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.
npx skills add receptron/mulmoterminal --skill mulmoterminal-configgit clone --depth 1 https://github.com/receptron/mulmoterminalWrote 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-config)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-config"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-config/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-config"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 122 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 149 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 160 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00374 | $0.05613 |
| Opus 5 | $0.00187 | $0.02806 |
| Sonnet 5 | $0.00075 | $0.01123 |
| Haiku 4.5 | $0.00037 | $0.00561 |
Grade A, and why
mulmoterminal-config scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:${MULMOTERMINAL_PORT:-34567}/api/config" How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring MulmoTerminal — start here
This skill does two things: it routes to whichever skill owns what the user wants, and it reports on how things are configured right now. Anything that writes a setting lives in a sibling skill.
Where settings live
| Place | What | Written by |
|---|---|---|
| Settings modal | Theme, terminal font size / family / scroll, roster rows, the grid header's load read-out, notification sounds, Push, PR repos, self-hosted GitLab, work comments, PR footer, closing summary, decision digest, dev-work log, copy-on-select, Enter behaviour, launch commands, phone quick commands, MCP servers | the user, in the UI |
~/.mulmoterminal/config.json |
Everything global — including the five Settings can only SHOW, never edit: keymap, themes, providers, customAgents, buttons / chips |
these skills, or by hand |
<project>/.mulmoterminal.json |
Per-project appearance and behaviour. No UI writes this file | these skills only |
Check Settings first when a request is one setting. Most global settings now have a control there, so "turn on work comments" is a click rather than a skill run — say where it is and let them choose. The five above are the exception: a keymap binding, a colour scheme, a backend, your own Claude Code command, a header button. Settings SHOWS each of them — what is configured now, and for a backend whether it can be reached — but cannot edit them: they are structured enough to need the questions a skill asks. Every one of those sections carries a button that launches the owning skill.
Routing
Ask what they want to change — one AskUserQuestion, concrete options — then invoke that skill and
carry on there. Do not re-explain its contents here; the sibling skill is the source of truth.
Two of those areas own a GLOBAL key as well as a per-project one, and the skill owns both halves:
mulmoterminal-dirs for headerStatusColors / headerStatusTint (the header while a session is
running), mulmoterminal-notify for the sounds. Route rather than editing the global file here.
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.
- yesterday Changed · +26 lines a8b912c1f4fb
- 3d ago Changed · +28 lines · +9 tokens per session caf3348c70ea
- 8d ago Changed · +28 lines · +9 tokens per session a539694f1746
- 13d ago First seen · 301 lines · 356 tokens per session scan A 129e4f0a7302
mulmoterminal-config is a skill published in the GitHub repository receptron/mulmoterminal (212 stars, last pushed today), licensed MIT. It adds 374 tokens to every session and 5,613 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.