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 vasuag09/harness-claude --skill design-reviewgit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/design-review)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/design-review"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/design-review/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/vasuag09/harness-claude/design-review"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/design-review.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 | $0.00068 | $0.01069 |
| Opus 5 | $0.00034 | $0.00535 |
| Sonnet 5 | $0.00014 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
design-review 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-review — craft & UX gate
Goal: prove a user-facing change is crafted, not merely correct, before it merges. The
design counterpart to /harness-claude:security-review — a conditional VERIFY gate that
blocks on Blockers. It checks the build against the design brief from /harness-claude:design
and the bar in references (skills/design/references/review-bar.md + ux-floor.md).
When to use
Only when the change touched a user-facing surface (a page, screen, component, form,
email, CLI/TUI presentation). Internal/back-end changes skip — say so. Run it in parallel
with /harness-claude:review and /harness-claude:security-review when the change is both
UI- and security-sensitive.
Do this
- Scope & intent. Bound what's under review (the branch's UI diff, or a named surface).
Read the
/harness-claude:designbrief if one exists, and the project's saved design-system note (e.g..design/system.md) if present — review against the design's own intent, not a generic ideal. Apply the harness's review standard inreferences/review-bar.md. - See the whole first (squint, before line-picking): does one thing lead, or is it a
parking lot? Does it breathe, or a monotone grid? Does it look like this product? The
worst slop is compositional. Squint the rendered output, not the source — serve it over
http and screenshot (a headless browser usually blocks
file://); a picture is worth 1000 tokens. - Run the lenses independently (review-bar.md): Hierarchy · Type & color · Surfaces & depth · Composition & rhythm · States/polish/motion · Structure-reuse-content.
- Apply the floor (ux-floor.md): a11y §1 + touch §2 are hard gates — contrast 4.5:1, visible focus, keyboard nav, 44px targets, reduced-motion. Automated checks catch ~30%; the floor isn't met until you've manually exercised it — keyboard-only through the whole flow, a screen reader (VoiceOver/NVDA) over the key path, and 200%/400% zoom without breakage. Cite the specific WCAG success criterion per failure (e.g. 1.4.3 contrast, 2.1.1 keyboard, 2.4.7 focus-visible). A failure here is a Blocker, full stop.
- Score and filter. Tag each finding Blocker / Should-fix / Note. Cut false positives:
taste, a bold choice working as intended, out-of-scope/untouched lines, anything
system.mdratifies, lint/format concerns. A few high-conviction findings beat forty nitpicks.
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 · 63 lines · 68 tokens per session scan A 59290e07de23
design-review is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,069 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 2026-08-31.
Other skills, from other repositories
frontend-taste
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…
design-tokens
Project-level DESIGN.md tokens reference. When the project has a DESIGN.md file, agents producing UI / components / visuals must consult this skill to use canonical color/typography/spacing tokens rather than inventing new ones. Triggers on: UI generation, component creation, design brief, visual asset, tailwind…
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
design
UI/UX, visual hierarchy, typography, color theory, design systems, accessibility, and prototyping skills. From wireframes to production-ready interfaces with research-backed decisions. Triggers on: UI, UX, design system, typography, color palette, wireframe, prototype, accessibility, visual hierarchy.
design-taste-frontend
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.