mux-ospec

mux-ospec is a skill for Claude Code from WaterplanAI/agentic-config. It costs 34 tokens per session (541 once invoked), scanned A, original, MIT.

A trigger alias for a workflow that coordinates specification stages through pimux, a terminal-based runtime controller.

In plain words
What is it for?
Use it to start a specification workflow from a provided file or prompt, then continue through the tmux-backed stage process as child updates arrive.
Why use it?
It keeps specification work in the project’s required staged process and lets the runtime manage stage creation and control locks.

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 a specification workflow from a provided file or prompt, then continue through the tmux-backed stage process as child updates arrive.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/mux-ospec"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/mux-ospec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 $0.00034 $0.00541
Opus 5 $0.00017 $0.00270
Sonnet 5 $0.00007 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 9d ago against content hash 9addf4689df4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mux-ospec 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/mux-ospec/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mux-ospec

This skill is a package-owned trigger alias for ac-workflow-mux-ospec. It is not an independent spec-stage workflow definition.

Delegate workflow semantics to ../ac-workflow-mux-ospec/SKILL.md and runtime semantics to ../../extensions/pimux/docs/.

Mandatory trigger behavior

If the user explicitly triggers mux-ospec, keep work in the tmux-backed stage lane.

Required sequence:

  1. after spawn, do not poll pimux or use Bash sleep/wait loops; wait for delivered child bridge activity
  2. pass through an explicit spec path unchanged when the user provides one; if the target is valid but missing, let the authoritative pimux runtime create it instead of blocking
  3. if the user provides an inline prompt without a spec path, let the authoritative pimux runtime derive/create the next current-branch spec path by following recent current-branch spec-path patterns and the spec skill convention
  4. use AskUserQuestion only when the user provided neither a spec path nor an inline prompt that is sufficient to spawn
  5. let the authoritative pimux extension enforce the fail-closed parent control-plane lock
  6. spawn the stage-owning pimux child before substantive stage work
  7. after spawn, run notify-first rather than poll-first: do not call status, capture, tree, list, or open on the happy path
  8. after a child progress report, use at most one send_message if input is needed, then wait again
  9. use status / capture / tree / list / open only for explicit live inspection, suspected stall/protocol violation/failure, or the inactivity watchdog
  10. after terminal settlement, do one final pimux status verification and then advance

Do not run spec-stage execution directly in the parent while this skill is active. Do not use parent-side Read, Bash, or manual repo discovery to figure out the spec before spawn. Do not poll pimux or use Bash sleep/wait loops; wait for delivered child activity, and treat status / capture / tree / list / open as recovery-only.

Read the full file on GitHub · 36 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 · 36 lines · 34 tokens per session scan A 9addf4689df4

Subscribe to this mod's changes

mux-ospec is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 541 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.