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/mbanderas/maestroWrote 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/mbanderas/maestro/maestro)<a href="https://agentmods.dev/plugins/mbanderas/maestro/maestro"><img src="https://agentmods.dev/badge/plugins/mbanderas/maestro/maestro/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/mbanderas/maestro/maestro"><img src="https://agentmods.dev/badge/plugins/mbanderas/maestro/maestro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
maestro 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": "maestro",
"version": "1.15.0",
"displayName": "Maestro",
"description": "Maestro Frontier is an opt-in, zero-dependency local multi-CLI fusion engine for AI coding agents. Use /maestro:frontier catalog to inspect Opus 5 and current Codex models, then compose a panel with validated effort. Panel, judge, and synthesizer subprocesses are one-shot and read-only. Optional policy hooks are independent and off by default.",
"author": {
"name": "Mark Laursen",
"url": "https://github.com/mbanderas"
},
"homepage": "https://github.com/mbanderas/maestro",
"repository": "https://github.com/mbanderas/maestro",
"license": "MIT",
"keywords": ["multi-cli-fusion", "fusion-engine", "frontier", "model-panel", "orchestration", "claude-code", "gemini", "codex", "agents"]
}
What it installs
The manifest is a name and a version. 8 skills, 6 commands, 7 hooks travel with it, and installing the plugin installs all of them — 298 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill maestro A 0 tokens
- Skill frontier A 23 tokens
- Skill terse A 55 tokens
- Skill maestro-settings A 27 tokens
- Skill maestro-terse A 23 tokens
- Skill maestro-token-efficiency A 29 tokens
- Skill maestro-update A 14 tokens
- Skill maestro-frontier C 36 tokens
- Command frontier A 0 tokens
- Command settings A 27 tokens
- Command update A 17 tokens
- Command compress A 20 tokens
- Command terse A 15 tokens
- Command context-bar B 12 tokens
- Hook UserPromptSubmit A not measured
- Hook PostToolUse A not measured
- Hook SessionStart A not measured
- Hook PreToolUse A not measured
- Hook SessionEnd A not measured
- Hook SubagentStop A not measured
- Hook Stop A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 b9ffefc011a7
maestro is a plugin published in the GitHub repository mbanderas/maestro (5 stars, last pushed 15d 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 2026-08-31.
Other plugins, from other repositories
toolport
Every tool. One port. Connects this agent to your local Toolport gateway: every MCP server you set up in Toolport, exposed through a handful of compact meta-tools instead of hundreds of tool definitions (90% fewer tokens, measured).
nightmarquee
Cinematic website prompts plus demo footage, tuned for Lovable, Bolt, Cursor, Claude and Codex. Free prompts need no account.
pn-core
MCP engine that runs software delivery as named, gated steps — not one long chat. Skills, agents, rules, and pn-core:// resources for Cursor, Claude Code, Codex, and Pi.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.