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.
npx agentmods add instructions/iplug3/audio-plugin-dev-skills/claude-mdgit clone --depth 1 https://github.com/iPlug3/audio-plugin-dev-skillsWrote 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/iplug3/audio-plugin-dev-skills/claude-md)<a href="https://agentmods.dev/instructions/iplug3/audio-plugin-dev-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/iplug3/audio-plugin-dev-skills/claude-md.svg" alt="Measured on agentmods" 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 | $0.00488 | $0.00488 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
audio-plugin-dev-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 3d 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 — 48 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
A Claude Code marketplace plugin providing AI-assisted skills for validating audio plugins across formats (VST3, AudioUnit, CLAP). This is a documentation-driven project — skills are Markdown files that give Claude context for running external validator CLI tools.
Repository Structure
.claude-plugin/marketplace.json # Marketplace registration
plugins/audio-plugin-validators/
.claude-plugin/plugin.json # Plugin metadata (name, version, keywords)
skills/
validate-audiounit/SKILL.md # auval (macOS only)
validate-clap/SKILL.md # clap-validator
validate-pluginval/SKILL.md # pluginval (VST3/AU)
validate-vst3/SKILL.md # Steinberg validator
validate-vst3-editorhost/SKILL.md # Steinberg editorhost
check-codesign/SKILL.md # macOS code signature check
Adding a New Skill
- Create
plugins/audio-plugin-validators/skills/<skill-name>/SKILL.md - Include YAML frontmatter with:
name,description(with trigger phrases),compatibility, andmetadata(author, version) - Structure the body with: Instructions, Basic Usage, Options, Common Issues sections
- Register the skill by adding it — auto-discovery finds
SKILL.mdfiles in skill directories
SKILL.md Conventions
- The
descriptionfield doubles as the trigger — include natural phrases users would say (e.g., "validate VST3", "test the .vst3") - Provide platform-specific binary paths in tables
- Include installation/build instructions for the underlying CLI tool
- Document common failure modes and fixes
- Use code blocks with
bashsyntax highlighting
Marketplace Metadata
marketplace.jsonat.claude-plugin/lists all plugins with name, source path, description, and category- Each plugin has its own
plugin.jsonatplugins/<name>/.claude-plugin/ pluginRootin marketplace.json points to./plugins
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.
- 3d ago First seen · 48 lines · 488 tokens per session scan A afbef30735f0
audio-plugin-dev-skills CLAUDE.md is an instructions file published in the GitHub repository iPlug3/audio-plugin-dev-skills (88 stars, last pushed 6mo ago), licensed MIT. It adds 488 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
skills AGENTS.md
AGENTS.md instructions for scenario-labs/skills, covering agents.md, what this repo is, layout, public content only and authoring contract.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.
lime CLAUDE.md
Claude Code instructions for limecloud/lime, covering claude code 工作指令 and 补充说明.
Skills CLAUDE.md
Instructions for kriscard/Skills, covering claude.md, requirements, repository structure, skill structure and frontmatter rules (verified against official docs).
fw-dev-tools AGENTS.md
Instructions for freshworks-developers/fw-dev-tools, covering agent instructions — marketplace repo (contributors), before you open a pr, if you change…, repository layout and rules and slash commands (inventory).
openehr-assistant-plugin AGENTS.md
Instructions for Cadasto/openehr-assistant-plugin, covering ai guidelines: openehr assistant plugin, project overview, domain context, companion mcp server and calling conventions the server enforces.