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-headergit 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-header)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-header"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-header/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-header"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-header.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 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 | $0.00200 | $0.03130 |
| Opus 5 | $0.00100 | $0.01565 |
| Sonnet 5 | $0.00040 | $0.00626 |
| Haiku 4.5 | $0.00020 | $0.00313 |
Grade A, and why
mulmoterminal-header 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 12d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Header buttons and chips
A session header carries buttons (things you can do) and chips (things you can read). Both are configured in two places and merged, and the two merge by different rules — that asymmetry is the thing to get right, and it has no UI anywhere.
Where to write it
| File | Applies to | Settings UI |
|---|---|---|
~/.mulmoterminal/config.json → buttons / chips |
every directory | none |
<project>/.mulmoterminal.json → buttons / chips |
that project | none |
Ask which the user means. "A button for yarn build" is usually per-project (the command only
exists there); "show me the branch everywhere" is global.
Global writes are a partial POST /api/config merge — send only buttons / chips. Per-project
writes go through your Write/Edit tool, and writing the file is itself the live-reload signal;
there is no filesystem watcher.
"Partial" is per TOP-LEVEL key, and buttons / chips are each replaced WHOLE. The merge is
body[key] !== undefined ? sanitize(body[key]) : current (server/config/app-config.ts), so posting
{ "buttons": [{ "id": "build", "icon": "build", "label": "Build", "run": "shell", "cmd": "yarn build" }] }
does not add a button — it makes that the entire global set, deleting every other button the user had. Nothing warns, and the reply is a success.
So a global write always sends the complete array: read the current one first, add or change your entry in memory, and post the whole thing. Every example below shows the entries under discussion on their own for readability — none of them is a body to post as-is unless the user genuinely has no others.
Three different "replace" rules live here and are easy to run together:
writing buttons to the global config |
replaces the whole global array — the one this section is about |
listing buttons at any level |
replaces DEFAULT_BUTTONS; the built-ins are not merged in |
| project vs global | merged, keyed by id — a project adds or overrides without restating |
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.
- 12d ago First seen · 238 lines · 200 tokens per session scan A 55f07b116e6b
mulmoterminal-header is a skill published in the GitHub repository receptron/mulmoterminal (212 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 3,130 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.