Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/monoes/monomindnpx agentmods add skills/monoes/monomind/monodesignWrote 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/monoes/monomind/monodesign)<a href="https://agentmods.dev/skills/monoes/monomind/monodesign"><img src="https://agentmods.dev/badge/skills/monoes/monomind/monodesign/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/monoes/monomind/monodesign"><img src="https://agentmods.dev/badge/skills/monoes/monomind/monodesign.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 | $0.00052 | $0.06336 |
| Opus 5.5 | $0.00021 | $0.02534 |
| Sonnet 5.5 | $0.00010 | $0.01267 |
| Haiku 4.5 | $0.00005 | $0.00634 |
Grade A, and why
monodesign 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 2d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designs and iterates production-grade frontend interfaces. Real working code, committed design choices, exceptional craft.
Setup
You MUST do these steps before proceeding:
- Run
node .claude/skills/monodesign/scripts/context.mjsonce per session; if the runtime shows this skill's loaded base directory, runnode <skill-base-dir>/scripts/context.mjsinstead. Keep cwd/workdir at the user's project, not the skill directory. If the request names or implies a file, route, or app inside a monorepo, infer the concrete path and append--target <path>to the same command. If you've already seen its output in this conversation, do not re-run it. The script either prints the project's PRODUCT.md (and DESIGN.md when present) as a markdown block, or tells you it's missing. Follow whatever it prints. If it reportsNO_PRODUCT_MD: divert intoreference/init.mdfirst when the user invokedinit,teach,craft, orshape, or when their wording clearly maps to one of those from-scratch build flows (for example: "build/create/make a landing page", "design a new app", or "shape a feature"). Captured product context is the point of those flows. For any other command, a scoped evaluate / refine / enhance / fix / iterate request against existing code, do not divert into init. The existing code is the context: proceed with the requested command, infer the register from the surface in focus (step 4), and offer/monodesign initonce as a suggestion the user can take later. A missing PRODUCT.md must never block a scoped request. If the output ends with anUPDATE_AVAILABLEdirective, follow it (ask the user once about updating, then continue). It never blocks the current task. - If the user invoked a sub-command (
craft,shape,audit,polish, ...), you MUST read the command's reference next:reference/<command>.md, or the native variant from the Commands table (e.g.reference/audit.native.md) when the project platform is native (ios/android/adaptive, per thecontext.mjsdirective). One file, not both. Non-optional. The reference defines the command's flow; without it you will skip steps the user expects. - Familiarize yourself with any existing design system, conventions, and components in the code. Read at least one project file (CSS / tokens / theme / a representative component or page). Required even when you've loaded a sub-command reference in step 2. Don't reinvent the wheel; use what's there when it works, branch out when the UX wins.
- Read the matching register reference. This is non-optional; skipping it produces generic output. If the project is marketing, a landing page, a campaign, long-form content, or a portfolio (design IS the product), read
reference/brand.md. If it is app UI, admin, a dashboard, or a tool (design SERVES the product), readreference/product.md. Pick by first match: (1) task cue ("landing page" vs "dashboard"); (2) surface in focus (the page, file, or route being worked on); (3)registerfield in PRODUCT.md. - If PRODUCT.md's
## Platformisiosorandroid, also readreference/<platform>.md(HIG / Material 3 conventions).adaptive(cross-platform, ships both) reads both files.web, absent, or unrecognized: nothing extra to read.context.mjsprints the directive when one applies. - If the project is brand-new (no existing CSS tokens / theme / committed brand colors found in step 3), run
node .claude/skills/monodesign/scripts/palette.mjsto receive a brand seed color and composition guidance. This is the anchor for your primary brand color. Compose the rest of the palette (bg, surface, ink, accent, muted) around it per the script's instructions. Use OKLCH throughout. Skip this step only if step 3 found committed brand colors in existing tokens; in that case identity-preservation wins.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- adapt.md 2.6 KB
- agents/monodesign-asset-producer.md 8.4 KB
- agents/monodesign-manual-edit-applier.md 7.0 KB
- animate.md 2.8 KB
- audit.md 3.2 KB
- bolder.md 2.3 KB
- clarify.md 2.5 KB
- colorize.md 2.9 KB
- craft.md 2.3 KB
- critique.md 2.8 KB
- delight.md 2.6 KB
- distill.md 2.4 KB
- document.md 2.5 KB
- extract.md 2.5 KB
- harden.md 2.5 KB
- init.md 2.4 KB
- layout.md 2.1 KB
- live.md 2.5 KB
- onboard.md 2.7 KB
- optimize.md 2.4 KB
- overdrive.md 3.0 KB
- polish.md 2.8 KB
- quieter.md 2.4 KB
- reference/adapt.md 10 KB
- reference/adapt.native.md 3.8 KB
- reference/android.md 3.1 KB
- reference/animate.md 10 KB
- reference/antipatterns-catalog.md 29 KB
- reference/audit.md 7.4 KB
- reference/audit.native.md 8.3 KB
- reference/bolder.md 6.8 KB
- reference/brand-workflow.md 6.6 KB
- reference/brand.md 10 KB
- reference/clarify.md 10 KB
- reference/codex.md 6.8 KB
- reference/cognitive-load.md 4.7 KB
- reference/color-and-contrast.md 5.6 KB
- reference/colorize.md 13 KB
- reference/component-specs.md 9.0 KB
- reference/component-states.md 6.7 KB
- reference/component-system.md 9.6 KB
- reference/copy-formulas.md 4.9 KB
- reference/craft.md 12 KB
- reference/critique.md 37 KB
- reference/delight.md 9.5 KB
- reference/design-principles.md 8.5 KB
- reference/distill.md 5.5 KB
- reference/document.md 27 KB
- reference/extract.md 3.3 KB
- reference/harden.md 8.4 KB
- reference/heuristics-scoring.md 8.6 KB
- reference/hooks.md 9.0 KB
- reference/image-prompts.md 6.0 KB
- reference/init.md 18 KB
- reference/interaction-design.md 6.4 KB
- reference/ios.md 3.0 KB
- reference/layout.md 12 KB
- reference/live.md 58 KB
- reference/motion-design.md 5.6 KB
- reference/onboard.md 7.6 KB
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.
- 2d ago First seen · 258 lines · 52 tokens per session scan A 134b071798bc
monodesign is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 6,336 once invoked, about $0.0002 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 2026-10-26.
Other skills, from other repositories
frontend-design
Give a web page or app its own look instead of a generic AI-made one: choose colors, type and layout on purpose before building, then critique the result. Use when building a new interface or reshaping an existing one.
accessibility-audit
Check a live page against the barriers that actually lock people out — keyboard, contrast, labels, focus — each with the fix.
frontend
Two-mode frontend skill: (1) authoring — accessibility, responsive layout, loading/error states, performance, DESIGN.md authoring, visual direction; (2) critique — READ-only scored review of built UI against anchored rubric, AI-slop detection, two isolated assessments. Router invokes mode via context.
accessibility
A guide for designing and checking digital interfaces so people using screen readers, keyboards, or switch controls can use them. It follows WCAG 2.2 Level AA, a common accessibility standard.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
design-audit
Read-only audit of a UI for the "made by AI" look and for design-system drift - generated-UI tells (purple gradients, gradient text, side-tab cards, icon-tile feature grids, kicker labels, buzzword copy), hardcoded colors/sizes bypassing tokens, and the a11y gaps that come with them. Runs a deterministic static scan…