Prun

Prun is an Automation skill for Claude Code, published by yzhao062 in anywhere-agents.

241 stars26 forkson yzhao062/anywhere-agentsAdded 2026/09/02+1% in starsRepository updated 2026/08/29

agent-configagent-skillsagents-mdai-agentsai-safetyclaude-codecode-reviewcodexdual-agent-reviewgit-safetynpmopinionatedportable-configpypisafety-hooksshared-configurationskill-dispatchskill-router

Install in seconds

Install Prun

Copy Prun 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/yzhao062/anywhere-agents/tree/main/skills/prun ~/.claude/skills/prun

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/yzhao062/anywhere-agents.git

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

In this catalog

Source file: skills/prun/SKILL.md in yzhao062/anywhere-agents
Installs to: ~/.claude/skills/prun
Collection: One of 5 skills cataloged from this repository
Category: Automation — 1648 skills

What Prun does

Prun fans a task into parallel units that the Claude session coordinates while workers do the execution. Use it for independent code, research, or analysis tasks that can run at once, especially when Codex should handle most units and Sonnet is reserved for session-only tools.

Prun is cataloged under Automation on DirSkills. Prun comes from a repository tagged agent-config, agent-skills, agents-md, ai-agents and ai-safety.

Documentation

README

Excerpt

prun (parallel run)

Overview

prun fans a task out into independent units that run in parallel on separate-quota or in-session workers, while the Claude session only coordinates. Workers are Codex (codex exec, a separate abundant account, frontier model) and Sonnet subagents (inside the Claude session). Codex is the prioritized default: its quota is separate from the Claude plan and its current model (gpt-5.6 tier) is strong on hard reasoning and code, so most units go to Codex. Sonnet is reserved for units that need something the Claude session uniquely provides (see the Executors rule). The coordinator decomposes the task, dispatches the units, gathers their results, reviews their diffs, and integrates. It never runs a unit itself.

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

Frequently asked about Prun

What else does yzhao062 publish alongside Prun?
Prun is one of 5 skills that DirSkills catalogs from yzhao062/anywhere-agents, the repository it ships in. Its siblings there include CI Mockup Figure, Implement Review and My Router. Each one is a separate skill with its own page in this directory, installs the same way Prun does, and is maintained by yzhao062 in that same repository. The rest of the collection is listed on the yzhao062/anywhere-agents page.
How does Prun compare to other Automation skills?
Prun ranks #1500 by stars among the 1648 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. 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 Prun against them. Open each page to compare what they document and how they install.