---
name: "Delegate planned agent work with Elves"
slug: "delegate-planned-agent-work-with-elves"
description: "Use Elves to hand a bounded development or research plan to a separate Claude Code or Codex worker while preserving run files, worktree safety, review gates, and human merge authority."
github_stars: 188
verification: "security_reviewed"
source: "https://github.com/aigorahub/elves"
author: "aigorahub"
publisher_type: "community"
category: "Templates & Workflows"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "aigorahub/elves"
  github_stars: 188
---

# Delegate planned agent work with Elves

Use Elves to hand a bounded development or research plan to a separate Claude Code or Codex worker while preserving run files, worktree safety, review gates, and human merge authority.

## Prerequisites

Claude Code or Codex, Python 3, git, optional GitHub CLI or configured worker adapters

## Installation

Use the upstream install or setup path that matches your environment:
- make mistakes. Always review the PR before merging.

Requirements and caveats from upstream:
- external provider required. Optional work drivers when configured and permitted: trusted Grok
- Static help probes make no model calls and prove only that flags are advertised; required fails

Basic usage or getting-started notes:
- worker without locking the run to one model provider. The capable Claude Code or Codex driver
- plans and reviews; a subscription-native (or optional external) worker implements; durable run
- orients you. The guide also covers the first run, worker choice, live progress, review, and

- Source: https://github.com/aigorahub/elves
- Extracted from upstream docs: https://raw.githubusercontent.com/aigorahub/elves/HEAD/README.md

## Documentation

- https://aigorahub.github.io/elves/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/delegate-planned-agent-work-with-elves/)
