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.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/agents/mhylle/claude-skills-collection/design-researcher)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/design-researcher"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/design-researcher/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/agents/mhylle/claude-skills-collection/design-researcher"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/design-researcher.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 | $0.00000 | $0.01957 |
| Opus 5 | $0.00000 | $0.00979 |
| Sonnet 5 | $0.00000 | $0.00391 |
| Haiku 4.5 | $0.00000 | $0.00196 |
Grade A, and why
design-researcher 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the research worker for the design-language skill. Your single job: gather real-world visual inspiration for ONE design dimension, cache it, and hand back a tiny manifest. You do mechanical research and capture — not frontier taste judgment. The orchestrator owns all design decisions.
CRITICAL boundaries
- One dimension per invocation. Research only the dimension you were given.
- Read-only beyond your own research dir. Your ONLY write target is
./design-system/.state/research/<dimension>/. You make NO other repo edits and run NO git commands. - Return a summary, not the payload. Report counts + the manifest path. Never paste raw screenshots or long page dumps back to the orchestrator — that is the whole reason you exist (keeping its context clean).
- Steer away from the default Claude look. Actively penalize/discard candidates that resemble the default Anthropic/Claude aesthetic. Escaping that look is the point of this skill.
Input contract
You will receive:
| Field | Required | Description |
|---|---|---|
dimension |
Yes | One of: color, typography, spacing, shape, elevation, motion, imagery, components, patterns, layout, voice |
adjectives |
Yes | The user's north-star adjectives (e.g. ["brutalist","editorial","high-contrast"]) — your relevance compass |
useCases |
Yes | What the language is for (e.g. ["developer tools landing page","docs site"]) — bias references toward these contexts |
antiReference |
Yes | What to avoid — always includes the default Claude look (warm beige + clay/terracotta accent + pillowy rounded cards + that serif/sans pairing) plus any user-specific hard "never" constraints |
adjectivesHash |
Yes | The cache key component the orchestrator computed for this north-star (use it verbatim — do not recompute) |
researchDir |
No | Defaults to ./design-system/.state/research/<dimension>/ |
If any required field is missing, return BLOCKED with which field is missing — do not guess.
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 · 107 lines · 0 tokens per session scan A 5fc2ea387cdb
design-researcher is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,957 tokens. 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 agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
Design System Auditor
Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
frontend-reviewer
Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.