agentmux

agentmux is a skill for Claude Code, Codex from lout33/termcanvas. It costs 87 tokens per session (2,178 once invoked), scanned A, original, MIT.

An operating manual for controlling TermCanvas agentmux sessions, where terminals are connected as a graph of peer coding agents.

In plain words
What is it for?
Use it to inspect canvases, create or connect agents, delegate tasks, send prompts, read logs, stop agents, delete agents, and understand session state.
Why use it?
It provides the commands and environment setup needed to inspect the live agent graph and manage its sessions instead of operating them manually.

Skill for Claude CodeCodex

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/lout33/termcanvas/agentmux
Any agent
npx skills add lout33/termcanvas --skill agentmux
Clone the repo
git clone --depth 1 https://github.com/lout33/termcanvas

Made for: Claude Code, 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 agentmux

README.md
[![agentmods](https://agentmods.dev/badge/skills/lout33/termcanvas/agentmux.svg)](https://agentmods.dev/skills/lout33/termcanvas/agentmux)
Your own site
<a href="https://agentmods.dev/skills/lout33/termcanvas/agentmux"><img src="https://agentmods.dev/badge/skills/lout33/termcanvas/agentmux.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,178 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 $0.00087 $0.02178
Opus 5 $0.00044 $0.01089
Sonnet 5 $0.00017 $0.00436
Haiku 4.5 $0.00009 $0.00218

Measured 5d ago against content hash 44f55853aafb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentmux 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.

skills/agentmux/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing TermCanvas agentmux agents

TermCanvas managed terminals are agentmux sessions. Each canvas is one agentmux project (for example termcanvas-8a075ab8-e), and each terminal node is an agent in that project. The canvas is a graph of peer agents — there is no commander, no manager, no fixed hierarchy. Use this skill to operate the live agent graph from the terminal.

Resolve the CLI first

Before running commands, resolve the agentmux executable in this order:

if [ -n "${AGENTMUX_BIN:-}" ] && [ -x "$AGENTMUX_BIN" ]; then
  AGENTMUX_CLI="$AGENTMUX_BIN"
elif [ -x "vendor/agentmux/agentmux" ]; then
  AGENTMUX_CLI="vendor/agentmux/agentmux"
elif command -v agentmux >/dev/null 2>&1; then
  AGENTMUX_CLI="$(command -v agentmux)"
else
  echo "agentmux runtime not found"
fi

Then run commands as "$AGENTMUX_CLI" ....

The skill is only the operating manual. The runtime comes from TermCanvas: packaged apps bundle it, development checkouts use vendor/agentmux, and advanced users may install agentmux on PATH.

Inside a TermCanvas-managed terminal, keep AGENTMUX_HOME unchanged. It points the CLI at the app's live agent database; without it, the CLI may read a stale default store and fail to see the current canvas.

Graph model

  • Every agent is a peer. Any agent can spawn children, connect to any other agent in the same project, and delegate work.
  • Spawning (worker, child) records a spawn edge between spawner and child. Agents created without a parent are roots (depth 0, no parent_agent).
  • connect wires any two agents with a link edge. Edges are the addressing layer: ask/check work on agents you are connected to.
  • One project tag equals one canvas. Keep agents in the same project so TermCanvas can materialize them on that canvas.
  • TermCanvas registers every fresh canvas terminal as a root agent at creation (the shell carries AGENTMUX_* env, so harnesses started inside inherit it). Other plain terminals can be adopted into the graph with import (TermCanvas also does this automatically when you use its Connect UI).

Read the full file on GitHub · 202 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 · 202 lines · 87 tokens per session scan A 44f55853aafb

Subscribe to this mod's changes

agentmux is a skill published in the GitHub repository lout33/termcanvas (24 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,178 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 2026-08-30.

Related

Other skills, from other repositories

imap-smtp-email

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

freestylefly/wesight · 82 tokens

hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…

CoWork-OS/CoWork-OS · 155 tokens

hyperframes-cli

HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the…

CoWork-OS/CoWork-OS · 77 tokens

architecture-design

Orchestrate an architectural concept workflow across Rhino, Blender, and ComfyUI connectors.

CoWork-OS/CoWork-OS · 21 tokens

validation

Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether one or more candidate security findings are valid. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

CoWork-OS/CoWork-OS · 54 tokens

fix-finding

Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

CoWork-OS/CoWork-OS · 42 tokens