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 designgit 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/design)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/design"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/design/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/design"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/design.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 | $0.00033 | $0.00976 |
| Opus 5.5 | $0.00013 | $0.00390 |
| Sonnet 5.5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
blueprint-from-collection-design 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 14d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The look
The person used this collection in MulmoTerminal and knows how it looks there. Unless they chose a template, the app
should look the same. The design is the design answer in .blueprint/answers.json (missing means
MulmoTerminal と同じ).
- Tailwind and the icon font. Add
tailwindcss,@tailwindcss/viteandmaterial-symbolswithyarn add -D. Puttailwindcss()in thepluginsof the web app'svite.config, and start the main stylesheet with@import "tailwindcss";. Importmaterial-symbols/outlined.cssonce, where the app starts. - The template, if one was chosen. The usecase pack's
design/themes/<theme>.css(softfor やわらかい,crispfor くっきり,calmfor 落ち着いた) is copied into the web app unchanged and imported right after@import "tailwindcss";. It redefines the colours and corners the classes below use, so nothing else changes. ForMulmoTerminal と同じthere is no template: do not redefine any colour. - The screens. Read the usecase pack's
design/mulmoterminal.md: the classes MulmoTerminal's collection screens use, copied from them. Rewrite every screen the earlier steps made (list, kanban, calendar, detail, forms, sign-in, errors) with those classes and that structure — the same header, toolbar, table, pills, cards and record panel. Keep each screen's behaviour, text and tests; change markup and classes only. Write class names out in full (Tailwind only sees complete names); a choice between classes is a lookup table of whole strings, as the reference does. Remove the plain CSS the classes replace. - Each collection's own icon.
.blueprint/source/source.jsonlists every copied collection's slug incollections(itsstartis the source's name, which for a shared app is the app's title, not a slug). Eachcollections/<slug>/schema.jsonmay haveicon(a Material Symbols name): show it in the icon box beside that collection's title, drawn as the reference draws it — MulmoTerminal does not colour that box by the collection'scolor, so neither does the app. DESIGN.mdat the app's root, for the person and for every later step: the design chosen (its answer, word for word), the template file if any, and the rule that new screens usedesign/mulmoterminal.md's classes — so the screens later steps add look like the rest.- Run
yarn buildand the tests, and fix what the markup change broke without weakening a test. Keep Vite's output in a folder nameddist(dist/,dist/client/,client/dist/): the check reads the built stylesheet there.
Done when the check passes: yarn build succeeds, and the stylesheet it wrote has MulmoTerminal's main button
(.bg-indigo-600), one class of each screen's own (the header's icon box, the table's cells, the record panel's field grid, and the
kanban's columns or the calendar's day cells when the collection has them — see design/mulmoterminal.md), the Material Symbols font, and the chosen design's colour and corner values (Tailwind's own for
MulmoTerminal と同じ, the template's otherwise); the screens use material-symbols-outlined and the collection's
icon; DESIGN.md names the design.
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.
- 14d ago First seen · 49 lines · 33 tokens per session scan A 239b9f3f0d8f
blueprint-from-collection-design is a skill published in the GitHub repository receptron/mulmoterminal (238 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 976 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons.
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.
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.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
page-prototype
An HTML wireframe tool for making a rough, clickable model of one page or screen. A wireframe shows structure and interactions with simple gray boxes rather than finished visual design.
brand-tokens
A reference library of visual design rules for well-known brands, including colors, fonts, corner shapes, and explanations of each brand's visual style. Design tokens are reusable values that keep an interface's appearance consistent.