By mbanderas
Achieve Frontier AI performance in your CLI by fusing the model CLIs you already run. Maestro Frontier is an opt-in, zero-dependency local multi-CLI fusion engine for AI coding agents: fan a prompt across a panel of any 1 to 8 local model CLIs you pick, have a judge model and a synthesizer you choose read the answers into a structured analysis and write one grounded synthesis (default Opus 4.8, override either with --judge/--synth). On a 100-task benchmark every fusion panel outscored its individual member models. Three adapters ship today: Opus 4.8, GPT-5.5, Gemini 3.1 Pro, with Kimi, DeepSeek, GLM, and Qwen to follow. Off, single, and fusion modes switch via /maestro:frontier. Built on Maestro orchestration discipline: decision-gated routing, verified done-claims, surgical scope, and structural enforcement hooks.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Compress a natural-language memory file into terse format to cut input tokens (backup kept, deterministic validation)
Toggle the Maestro context progress bar in the Claude Code status line
Maestro Frontier local multi-CLI engine: arm a mode (off/single/fusion) so it auto-runs every prompt, pick a model/preset, or run a one-off prompt
View and change Maestro's toggles (terse, frontier, context-bar) — direct args or a keyboard picker
Switch Maestro terse output mode (lite|full|ultra|off)
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Achieve Frontier AI performance in your CLI — by fusing the model CLIs you already run. Fan one prompt across a panel of 1-8 of your local CLIs in parallel, have a judge model you pick read every answer into a structured analysis, then a synthesizer you pick write one grounded answer that does not majority-vote. On a 100-task benchmark, every fusion panel outscored its individual member models. It runs on Maestro's discipline layer: verified done-claims, surgical scope, and a research-backed multi-agent gate.
17 fixture tasks · 147 valid A/B runs · 11 voids excluded & re-run · 6 hooks, all tested · ~10 KB always-on kernel · plugin + portable installs
Install — run the command block for your tool, inside that tool. Claude Code and Codex use native plugins. Cursor, Gemini, Cline, Windsurf, and other CLIs use the portable installer, which copies Maestro's runtime-agnostic files into the current project/workspace by default. Global/user installs are optional when you intentionally want cross-project behavior.
Claude Code / Desktop — native plugin (enforcement hooks, /maestro:* commands, skills, status line, Frontier auto-run):
/plugin marketplace add mbanderas/maestro
/plugin install maestro@maestro
Codex CLI / Desktop — native Codex plugin via the Maestro repo marketplace (skills, trusted hooks, and Frontier auto-run after you review and trust the hooks):
codex plugin marketplace add mbanderas/maestro
codex plugin add maestro@maestro
Start a new Codex thread after installing or changing plugin trust so the bundled skills and hooks reload.
Portable installs for other CLI / Desktop apps — run the matching line in that tool's terminal, or ask its agent to run it. These integrations are prompt/skill/workflow shortcuts around the portable CLI unless the tool has native hook support.
| Tool | Install (run inside the tool) |
|---|---|
| Cursor | npx github:mbanderas/maestro install --target cursor |
| Gemini CLI | npx github:mbanderas/maestro install --target gemini |
| Cline | npx github:mbanderas/maestro install --target cline |
| Windsurf / Devin | npx github:mbanderas/maestro install --target windsurf |
| Not sure / auto-detect | npx github:mbanderas/maestro install --target auto |
Portable installs lay down AGENTS.md plus that tool's adapter or
integration file, docs/orchestration.md, the zero-dependency Frontier
engine, and the relevant command/skill files. Codex does not need that copy
path for normal use: the repo is its marketplace
(.agents/plugins/marketplace.json) and plugin
(.codex-plugin/plugin.json), bundling the Codex skills, hooks, Frontier
engine, settings CLI, commands, and docs/codex.md. The older
maestro install --target codex path remains a manual fallback when you
intentionally want project files instead of the plugin. Once published, swap
github:mbanderas/maestro for @maestrofrontier/frontier for portable npm
installs.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub mbanderas/maestro --plugin maestroFind and quantify cloud and CI spend waste from your coding agent. Costguard runs read-only billing checks (GitHub Actions, Supabase, Railway, Netlify, Neon), static CI/cron waste rules, dry-run-first auto-fixes for workflow files, and a monthly cost digest — all driven from your session via /costguard-audit, /costguard-fix, and /costguard-live, or the costguard skill. Never writes to provider accounts, never pushes git, never prints secrets.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.