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 ulises-jeremias/agent-toolkit --skill design-assessmentgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/design-assessment)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/design-assessment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/design-assessment/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/ulises-jeremias/agent-toolkit/design-assessment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/design-assessment.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 | $0.00061 | $0.02346 |
| Opus 5.5 | $0.00024 | $0.00938 |
| Sonnet 5.5 | $0.00012 | $0.00469 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
design-assessment 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Assessment (WHAT)
Assess a product's interface as a design unit delegated by project-assessment. Use this skill when the user asks for a design audit, visual review, UX assessment, accessibility evaluation, design-system compliance check, or distinctive-identity review.
Router contract (ADR-0002 Option A): project-assessment collects evidence via project-assessment-evidence, then delegates to this skill alongside technical-unit-assessment / management-unit-assessment when UI/design is in scope. This skill is also directly invokable for single-page or multi-screen UI audits. It reuses the single evidence framework — do not re-ask evidence already in the map.
Default guardrails
- Apply
project-assessment-evidencebefore scoring. If calling viaproject-assessment, reuse its evidence map — do not duplicate intake questions. - Apply
output-handshakebefore producing any final design assessment report, scorecard, or roadmap. - Never assign a maturity score without evidence. If evidence is missing, mark the indicator as Not assessed or score with Low confidence and state the assumption. Never emit fake precision like
72/100— use rating bands + severity/confidence. - Screenshots must not capture secrets. Observe-only, L1. Redact private data. Keep sensitive details out of reusable artifacts.
- Generic-template risk (distinctiveness) must be context-aware —
rounded cards = badis not a rule. Evaluate whether the aesthetic is distinctive for this product's subject and tone, not via a checklist. - Vision fallback: This skill is
vision-requiredfor full visual critique. If the harness cannot render screenshots/recordings, perform a text-only heuristic review (code, tokens, a11y attributes) and flag each finding with Low confidence — vision unavailable.
Design-unit intake
Ask before scoring (or reuse from router evidence map):
- Product & purpose: product name, audience, single job the page/ flow does
- Scope: screens/flows/components in scope, Figma files / variables, Storybook, Tailwind/config, design-system entry points
- Repositories & assets: app repo(s), component library, token files, asset locations
- Systems of record for design evidence: Figma, Storybook, WCAG reports, performance reports, screenshots, recordings, product analytics, UX research
- Assessment period & audience: who will act on findings
- Decision ownership: who validates subjective visual judgments
What ships with it
1 file 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.
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.
- 1mo ago First seen · 151 lines · 61 tokens per session scan A 28e249cf36ec
design-assessment is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 2,346 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 2026-08-30.
Other skills, from other repositories
vibe-to-ui
Design systems, motion, mood boards, spatial layout, visual assets, Design Context profiles, and a global Inspiration Library from screenshots, website URLs, inspiration images, music, or fuzzy aesthetic intent. Classifies page archetype, explores 3 product-aware directions before locking tokens (unless exact…
ui-ux-design
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, modals, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work. Use even when the user…
ndv-perceptual
Perceptual cognition module. Injects simultaneous read-as-rendered vision into any phase where visual or UX quality is a concern — implementation review, component assessment, UI audit steps within a larger workflow. Source: ndv-design (Pixel).
design-logo
Generate a commercial-grade SVG logo for a project by reading its codebase and iterating with the user.
figma
Read Figma design files, nodes, rendered images and comments via the Figma REST API. Use when the user mentions Figma, a figma.com file link, implementing a design as code, extracting design tokens / colors / spacing, or summarizing comments on a design.
ux-audit
Production-grade UX audit and design guidance skill. Transforms vague design feedback into actionable, implementable recommendations. Two modes: guide (principles + do/don't rules for modern interfaces) and review (structured audit with prioritized fixes). Covers task-first UX, information architecture, CRAP visual…