Prun — Development skill for Claude Code
Run prun: parallel delegation fan-out (Codex-primary, Opus coordinates).
How to install Prun
Installs to ~/.claude/commands/yzhao062-anywhere-agents-prun.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/yzhao062/anywhere-agents/HEAD/.claude/commands/prun.md -o ~/.claude/commands/yzhao062-anywhere-agents-prun.md Restart Claude Code, or start a new session, for it to be picked up.
What Prun does
description: "Run prun: parallel delegation fan-out (Codex-primary, Opus coordinates)" argument-hint: "[task description or context]"
Read and follow the skill definition. Look for it at `skills/prun/SKILL.md` first, then `.claude/skills/prun/SKILL.md`, then `.agent-config/repo/skills/prun/SKILL.md`.
Command arguments from the slash invocation: `$ARGUMENTS`
Treat the command arguments as the task to fan out. prun decomposes the task into independent units and runs many of them in para
Alternatives in Development
- OpenAI Codex CLI — (Rust implementation) 67.8k ★
- Master Routing — reverse-skill PRIMARY 快路径 29.6k ★
- Vibe Kanban — Get 10X more out of Claude Code, Gemini CLI, Codex, Amp and other coding agents 23.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Fan Out
Prepare independent slices with explicit ownership and integration evidence for authorized delegation.
Regression
Codebase-wide regression scan — fan out per-area review subagents in parallel, dedupe against existing issues,
Orchestrating Parallel Sessions
Run a project - or a whole business - through orchestrator agents that fan work out to parallel Claude Code se
Panel
Fan a question out to every available provider in parallel (read-only), then synthesize their answers against
Final Review
Orchestrate the final review fan-out (integration + diversity + risk + release readiness)
Book Stay
Choose and book a hotel (or stay) — quiz preferences, generate shortlist, verify rates, hand off booking, fan
Related Agents
Agent Chadi
Industry-grade OpenCode all-rounder — your primary agent. 5-gate hybrid workflow with contract-first wave fan-
Deep Research Sonnet
Bulk-fan-out worker for multi-axis breadth-first research. Sonnet 5 tier (NOT frontier) — the canonical worker
Haiku
Haiku, which has no effort level. Use for searches, grep fan-out, classification, and throwaway output such as