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-keysgit 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-keys)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-keys"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-keys/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-keys"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-keys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 3 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 Rogue Agent · line 64 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 Excessive Agency · line 196 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.
- medium Excessive Agency · line 198 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 | $0.00310 | $0.10451 |
| Opus 5.5 | $0.00124 | $0.04180 |
| Sonnet 5.5 | $0.00062 | $0.02090 |
| Haiku 4.5 | $0.00031 | $0.01045 |
Grade A, and why
mulmoterminal-keys 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 18d 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 — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keyboard, shortcuts and clipboard
These settings all live in ~/.mulmoterminal/config.json, and each write is a partial
POST /api/config merge — write only the key you are changing, so the user's other settings
survive.
"Partial" means per TOP-LEVEL key, and keymap is replaced WHOLE. The merge is
body[key] !== undefined ? sanitize(body[key]) : current (server/config/app-config.ts), so
posting
{ "keymap": { "send": [ … ] } }
does not add a send to the keymap — it makes that the entire keymap, deleting every action
binding the user had. Nothing warns, and the reply is a success.
So a keymap write always sends the complete keymap: what step 1 read, plus the change. Read it,
merge in memory, post the whole thing. An entry naming an action this version does not know (a typo like
zoom-toogle, or a newer release's action) is kept in the file whatever you post, including when you leave
it out (GET /api/config does not return it) — to remove one, edit config.json directly. Every keymap example below shows one setting on its own for
readability — none of them is a body to post as-is unless the user genuinely has nothing else bound.
Settings has a Keyboard shortcuts section: every action and its current binding, plus a send row
(one per configured entry, or a single "Not set" placeholder). Each action row has Change, which
records the next keystroke pressed and saves it at once (a single keystroke — a two-key sequence and
the send list are still written here), and Clear. A binding that would stop the server from
starting is refused there, and one the browser keeps is saved with a warning. Point the user at it
after writing, as the check — or at Change, when all they want is one single-key shortcut. Below the list, Recommended keys
adds this browser's platform's starter set (Mac: the Up/Down pair of Arrows plus the macOS
line-editing send set; Windows/Linux: all four Arrows) in one click — only to actions that are
unbound and keys nothing starts with, so it never replaces a binding. Anything beyond that set, or a
different key, is still this skill's job.
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.
- 18d ago Changed · +22 lines 9642a700acd9
- 21d ago Changed · +1 lines c4c2c0128ac4
- 27d ago Changed · +2 lines 4a2e815029b7
- 28d ago Changed · +3 lines · +5 tokens per session f40fb79cb675
- 29d ago Changed · +66 lines · +16 tokens per session 770b5fc28149
- 1mo ago Changed · +3 lines 655c09672786
- 1mo ago Changed · +24 lines 62f6e3434543
- 1mo ago Changed · +3 lines 02f652c59e04
- 1mo ago Changed · +10 lines edf4997b28f2
- 1mo ago First seen · 370 lines · 289 tokens per session scan A 6a8514f518a2
mulmoterminal-keys is a skill published in the GitHub repository receptron/mulmoterminal (255 stars, last pushed yesterday), licensed MIT. It adds 310 tokens to every session and 10,451 once invoked, about $0.0012 per session on Opus 5.5. 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
refit
Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, and plan notepads. Every finding lands on the surface that owns the fix (deterministic check, steering volume, tooling, or information access); nothing is written without user approval.
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
moai-factory-foreman
One unattended factory foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
moai-gtd
Canonical GTD entry point for capture, clarification, organization, review, and engagement.
moai-todo
Compatibility alias for the canonical GTD task-management entry point.
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.