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 vidhunnan/agentic-skills --skill design-critiquegit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/design-critique)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-critique"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-critique/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/vidhunnan/agentic-skills/design-critique"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-critique.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 | $0.00124 | $0.03315 |
| Opus 5 | $0.00062 | $0.01657 |
| Sonnet 5 | $0.00025 | $0.00663 |
| Haiku 4.5 | $0.00012 | $0.00331 |
Grade A, and why
design-critique scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
screenshots, curl a running URL. Full flow. How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-critique
Judges a built thing against what you said you wanted. One question, asked seriously: does this match the stated intent, and where it doesn't, how does it actually read?
Design feedback from a model fails in two directions and this skill is shaped against both. It flatters — every finding hedged into a suggestion, every section opening with what's working — or it produces a checklist of generic improvements that would apply equally to any interface ever built. Both are useless. What's useful is the thing a good design critic does: name how the thing reads to someone encountering it, then say what to do about it.
The hard gate in Step 1 is this skill's expression of ADR 0021, which closes by naming this skill directly: it "may only review against a written brief, because reviewing against nothing is exactly the generation this decision forbids." Critique is a check, and a check needs something to check against.
Three rules govern this skill:
- Diagnosis before prescription. Every finding must first name how the thing reads — in the form "reads as X rather than Y" — before any fix is proposed. No diagnosis, no finding. This is not a stylistic preference: a fix without a diagnosis is a guess, and it's how critique turns into an arbitrary list of changes. Five chips floating in an empty card "read as browser tabs rather than an iteration canvas." That sentence is the entire value of a critique; the fix follows from it in a way it never does from "consider adjusting the spacing".
- Delete is a verdict, and it's first in the list. Most model critique only ever adds — another affordance, another label, another explanatory line. In practice the most common good design move is removal: the redundant CTA, the feature card promising something that doesn't ship yet, the caption explaining what the UI already shows, the greyed-out button that's never enabled.
- Against intent, not against taste. With no written intent this becomes your aesthetic preferences delivered with authority. That's why the gate in Step 1 is hard rather than advisory.
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.
- 11d ago First seen · 269 lines · 124 tokens per session scan A fc47b70d19b1
design-critique is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 124 tokens to every session and 3,315 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.