ac-workflow-mux

ac-workflow-mux is a skill for Claude Code from WaterplanAI/agentic-config. It costs 27 tokens per session (1,107 once invoked), scanned A, original, MIT.

A coordination skill for tasks too large for one uninterrupted coding session, using waves of work and long-running terminal sessions.

In plain words
What is it for?
Running multi-stage development tasks that need long-lived processes and coordinated waves of execution.
Why use it?
It keeps large jobs organised across multiple execution periods and preserves their working state.

Skill for Claude Code

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

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

Good fit Running multi-stage development tasks that need long-lived processes and coordinated waves of execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waterplanai/agentic-config/ac-workflow-mux
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 ac-workflow-mux
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 ac-workflow-mux

README.md
[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-workflow-mux/github.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-workflow-mux)
Your own site
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-workflow-mux"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-workflow-mux/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 ac-workflow-mux

Your own site · 80×15
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-workflow-mux"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-workflow-mux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 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 $0.00027 $0.01107
Opus 5 $0.00014 $0.00553
Sonnet 5 $0.00005 $0.00221
Haiku 4.5 $0.00003 $0.00111

Measured 9d ago against content hash cf7a592e2db0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ac-workflow-mux 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 9d 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/ac-workflow-mux/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MUX - pi coordinator pattern (pimux runtime)

Use this when the task is too large for one uninterrupted context window and you need mux wave semantics with tmux-backed long-lived execution.

Binding activation

If the user explicitly invokes mux / ac-workflow-mux, or embeds this skill text as the runtime for the task, treat this document as a binding runtime contract, not as optional guidance, commentary, or a planning reference.

Absolute compliance rule

For explicit mux-family triggers in pi, the current session is a pimux-only control plane.

  • FIRST after spawn: do not poll pimux or use Bash sleep/wait loops; wait for delivered child bridge activity.
  • The authoritative pimux extension applies a fail-closed parent control-plane lock for explicit mux-family wrappers.
  • Before the first child exists, the parent must not call Read, Bash, Edit, Write, NotebookEdit, Grep, Glob, web_search, subagent, or any other non-pimux tool for substantive repo work.
  • Do not do substantive repo or domain work in the parent session.
  • Do not use parent-side repo discovery, file inspection, implementation planning, or direct edits before spawn.
  • The first real move is to spawn the authoritative pimux child coordinator.
  • The first observable parent tool call must be pimux spawn.
  • If you have not spawned that child yet, you are not allowed to analyze, compare, implement, or answer the task from the parent.
  • If the parent performs substantive repo inspection or any forbidden tool call before spawn, stop immediately, acknowledge a protocol violation, discard any parent-side conclusions, and restart from pimux spawn.

Parent tool surface

While this skill is active, the parent session is runtime-locked to pimux, AskUserQuestion, and say only:

  • before the first child exists: pimux spawn only
  • AskUserQuestion is allowed only for explicit user clarification that blocks spawn
  • after spawn: notify-first, not poll-first; wait for delivered child bridge activity instead of inspecting live state
  • do not poll pimux or use Bash sleep/wait loops; if you are about to inspect routine progress, stop and wait for delivered child activity instead
  • happy path after spawn forbids status, capture, tree, list, and open; those are recovery-only tools for explicit live inspection, suspected stall/protocol violation/failure, or the inactivity watchdog
  • after a child progress report arrives, use at most one send_message when the child needs input; then wait for closeout or another child report
  • terminal settlement re-arms exactly one final pimux status verification before advancing
  • say is allowed only for short user-attention prompts

Read the full file on GitHub · 88 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. 9d ago First seen · 88 lines · 27 tokens per session scan A cf7a592e2db0

Subscribe to this mod's changes

ac-workflow-mux is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,107 once invoked, about $0.0001 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.