Efficient Orchestrator

From the author

Run only when the user explicitly invokes /efficient-orchestrator (or the /efficient-frontier and /efficient-fable aliases). Keeps an expensive model (Fable, Opus, Astra, Sol) on planning, judgment and review while cheaper subagents do bounded research, coding, QA and log work. Never self-activate.

— the description by Builder.io

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Efficient Orchestrator is a meta-skill designed to optimize AI agent performance and cost. It establishes a hierarchy where a primary, high-capability model manages planning, judgment, and final review, while delegating token-intensive or mechanical tasks to smaller, specialized subagents. This approach ensures that expensive computational resources are reserved for high-level decision-making, while routine operations like research, testing, and log analysis are handled by more efficient models.

What it does

Establishes a clear hierarchy between a primary decision-making model and specialized subagents.
Provides a structured workflow for delegating bounded tasks such as research, coding, and QA.
Defines specific model-tier pairings to balance capability with cost-efficiency.
Standardizes the format for task handoffs to ensure subagents receive clear scope and objectives.
Implements strict operational limits, such as helper counts and non-recursive delegation, to maintain control.
Requires the primary model to synthesize and verify all delegated outputs before finalizing.

When to use it

When a project involves complex, multi-step tasks that require both high-level reasoning and extensive mechanical work.
When you need to manage the computational cost of an agentic workflow without sacrificing quality.
When you have clear, bounded sub-tasks that can be performed independently by specialized models.
When you want to maintain centralized control over architecture, risk, and final output quality.

Advantages

Reduces overall token costs by offloading routine tasks to cheaper models.
Improves focus by allowing the primary model to concentrate on strategy and synthesis.
Enforces a disciplined, modular approach to complex problem-solving.
Provides transparency regarding the distribution of work and associated costs.

Usage examples

“/efficient-orchestrator Refactor the authentication module and update all related unit tests.”: The agent plans the refactoring strategy, delegates the unit test updates to a smaller model, and performs the final integration and review of the changes.
“/efficient-orchestrator Analyze these logs to identify the root cause of the recent deployment failures.”: The agent uses a subagent to perform log reduction and clustering, then reviews the findings to provide a definitive diagnosis and recommended fix.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/builderio/efficient-orchestrator/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip efficient-orchestrator.zip -d .agents/skills

Documentation by Builder.io

Use this only when the user asks for it by name. Without that request, do the work yourself and don't spawn helpers.

The expensive main model plans, decides, integrates and reviews. Cheaper subagents do the token-heavy, bounded work.

Model tiers

Main model	Cheap helpers	Use
Claude Fable / Opus	`haiku`	search, scans, docs extraction, log reduction, mechanical edits, test and browser runs
	`sonnet`	coding or analysis that needs judgment
OpenAI Astra / Sol	`gpt-6.1-terra` low or medium	coding, QA, research, most delegated work
	`gpt-6-luna`	bulk mechanical scans, only when Terra isn't needed

Set the model and effort explicitly on every spawn; never let a helper inherit the expensive model. If the main model is already a cheap tier, don't use this skill.

Workflow

Keep at the top: architecture, prioritization, ambiguity, risk, synthesis and final review.
Delegate: repo scans, research, narrow patches with clear file ownership, test and browser passes, failure clustering, log reduction.
Write each handoff as a self-contained packet: repo path, objective, scope and out-of-scope, files or search targets, verification command, return format, stop conditions.
Require compact returns: findings, changed files, commands run, evidence, open decisions.
Inspect the evidence that matters before claiming done. Delegated output is evidence, not a verdict.

Limits

At most 3–5 helpers at once. Helpers never spawn their own helpers.
Close each helper as soon as its result is in.
Don't delegate the blocker your next step depends on, and never give two helpers the same files.
Stop helpers that return nothing usable twice; do that step yourself.
When done, say roughly how much work was delegated, so the cost is visible.

Files

ATTRIBUTION.mdAdded by AutoGineer869 B
LICENSELicence file added by AutoGineer1.0 KiB
README.md1.3 KiB
SKILL.md2.2 KiB
assets/fable-orchestrator-dark.png108.7 KiB
assets/fable-orchestrator.excalidraw19.1 KiB
assets/fable-orchestrator.png108.6 KiB

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Handoff
Matt Pocock· Community
Generates a concise handoff document to facilitate seamless transitions between AI agents.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Chief Of Staff
Matt Pocock· Community
A strategic orchestration agent that manages long-term goals by coordinating subagents and maintaining a persistent knowledge wiki.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Ask Matt
Matt Pocock· Community
A central routing skill that helps you identify the correct agent skill or workflow for your current situation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Claude Handoff
Matt Pocock· Community
Seamlessly transfer your current conversation context to a new background agent.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Executing Plans
Jesse Vincent (obra)· Community
Execute implementation plans inline without subagents, maintaining rigorous progress tracking and verification.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository314k
Using Superpowers
Jesse Vincent (obra)· Community
A mandatory protocol for AI agents to identify and invoke relevant skills before performing any task or responding to user input.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository314k