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/sudara/pamplejuce/claude-mdgit clone --depth 1 https://github.com/sudara/pamplejuceWrote 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/sudara/pamplejuce/claude-md)<a href="https://agentmods.dev/instructions/sudara/pamplejuce/claude-md"><img src="https://agentmods.dev/badge/instructions/sudara/pamplejuce/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 | $0.02450 | $0.02450 |
| Opus 5 | $0.01225 | $0.01225 |
| Sonnet 5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
pamplejuce 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 — 159 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.
First-Time Setup
If the values below still say "Pamplejuce" or "Pamplejuce Demo", this project was freshly created from the template and hasn't been personalized yet. Ask the user:
- What's your plugin called? (display name for DAWs, e.g. "Super Synth")
- What's your company name? (e.g. "My Audio Co")
- What type of plugin is this? (synth, effect, utility, etc.)
- What IDE do you use? (CLion, VS Code, Xcode, other)
- Do you want CI/CD via GitHub Actions? Note: public repos get unlimited CI minutes, but private repos have a limited monthly allowance. If they're on a private repo and want to avoid burning minutes during active development, suggest commenting out matrix entries in the workflow to build on just one platform (e.g. only their dev OS) and running tests only — they can re-enable the full matrix when preparing a release.
- If using CI, do you need Intel IPP? (provides SIMD-optimized DSP functions — if not, comment out the IPP install steps in the workflow to avoid CI failures)
- Are you code signing? Code signing is essentially required to distribute to anyone (beta testers, friends, customers) — without it, macOS Gatekeeper and Windows SmartScreen will block or warn on the plugin. But it can be set up later; it's fine to skip during early development. Ask separately for macOS and Windows:
- macOS: codesigning + notarization requires an Apple Developer account ($99/year). If not signing yet, comment out the codesign/notarize steps in the CI workflow. Guide: How to code sign and notarize macOS audio plugins in CI
- Windows: Azure Trusted Signing is the recommended approach (free tier available). If not signing yet, comment out the Azure signing step. Guide: Code signing on Windows with Azure Trusted Signing
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 · 159 lines · 2,450 tokens per session scan A 6afd6f6dbbf2
pamplejuce CLAUDE.md is an instructions file published in the GitHub repository sudara/pamplejuce (757 stars, last pushed 17d ago), licensed MIT. It adds 2,450 tokens to every session, about $0.0123 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
claude-code-tts CLAUDE.md
Instructions for ybouhjira/claude-code-tts, covering claude.md, project overview, commands, build and run locally (requires openaiapikey).
pydevices-examples AGENTS.md
Instructions for PyDevices/pydevices-examples, covering agents.md, cursor cloud specific instructions, environment, tests and lint and running examples headlessly (gui smoke tests).
postman-claude-code-plugin CLAUDE.md
Instructions for Postman-Devrel/postman-claude-code-plugin, covering claude.md, what this is, repository structure, how the plugin works and component conventions.
orkid CLAUDE.md
Claude Code instructions for tweakoz/orkid, covering orkid — repo-wide agent law and commits.
no-vibe AGENTS.md
Instructions for rizukirr/no-vibe, covering agents, repo purpose, architecture (high-signal files), verification commands and conventions that are easy to miss.
qb-linq copilot-instructions.md
Instructions for isndev/qb-linq: Header-only C++17 library: CMake target qb::linq, public include .