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/josstei/maestro-orchestrateWrote 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/josstei/maestro-orchestrate/gemini-extension)<a href="https://agentmods.dev/plugins/josstei/maestro-orchestrate/gemini-extension"><img src="https://agentmods.dev/badge/plugins/josstei/maestro-orchestrate/gemini-extension/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/josstei/maestro-orchestrate/gemini-extension"><img src="https://agentmods.dev/badge/plugins/josstei/maestro-orchestrate/gemini-extension.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 9d 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": "1.6.4",
"description": "Multi-agent development orchestration platform — 39 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands",
"contextFileName": "GEMINI.md",
"settings": [
{
"name": "Disabled Agents",
"description": "Comma-separated list of agent names to exclude from implementation planning.",
"envVar": "MAESTRO_DISABLED_AGENTS"
},
{
"name": "Max Retries",
"description": "Maximum retry attempts per phase before escalating to user.",
"envVar": "MAESTRO_MAX_RETRIES"
},
{
"name": "Auto Archive",
"description": "Automatically archive session state on successful completion (true/false).",
"envVar": "MAESTRO_AUTO_ARCHIVE"
},
{
"name": "Validation",
"description": "Post-phase validation strictness level (strict/normal/lenient).",
"envVar": "MAESTRO_VALIDATION_STRICTNESS"
},
{
"name": "State Directory",
"description": "Base directory for session state and plans (default: docs/maestro).",
"envVar": "MAESTRO_STATE_DIR"
},
{
"name": "Max Concurrent",
"description": "Maximum subagents emitted in one native parallel batch turn (0 = dispatch the entire ready batch).",
"envVar": "MAESTRO_MAX_CONCURRENT"
},
{
"name": "Execution Mode",
"description": "Phase 3 execution mode: 'parallel' (native concurrent subagents), 'sequential' (one at a time), or 'ask' (prompt each time). Default: ask.",
"envVar": "MAESTRO_EXECUTION_MODE"
}
],
"mcpServers": {
"maestro": {
"command": "node",
"args": [
"${extensionPath}/mcp/maestro-server.js"
],
"cwd": "${extensionPath}",
"env": {
"MAESTRO_RUNTIME": "gemini",
"MAESTRO_WORKSPACE_PATH": "${workspacePath}"
}
}
}
}
What ships with it
11 files beside gemini-extension.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.
- scripts/check-layer-boundaries.js 1.5 KB runs code
- scripts/generate.js 4.7 KB runs code
- scripts/install-codex-plugin.js 4.3 KB runs code
- scripts/install-git-hooks.js 1.3 KB runs code
- scripts/lib/cli.js 772 B runs code
- scripts/npm-publish-idempotent.js 6.6 KB runs code
- scripts/package-release-artifacts.js 3.2 KB runs code
- scripts/release-artifact-manifest.js 9.8 KB runs code
- scripts/update-versions.js 3.1 KB runs code
- scripts/verify-npm-pack.js 2.0 KB runs code
- scripts/verify-release-artifacts.js 2.4 KB runs code
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.
- 9d ago First seen · 57 lines scan A 82ffb1df955d
maestro is a plugin published in the GitHub repository josstei/maestro-orchestrate (479 stars, last pushed 5d ago), licensed Apache-2.0. 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 2026-10-07.
Other plugins, from other repositories
milestone-driver
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…
gemini
Gemini via Antigravity CLI for Claude Code — ask, review, adversarial-review, implement.
orbit
Turn any repo into a self-prompting agentic loop — a governed, project-fitted sub-agent team with persistent memory, a task/question router, hard safety brakes, a live team board, and active learning.
gemini
Use Gemini CLI from Claude Code to review code or delegate tasks.
gemini-as-tool
Use Google Gemini (3.x Pro/Flash) as a headless tool, builder, or judge from Claude Code — via Google AI Pro OAuth, no API key.
looker
Connect to Looker and interact with your data using LookML.