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 dvdarkin/claude-skills --skill benji-taylor-design-evalgit clone --depth 1 https://github.com/dvdarkin/claude-skillsWrote 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/dvdarkin/claude-skills/benji-taylor-design-eval)<a href="https://agentmods.dev/skills/dvdarkin/claude-skills/benji-taylor-design-eval"><img src="https://agentmods.dev/badge/skills/dvdarkin/claude-skills/benji-taylor-design-eval/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/dvdarkin/claude-skills/benji-taylor-design-eval"><img src="https://agentmods.dev/badge/skills/dvdarkin/claude-skills/benji-taylor-design-eval.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 | $0.00069 | $0.01578 |
| Opus 5 | $0.00034 | $0.00789 |
| Sonnet 5 | $0.00014 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
benji-taylor-design-eval 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 11d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benji Taylor Design Evaluation
Overview
Structured design critique based on the principles Benji Taylor has articulated and demonstrated through his work on the Family self-custody wallet, Base (Coinbase L2), and X. Surfaces real tensions in a design and where it resolves or fails them -- not a scorecard with arbitrary numbers.
When to Use
- User asks to critique, review, audit, or score a product's design
- User asks "is this well designed" or "how would a great designer look at this"
- User wants to improve the design quality of their own product or feature
- Reviewing screenshots or mockups for design principles compliance
When NOT to use:
- Pure developer tooling (delight and fluidity have different meanings in CLI/API contexts)
- Enterprise software (progressive disclosure is often inverted by necessity)
- Flag and adapt if the product falls in these categories rather than skipping entirely
Quick Reference
| Dimension | Core Question |
|---|---|
| Progressive Disclosure | Does complexity appear only when needed? |
| Fluidity | Does motion communicate state changes? |
| Simplicity/Fluidity/Delight | Are all three present, not just one? |
| Craft | Are edge cases designed with equal care? |
| Trust Through Clarity | Are high-stakes actions unambiguous? |
| Accessibility Without Depth | Can novices and experts coexist? |
The Six Evaluation Dimensions
1. Progressive Disclosure
The principle: Fundamentals at your fingertips. Everything else appears as it becomes relevant. Never dump all features at once.
What to look for:
- Does the first screen show only what a new user needs?
- Are advanced features gated behind discovery (not hidden, but not foregrounded)?
- Is there a coherent mental model for what is always visible vs. what appears contextually?
Failure modes:
- Settings exposed before the user has done anything
- Feature parity between power and novice users baked into primary navigation
- Long lists of options when a single default would serve 80% of users
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.
- 11d ago First seen · 183 lines · 69 tokens per session scan A c6d64613dd1a
benji-taylor-design-eval is a skill published in the GitHub repository dvdarkin/claude-skills (11 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,578 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.