Agent Coordinator
Agent Coordinator is a skill for Codex that structures complex jobs into a clear plan with accountable parts and a checked, recoverable result. It helps developers keep long tasks understandable, track progress, and resume after interruptions. It is for developers using Codex on multi-step projects that need verification.
✨ Key features
- Creates a clear plan from request to finish.
- Breaks work into accountable parts with owners.
- Checks results with positive and negative proof commands.
- Recovers from interruptions using private state.
- Supports optional parallel agents or inline execution.
- Read-only state inspection commands for workflows.
🎯 Use cases
- Implementing a feature with multiple dependent steps.
- Diagnosing intermittent test failures without changing production.
- Resuming an interrupted schema migration workflow.
- Comparing architecture options with evidence and tradeoffs.
- Reviewing a project README for confusing steps without editing files.
📦 Installation
🧰 Requirements: Requires Python 3.11 or newer and Codex; no third-party runtime packages. Installation is per-user and does not change Codex settings.
Ask Codex to follow the repository-owned installer:
Install https://github.com/alanhoff/agent-coordinator by following INSTALL.md
The procedure clones the repository to a temporary directory, records its commit, copies the self-contained skill/ directory for the current user, removes the temporary checkout, and reports the installed path and source commit. It replaces an existing destination only when that destination identifies itself as Coordinator.
🚀 Usage
In a project, send this starter prompt:
$coordinator Review this project's README for confusing setup steps. Do not edit files.
Return the three highest-impact fixes, cite the evidence for each, and confirm that no files changed.
A successful response meets three conditions:
- Three fixes are ranked by impact.
- Each fix cites evidence from the project.
- The response confirms that no files changed.
⚠️ Good to know
Coordinator does not invoke or inspect a version-control system, and it requires explicit invocation with the $coordinator prefix.
❓ FAQ
Does this require multiple agents?
No. When extra agent capacity is available, Coordinator can send independent pieces to separate workers; otherwise it completes them inline, one at a time.
Do I need to invoke it explicitly?
Yes. The documented prompt pattern starts each coordinated task with $coordinator; installation itself only places the skill and changes no settings.
What does it add to my project or settings?
It adds no persistent Coordinator-owned file to the target project and does not edit Codex settings or global custom-agent profiles. During initialization, it creates and removes one private-name file solely to detect the repository filesystem's case behavior.
What happens if work is interrupted?
A new Coordinator run can resume from private state. It marks work that may still be active for reconciliation before retrying, preserves completed evidence, and avoids starting an uncertain step twice.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.