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.
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.
[](https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-notify)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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-exitedfires 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-failedis 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 — asoundsentry for a kind that isn't insoundKindsplays nothing.sounds— per-kind sound. Apreset:<id>or an absolute path. A kind with no entry falls back tosoundFile, and then to the built-in chime.soundFile— the fallback for every kind. Absolute path.
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.
- 13d ago First seen · 129 lines · 198 tokens per session scan A e621abd83035
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.
Other skills, from other repositories
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.
nl-router
Route natural language requests to appropriate skills and workflows by parsing intent and matching trigger patterns.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.