy00johns/skill-madness/claude-md"><img src="https://agentmods.dev/badge/instructions/ivy00johns/skill-madness/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 | $0.01912 | $0.01912 |
| Opus 5.5 | $0.00765 | $0.00765 |
| Sonnet 5.5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
Skill-Madness 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Lost? Start at
START-HERE.md— status at a glance + which doc is canonical vs frozen vs archived. Also readAGENTS.md— it contains shared instructions for all AI agents working in this repo.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A multi-agent orchestration toolkit for Claude Code — 78 OSS-publishable skills in skills/. Skills are symlinked to ~/.claude/skills/ for global availability.
The toolkit targets Claude Code as the primary host but the SKILL.md format is platform-agnostic — Claude.ai, Copilot CLI, Codex, and Gemini CLI all consume it. Skills should describe work in terms of capabilities ("read the file", "run the command") rather than Claude-Code-specific tool names where reasonable, so the same skill body works across hosts.
Install / Sync
Use the /sync-skills command to create symlinks from ~/.claude/skills/ back to this repo. This keeps skills always in sync — edits in either location are reflected immediately.
# Via slash command (recommended)
/sync-skills
# Manual: create category symlinks + flattened discovery symlinks
# See skills/workflows/sync-skills/SKILL.md for details
Skill Anatomy
Every skill follows this structure:
skill-name/
├── SKILL.md # YAML frontmatter + markdown instructions (≤5,000 words; warn at 500 lines)
└── references/ # On-demand reference files (unlimited size)
All SKILL.md files use the frontmatter convention defined in skills/meta/skill-writer/references/frontmatter-spec.md. This spec aligns with Anthropic's official Agent Skills standard. Required fields: name (kebab-case; claude-*/anthropic-* prefixes discouraged but allowed as documented exceptions), version (semver, top-level), description (trigger text, ≤1024 chars, no < or > in field values). Optional Anthropic fields: compatibility, license, allowed-tools (hyphen canonical; allowed_tools accepted as alias), metadata. Agent roles also declare owns, composes_with, spawned_by.
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.
- 4d ago Changed · +6 tokens per session 087230299181
- 5d ago Changed · +37 tokens per session fa48068558d4
- 22d ago Changed · +50 tokens per session c5f80540f815
- 1mo ago Changed · +4 tokens per session 39ffe180f49c
- 1mo ago Changed 9ab3f455c512
- 1mo ago Changed · +6 tokens per session b9a43457d7ae
- 2mo ago First seen · 65 lines · 1,809 tokens per session scan A 8a2b4ae04421
Skill-Madness CLAUDE.md is an instructions file published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 4d ago), licensed MIT. It adds 1,912 tokens to every session, about $0.0076 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.