tmux-delegation

tmux-delegation is a skill for Claude Code, Codex from LFTPadilla/agent-dev-kit. It costs 58 tokens per session (2,291 once invoked), scanned A, original, MIT.

A task-delegation guide for running multiple coding agents in separate tmux panes, which are terminal work areas that can run side by side.

In plain words
What is it for?
It helps allocate panes, send multiline instructions, detect when agents finish, queue follow-up input, and audit changes on disk across Codex, Claude Code, Pi, OpenCode, and cursor-agent.
Why use it?
It helps an orchestrator assign work without mixing repositories, conversations, or unfinished tasks between workers.

Skill for Claude CodeCodex

Part of the dev-skills plugin — 24 skills, 1 command shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/lftpadilla/agent-dev-kit/tmux-delegation
Any agent
npx skills add LFTPadilla/agent-dev-kit --skill tmux-delegation
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code, Codex.

Or install dev-skills, the plugin that ships this one along with the rest of its 24 skills, 1 command.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tmux-delegation

README.md
[![agentmods](https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/tmux-delegation.svg)](https://agentmods.dev/skills/lftpadilla/agent-dev-kit/tmux-delegation)
Your own site
<a href="https://agentmods.dev/skills/lftpadilla/agent-dev-kit/tmux-delegation"><img src="https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/tmux-delegation.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.02291
Opus 5 $0.00029 $0.01145
Sonnet 5 $0.00012 $0.00458
Haiku 4.5 $0.00006 $0.00229

Measured 5d ago against content hash 93632dd76569, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tmux-delegation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dev-skills/skills/tmux-delegation/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Harness tmux Delegation

Manage and delegate tasks to coding agents running inside tmux panes and windows. Designed for orchestrators (like Hermes, OpenCode, Pi, or Tech Lead profiles) that decompose work and delegate execution to bounded workers across diverse CLI harnesses: Codex CLI, Claude Code, Pi CLI, OpenCode, cursor-agent, or standard shells.

The core rule: The orchestrator plans, routes, and audits; the worker implements in an isolated tmux pane.


1. Pane Selection & Allocation (Anti-Contamination Rule)

Never reuse a pane that has active context or conversation history from a different task or repository. Context pollution corrupts reasoning.

Inventory Existing Panes

# Check all windows and panes in the session with command, cwd, and alive status
tmux list-panes -t "$TMUX_SESSION" -F \
  '#{window_index}:#{pane_index} #{pane_id} #{pane_current_command} #{pane_dead} #{pane_current_path}'

Pane Selection Matrix

Pane Condition Suitable? Action
Target harness running, same repo, idle prompt YES Reset context if needed (/clear in Claude/Codex) and proceed.
Target harness running, different repo NO Open a new window. Do not contaminate active context.
Empty shell (zsh/bash), same repo YES Boot the desired agent directly in this pane.
Empty shell, different directory YES cd /abs/repo/path then launch agent.
All panes occupied or conflicting NO Spawn a fresh window.

Spawning a Fresh Pane

When creating a new window, always specify the absolute working directory:

# 1. Create window with explicit cwd
tmux new-window -t "$TMUX_SESSION" -n "$TASK_SLUG" -c "$ABS_REPO_PATH"

# 2. Launch the target harness
# Claude Code:
tmux send-keys -t "$TMUX_SESSION:$WINDOW_INDEX" "claude --dangerously-skip-permissions" Enter

# Codex CLI:
tmux send-keys -t "$TMUX_SESSION:$WINDOW_INDEX" "codex" Enter

# Pi CLI:
tmux send-keys -t "$TMUX_SESSION:$WINDOW_INDEX" "pi" Enter

# OpenCode CLI:
tmux send-keys -t "$TMUX_SESSION:$WINDOW_INDEX" "opencode" Enter

# cursor-agent CLI:
tmux send-keys -t "$TMUX_SESSION:$WINDOW_INDEX" "cursor-agent" Enter

Read the full file on GitHub · 244 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 244 lines · 58 tokens per session scan A 93632dd76569

Subscribe to this mod's changes

tmux-delegation is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 2,291 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.