pimux

pimux is a skill for Claude Code from WaterplanAI/agentic-config. It costs 32 tokens per session (232 once invoked), scanned A, original, MIT.

A trigger for spawning and supervising Pi coding agents running inside tmux, a terminal tool that keeps sessions open. It uses messages between agents and sends notifications when follow-up is needed.

In plain words
What is it for?
Use it to start Pi agents in tmux and coordinate their work through explicit messages and notifications.
Why use it?
It avoids repeatedly checking whether child agents have finished and gives supervision updates when activity arrives.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the agentic-config plugin — 49 skills, 1 plugin shipped together

Good fit Use it to start Pi agents in tmux and coordinate their work through explicit messages and notifications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waterplanai/agentic-config/pimux
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 WaterplanAI/agentic-config --skill pimux
Clone the repo
git clone --depth 1 https://github.com/WaterplanAI/agentic-config

Made for: Claude Code.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 1 plugin.

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 pimux

README.md
[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/pimux.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/pimux)
Your own site
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/pimux"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/pimux.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 232 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 $0.00032 $0.00232
Opus 5 $0.00016 $0.00116
Sonnet 5 $0.00006 $0.00046
Haiku 4.5 $0.00003 $0.00023

Measured 8d ago against content hash 256f0a7e2e08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pimux 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 8d 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.

packages/pi-ac-workflow/skills/pimux/SKILL.md · 25 lines

What it actually says

pimux

FIRST: do not poll pimux and do not use Bash sleep/wait loops; wait for delivered child activity.

This skill is a non-authoritative trigger shim for the package-owned pimux extension runtime. Runtime semantics are owned by packages/pi-ac-workflow/extensions/pimux/ and its docs.

Use /pimux or the pimux tool to spawn and supervise tmux-backed Pi agents. The notification behavior is fixed to notify-and-follow-up.

See:

  • ../../extensions/pimux/docs/commands.md
  • ../../extensions/pimux/docs/protocol.md
  • ../../extensions/pimux/docs/patterns.md

Do not duplicate runtime protocol text here. Keep this alias minimal so package docs and extension prompts remain the single source of truth.

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. 8d ago First seen · 25 lines · 32 tokens per session scan A 256f0a7e2e08

Subscribe to this mod's changes

pimux is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 232 once invoked, about $0.0002 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.