mulmoterminal-notify

mulmoterminal-notify is a skill for Claude Code, Codex from receptron/mulmoterminal. It costs 198 tokens per session (1,843 once invoked), scanned A, original, MIT.

A notification setup for MulmoTerminal, a tool that runs coding-agent sessions. It lets you choose which events trigger sounds or push messages, including when a turn finishes or the agent needs input.

In plain words
What is it for?
Use it to configure sounds and push notifications for completed turns, waiting agents, finished or failed commands, closed sessions, and CI-failing pull-request phases.
Why use it?
Running several agent sessions can create too many interruptions. This helps you hear only the events you consider important, with separate settings for one project if needed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/you/sounds/done.mp3.

Good fit Use it to configure sounds and push notifications for completed turns, waiting agents, finished or failed commands, closed sessions, and CI-failing pull-request phases.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 mulmoterminal-notify

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-notify"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-notify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,843 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 $0.00198 $0.01843
Opus 5 $0.00099 $0.00922
Sonnet 5 $0.00040 $0.00369
Haiku 4.5 $0.00020 $0.00184

Measured 13d ago against content hash e621abd83035, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mulmoterminal-notify 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 13d 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.

server/skills/mulmoterminal-notify/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Which moments notify you, and how

Running several agents at once is what turns notifications into noise, so the defaults are deliberately narrow: only finished and waiting beep, and the other four are opt-in.

Ask what they actually want to be interrupted for before changing anything. "Turn on all six" is almost never the right answer.

The six moments

Kind Fires when Beeps by default
finished The turn ended; output is waiting to be reviewed yes
waiting The agent is blocked on input — a permission prompt or a question yes
command-done A Run cell's command exited 0 no
command-failed A Run cell's command exited non-zero no
session-exited A session's PTY ended no
pr-ci-failed A directory's PR phase became CI-failing no

Two of these have caveats worth saying out loud:

  • session-exited fires when you close a cell yourself. Closing goes through the same path, so someone who enables it will hear it on every deliberate close and think it is misfiring.
  • pr-ci-failed is only seen while the roster is on screen. The phase poll doesn't run otherwise, so a failure that lands while the user is in another view is never noticed. It is not a background CI watcher; don't offer it as one.

Sound — global

Settings has a UI for this (Notification sounds), so use this skill when the user wants something the UI makes tedious — a different sound per moment, or per project.

{
  "soundKinds": ["finished", "waiting", "command-failed"],
  "sounds": { "waiting": "preset:coin", "command-failed": "preset:gong" },
  "soundFile": "/Users/you/sounds/done.mp3"
}
  • soundKinds — which moments beep. Omit to keep ["finished", "waiting"]; [] for silence. Listing a kind here is what makes it audible at all — a sounds entry for a kind that isn't in soundKinds plays nothing.
  • sounds — per-kind sound. A preset:<id> or an absolute path. A kind with no entry falls back to soundFile, and then to the built-in chime.
  • soundFile — the fallback for every kind. Absolute path.

Read the full file on GitHub · 129 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. 13d ago First seen · 129 lines · 198 tokens per session scan A e621abd83035

Subscribe to this mod's changes

mulmoterminal-notify is a skill published in the GitHub repository receptron/mulmoterminal (212 stars, last pushed today), licensed MIT. It adds 198 tokens to every session and 1,843 once invoked, about $0.0010 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.