tmux-agents

tmux-agents is a skill for Codex from noho/code-is-cheap. It costs 42 tokens per session (1,266 once invoked), scanned A, original, Apache-2.0.

A communication protocol for sending tasks to coding agents already running inside tmux panes. Tmux is a terminal tool that lets several command-line sessions run and be controlled separately.

In plain words
What is it for?
Use it to discover Claude or Codex agent panes, clear a session for a new task, send instructions, wait for completion, and capture responses. It also defines safeguards for unclear pane IDs and truncated messages.
Why use it?
It prevents messages from going to the wrong agent or session and avoids interrupting work that is still running. It requires checking the pane identity and agent type before sending commands.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to discover Claude or Codex agent panes, clear a session for a new task, send instructions, wait for completion, and capture responses. It also defines safeguards for unclear pane IDs and truncated messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/noho/code-is-cheap/tmux-agents
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.

Any agent
npx skills add noho/code-is-cheap --skill tmux-agents
Clone the repo
git clone --depth 1 https://github.com/noho/code-is-cheap

Made for: Codex.

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-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/noho/code-is-cheap/tmux-agents/github.svg)](https://agentmods.dev/skills/noho/code-is-cheap/tmux-agents)
Your own site
<a href="https://agentmods.dev/skills/noho/code-is-cheap/tmux-agents"><img src="https://agentmods.dev/badge/skills/noho/code-is-cheap/tmux-agents/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tmux-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/noho/code-is-cheap/tmux-agents"><img src="https://agentmods.dev/badge/skills/noho/code-is-cheap/tmux-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.01266
Opus 5.5 $0.00017 $0.00506
Sonnet 5.5 $0.00008 $0.00253
Haiku 4.5 $0.00004 $0.00127

Measured 29d ago against content hash 02bb9a5c1a7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tmux-agents 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 29d 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.

skills/tmux-agents/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tmux Agents

目标 Agent 必须已经在 pane 中运行;本 skill 不分配角色。

本 skill 要求安装支持延迟创建托管 session 的 tmux-cli:在 tmux 外,status、列表和针对显式 full pane id 的 send / wait_idle / capture 不创建 remote-cli-session;只有明确 launch 新托管 window 才按需创建。 旧版不满足这一前提时先升级工具,不用环境变量伪装 tmux,也不在本 skill 中保留旧版兼容分支。

Preflight Checklist

每次发送前逐项过;任何一项不满足就先报告,不得盲发:

  • 先用原生 tmux list-panes -a 只读确认 socket 和目标,再运行无隐式建 session 副作用的 tmux-cli status;报 Operation not permitted 说明 socket 被沙箱拦,改在沙箱外重试;
  • 目标 pane 每次重新 discovery,发送只用跨 window 的 full pane id(如 ai-2:1.3),不靠记忆或上次的 id;
  • CLI 类型来自 pane title + pane_current_command(ClaudeAgent-* / CodexAgent-*),不得凭任务角色猜;
  • 目标状态已确认:空闲可输入,或仍在完成同一任务(此时只发补充指令,不 clear);
  • 仅新任务 / 新 gate / 新 slice 才先发 /clear,并等它完成 clear 回到可输入状态;
  • 发送文本不含裸 #数字(改用 PR 45 / PR-45 / 完整 URL);
  • 发送后执行 wait_idle → capture;单次 wait_idle、暂时无输出、主观耗时都不构成完成证据;
  • 完成判定按 Completion Check 的证据规则;并发发送仅限相互独立且写入范围不重叠的任务。

Agent CLI Types

根据 pane title 和 pane_current_command 确认 CLI 类型:

Pane title pattern CLI type Skill trigger
ClaudeAgent-* Claude Code Agent slash command,例如 /planreview
CodexAgent-* Codex Agent dollar skill,例如 $planreview

不得仅凭任务角色猜 CLI 类型。

Pane Discovery

tmux 命令报 error connecting to ... (Operation not permitted) 说明 socket 被沙箱拦,在沙箱外重试。

每次发送前都重新确认目标 full pane id:

tmux list-panes -a -F '#{session_name}:#{window_index}.#{pane_index} #{window_name} #{pane_current_command} #{pane_title}'
tmux-cli status

后续 send、wait_idle、capture 都使用跨 window 的 full pane id,例如 ai-2:1.3。目标 Agent 不在线、pane id 不明确、名称冲突、命令不可用或安装版本不满足上述延迟创建前提时,先报告,不得盲发。

Session Clear

新 assigned task 或新的 gate/slice,先单独发送 /clear,确认目标完成 clear 并回到可输入状态后,再发送正式任务。

如果目标 Agent 仍在完成同一任务、等待补充信息、返回 artifact、修正输出或回答 follow-up,不要 clear,直接发送补充指令。 Agent 仍在工作时不得因耗时长而 clear、覆盖任务或擅自中断。

Send Safety

通过 tmux-cli send 发送文本时避免裸 #数字,使用 PR 45、PR-45、issue 123 或完整 URL。 若内容被截断,不要 clear;重新 discovery 后发送不含裸 #数字 的完整文本。

Read the full file on GitHub · 95 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 29d ago Changed · +4 lines 02bb9a5c1a7b
  2. 1mo ago Changed · +13 lines af8c06534929
  3. 1mo ago Changed · +2 lines 274bb866ca6a
  4. 1mo ago First seen · 76 lines · 42 tokens per session scan A 9be892b6134d

Subscribe to this mod's changes

tmux-agents is a skill published in the GitHub repository noho/code-is-cheap (94 stars, last pushed 7d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,266 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens