Worker Delegation

Worker Delegation is an AI Engineering skill for Claude Code, published by aden-hive in hive.

10.9K stars5.7K forkson aden-hive/hiveAdded 2026/08/15Repository updated 2026/08/13

agentagent-frameworkagent-skillsanthropicautomationautonomous-agentsclaudeharnessharness-engineeringhuman-in-the-loopopenaipythonself-hostedself-improving

Install in seconds

Install Worker Delegation

Copy Worker Delegation into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/worker-delegation ~/.claude/skills/worker-delegation

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/aden-hive/hive.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: core/framework/skills/_default_skills/worker-delegation/SKILL.md in aden-hive/hive
Installs to: ~/.claude/skills/worker-delegation
Collection: One of 24 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Worker Delegation does

Worker Delegation models a goal as a tracker table and writes a playbook that fans out independent row-level work to parallel workers via run_playbook. Use it in colony mode before fan-out to pilot the worker skill, then let convergence retry and resume unfinished rows.

Worker Delegation is cataloged under AI Engineering on DirSkills. Worker Delegation comes from a repository tagged agent, agent-framework, agent-skills, anthropic and automation.

Documentation

README

Excerpt

Operational Protocol: Worker Delegation

Applies when you're in COLONY mode and considering whether (and how) to fan out work to parallel workers via run_playbook. Read this before fan-out, not during.

Mental model: the tracker is the spine, the playbook is the controller

You don't coordinate workers by reading their reports and deciding what's next each turn. You model the goal as a tracker table where every unit of work is a row, and you write a playbook — a deterministic Python script — that drives that table to completion:

The playbook queries the rows that aren't done yet, dispatches one worker per undone row, and re-queries until none are left. Workers advance their own rows. Re-running the playbook resumes — done rows simply aren't in the work-list anymore.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Worker Delegation

What else does aden-hive publish alongside Worker Delegation?
Worker Delegation is one of 24 skills that DirSkills catalogs from aden-hive/hive, the repository it ships in. Its siblings there include Background Job Control, Browser Edge Cases and Chart Creation Foundations. Each one is a separate skill with its own page in this directory, installs the same way Worker Delegation does, and is maintained by aden-hive in that same repository. The rest of the collection is listed on the aden-hive/hive page.
How does Worker Delegation compare to other AI Engineering skills?
Worker Delegation ranks #378 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Worker Delegation against them. Open each page to compare what they document and how they install.