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.
git clone --depth 1 https://github.com/danielraffel/generous-corp-marketplaceWrote 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/plugins/danielraffel/generous-corp-marketplace/juce-dev)<a href="https://agentmods.dev/plugins/danielraffel/generous-corp-marketplace/juce-dev"><img src="https://agentmods.dev/badge/plugins/danielraffel/generous-corp-marketplace/juce-dev/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/plugins/danielraffel/generous-corp-marketplace/juce-dev"><img src="https://agentmods.dev/badge/plugins/danielraffel/generous-corp-marketplace/juce-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
juce-dev 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 1mo 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.
What it actually says
{
"name": "juce-dev",
"version": "1.0.0",
"description": "Create and manage JUCE audio plugin projects from the JUCE-Plugin-Starter template",
"author": {
"name": "Daniel Raffel",
"url": "https://danielraffel.me"
},
"repository": "https://github.com/danielraffel/generous-corp-marketplace",
"license": "MIT",
"keywords": ["juce", "audio", "plugin", "vst", "au", "daw", "music"],
"commands": "./commands/",
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 3 skills, 10 commands travel with it, and installing the plugin installs all of them — 536 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill juce-visage A 172 tokens
- Skill visage-theme A 83 tokens
- Skill JUCE Plugin Starter B 140 tokens
- Command port A 14 tokens
- Command ci A 16 tokens
- Command setup-updates A 17 tokens
- Command build A 13 tokens
- Command setup-ios A 15 tokens
- Command theme A 20 tokens
- Command vm A 8 tokens
- Command create B 11 tokens
- Command website C 12 tokens
- Command setup-visage C 15 tokens
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.
- 1mo ago First seen · 15 lines scan A 9794465d7f2f
juce-dev is a plugin published in the GitHub repository danielraffel/generous-corp-marketplace (11 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
modern-cpp
Modern C++ best practices (C++20/23/26). Use when writing C++ code, creating new C++ projects, or modernizing legacy C++ patterns.
qt-development-skills
Agentic engineering skills for Qt software development, including Qt C++/QML code review, QML coding, and Qt C++/QML code documentation. Bundles the hosted Qt Documentation MCP server for live Qt API lookups. These skills use AI and can make mistakes. Always double-check the output carefully.
drogon
Drogon C++ backend rules & skills: correct async code, avoiding callback / event-loop pitfalls. Works with Claude Code, ZCode, Codex, Cursor, VS Code (Copilot), Gemini CLI and any AGENTS.md-compatible agent.
cpp-lsp
Claude Code plugin for C/C++ development with clangd LSP integration, 14 automated hooks for compilation, linting (clang-tidy), formatting (clang-format), and memory analysis (valgrind).
c-cpp-analyzer
Analyze C/C++ code for Rust migration planning — difficulty classification, pattern detection, risk flags.
o2-scalpel-cpp
Scalpel refactor MCP server for C/C++ via clangd.