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-themegit 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-theme)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-theme"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-theme/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-theme"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-theme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00168 | $0.01882 |
| Opus 5 | $0.00084 | $0.00941 |
| Sonnet 5 | $0.00034 | $0.00376 |
| Haiku 4.5 | $0.00017 | $0.00188 |
Grade A, and why
mulmoterminal-theme 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make a colour scheme of your own
themes in ~/.mulmoterminal/config.json defines schemes that appear in Settings' picker next to
the four built-ins, and that a project can then name in its .mulmoterminal.json theme key.
Settings can choose a theme; nothing in the app can create one. This skill is that path.
This is the whole app's palette — panel backgrounds, borders, accent, text. A single project's
badge and header colours are a different thing (mulmoterminal-dirs).
How to run this
1. Find out what they're going after
Ask for the direction first, with concrete options rather than "what colours?":
- From something that exists — a painting, a photo, a brand, an editor theme they like. This is the easiest to do well: take 5–8 colours off the source and assign them to roles.
- A variant of a built-in — "Nord but warmer", "Daylight with more contrast". Use
extendsand write only the keys that differ. - Light or dark, if it isn't already obvious. It decides every value below.
2. Decide extends — and know what it costs
{ "id": "arles", "label": "Van Gogh (Arles)", "extends": "daylight", "colors": { "--accent": "#c8971e" } }
- With
extends,colorsis a diff over that built-in (midnight/nord/daylight/solarized). Anything you leave out is inherited. Start here — it is far easier to get right, and a three-key diff is a real theme. - Without
extends, the theme must set every one of the 20 keys below. This is enforced when the config is saved, not when the theme is painted: an incomplete theme with no base is rejected outright rather than half-applied, because the missing half would inherit whatever the previous theme left on the element.
3. Write the colours
Assign the source's colours to roles, then say what each one is doing before you write it. Rules that matter more than taste:
--texton--bg-baseand--bg-panelmust stay readable. Check the WCAG contrast ratio: gamma-decode each channel (c/255, thenc<=0.03928 ? c/12.92 : ((c+0.055)/1.055)^2.4), weight0.2126 R + 0.7152 G + 0.0722 B, ratio(lighter+0.05)/(darker+0.05). Aim for 4.5:1 or better for--text, and don't let--text-mutedfall below 3:1 — a beautiful palette that can't be read is the usual way this goes wrong.--on-accentgoes on--accent-bg, not on the page. Check it against that, and nothing else.- A painting's colours are rarely usable raw. Backgrounds want the muted, desaturated end of the source; the accent wants its most saturated note. Taking six vivid colours and putting them in six roles produces something unusable at 12px.
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 · 129 lines · 168 tokens per session scan A 340c9850532a
mulmoterminal-theme is a skill published in the GitHub repository receptron/mulmoterminal (212 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 1,882 once invoked, about $0.0008 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
uiuxdesign
UI/UX design quality across interfaces - visual design, UX review, accessibility audits, design systems, and design critique - plus modern web frontend implementation. Use for design-quality scoring and refactor loops, design reviews, style selection (40+ named styles), color palettes and font pairing by product type…
opendesign
Generate polished single-file HTML design artifacts using the nexu-io/open-design catalog of production skills and brand-grade design systems. Use when the user asks to design, mock up, prototype, draft, build, or render a visual web artifact, chooses a brand/style direction, requests a deck/PPT, hero, section…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
web-design-reviewer
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage…
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.