Claude Code Pro ⚡

Production-grade Claude Code workflow that doesn't waste your tokens.

The Problem with Other Skills

Most Claude Code tmux skills work like this:
CODEBLOCK0

Each poll reads 100-200 lines of terminal output, feeds it to your agent, and burns tokens deciding "is it done yet?" A 20-minute task = 40 polls = thousands of wasted tokens.

How This Skill Works

CODEBLOCK1

The task itself tells you when it's done. Your agent sleeps until notified. One lightweight check confirms the result. That's it.

Token Savings Breakdown

80-97% token savings on supervision alone.

Smart Dispatch: Know When NOT to Start

Before spawning Claude Code, ask:

The fastest token savings come from not spawning a session at all.

Quick Start

CODEBLOCK2

That's the key line: openclaw system event --text "Done: ..." --mode now. The task notifies your agent on completion. No polling needed.

Task from file (complex requirements)

CODEBLOCK3

Write detailed requirements once upfront → fewer mid-task corrections → fewer tokens.

Monitor (Only When Needed)

CODEBLOCK4

Manage Sessions

CODEBLOCK5

Attach (Human SSH Access)

CODEBLOCK6

Agent Workflow

CODEBLOCK7

Fallback: If no notification after 15 minutes, one lightweight poll with --json.

Completion Callback Template

Always append to your task prompt:

CODEBLOCK8

This is what makes the whole approach work. The task signals completion; your agent doesn't need to guess.

Modes

Design Choices

• - Isolated tmux socket (-L cc) — doesn't interfere with your tmux sessions
• cc- prefix on all sessions — easy to list/filter
• Bracketed paste for multi-line prompts — no escaping issues
• JSON output from list/monitor — agent-friendly, fewer tokens to parse

Files