cmux-orchestrate

cmux-orchestrate is a skill for Claude Code from EternallLight/tgc-skills. It costs 71 tokens per session (2,559 once invoked), scanned A, original, MIT.

A skill for controlling cmux, a terminal workspace that can contain panes, tabs, and other coding-agent sessions. It helps an agent inspect and coordinate those terminal areas.

In plain words
What is it for?
Opening or arranging cmux panes and tabs, reading their screens, sending commands, answering prompts, and checking for unread activity.
Why use it?
Working across several terminal panes can otherwise require manual switching and repeated commands. This provides a defined way to find activity and communicate with other sessions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Part of the tgc-skills plugin — 9 skills shipped together

Good fit Opening or arranging cmux panes and tabs, reading their screens, sending commands, answering prompts, and checking for unread activity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eternalllight/tgc-skills/cmux-orchestrate
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 EternallLight/tgc-skills --skill cmux-orchestrate
Clone the repo
git clone --depth 1 https://github.com/EternallLight/tgc-skills

Made for: Claude Code.

Or install tgc-skills, the plugin that ships this one along with the rest of its 9 skills.

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 cmux-orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/eternalllight/tgc-skills/cmux-orchestrate/github.svg)](https://agentmods.dev/skills/eternalllight/tgc-skills/cmux-orchestrate)
Your own site
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/cmux-orchestrate"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/cmux-orchestrate/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 cmux-orchestrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/cmux-orchestrate"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/cmux-orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,559 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 $0.00071 $0.02559
Opus 5 $0.00036 $0.01280
Sonnet 5 $0.00014 $0.00512
Haiku 4.5 $0.00007 $0.00256

Measured 12d ago against content hash c225f38a4d9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cmux-orchestrate 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 12d 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/cmux-orchestrate/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cmux Orchestrate

Drive a cmux terminal workspace — build pane layouts, name tabs, send work to worker panes, read their screens, and answer the agents running inside them — translating the user's plain English into real cmux CLI calls fast, without paging through help every time.

cmux is agent-first: it exposes a Unix-socket CLI so an agent can inspect and control the whole window/workspace/pane/surface tree. You don't memorize a GUI; you read the surface and act on it.

Trigger eagerly even when the user does not say "cmux" but is clearly orchestrating terminal panes: "open a pane", "split the terminal", "the agent in my other tab", "my worker panes", "check the other pane", "send X to the left pane", or "jump to whatever needs input".

0. Gate: are we even in cmux?

Before running any cmux command, confirm the environment:

[ -n "$CMUX_SURFACE_ID" ] && echo "in cmux: surface $CMUX_SURFACE_ID" || echo "NOT in cmux"

If $CMUX_SURFACE_ID is empty, you are not in a cmux workspace. Tell the user, and do not run cmux orchestration commands. (cmux may still launch a new workspace via cmux <path>, but pane/surface control assumes you're inside one.)

$CMUX_SURFACE_ID is this pane (where you're running). That's how you tell yourself apart from workers.

Golden rules

  1. Don't invent flags. The cheat sheet below is verified. For anything else, check cmux <command> --help or references/cmux-cli.md. The CLI is the source of truth; your memory of it may be stale.
  2. --json is a global flag — it goes BEFORE the subcommand: cmux --json tree, not cmux tree --json.
  3. Re-inspect before you act on a worker. Refs like surface:21 / pane:19 and indexes can shift as panes open/close. Run cmux --json tree (or cmux list-panes) to get current refs right before targeting one. Need durable IDs? add --id-format uuids.
  4. cmux send only TYPES text. To make a worker actually run a command or submit a prompt, it must receive Enter. For short commands, ending the text with \n works (\n/\r → Enter, \t → Tab). For long prompts, a trailing \n is often swallowed into a bracketed paste — send the text first, then submit with a separate cmux send-key --surface surface:N enter.
  5. Single-quote free text — never double-quote it. Always pass task text as -- '<task>'. Inside double quotes the shell expands $(), backticks, and $VAR in YOUR (manager) shell before cmux ever sees the text — command injection and credential leakage. If the text itself needs a single quote, rephrase to avoid it (e.g. don'tdo not).
  6. Prefer panes over tab groups — tab groups are easy to lose track of.
  7. Keep upfront planning human-led. Confirm the layout/plan with the user before fanning out workers.
  8. Pick the worker model and effort deliberately. Workers don't need the orchestrator's model tier — a cheaper model (e.g. claude --model sonnet) keeps cost and latency down. Effort follows the task: high for open-ended research or investigation; medium for well-specified implementation against a locked plan (the orchestrate-plan skill mandates this). This applies only to workers you spawn, never to the Manager pane (you).

Read the full file on GitHub · 139 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. 12d ago First seen · 139 lines · 71 tokens per session scan A c225f38a4d9b

Subscribe to this mod's changes

cmux-orchestrate is a skill published in the GitHub repository EternallLight/tgc-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 2,559 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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