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 sanky369/vibe-building-skills --skill product-design-reviewgit clone --depth 1 https://github.com/sanky369/vibe-building-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/sanky369/vibe-building-skills/product-design-review)<a href="https://agentmods.dev/skills/sanky369/vibe-building-skills/product-design-review"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/product-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/sanky369/vibe-building-skills/product-design-review"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/product-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 | $0.00161 | $0.02128 |
| Opus 5 | $0.00081 | $0.01064 |
| Sonnet 5 | $0.00032 | $0.00426 |
| Haiku 4.5 | $0.00016 | $0.00213 |
Grade A, and why
product-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Design Review
Review a product the way a strong design lead would: walk its real tasks, judge it against explicit heuristics, and deliver findings a team can act on tomorrow. Prime directive: evidence over opinion. Every finding names where it occurs, what the user suffers, and the concrete fix — and never claims to have seen something you didn't actually render. A review that says "improve the hierarchy" has failed; one that says "the destructive Clear action sits one unconfirmed click from the primary CTA (checkout.html:18) — gate it behind a confirm" has done its job.
When to use / when not
- Use for critique of an existing product surface: a page, flow, app, prototype, or design system in use.
- If the user wants the fixes implemented, deliver the review, then route each fix per the table in step 5 — don't rebuild the UI inside this skill.
- If the product's problem is the promise, not the pixels (nobody wants the thing), hand off to
skills/product-strategy/foundation-sprint. - If the user wants a broad "make it better" engagement rather than a review artifact, hand off to
skills/frontend-design/frontend-orchestrator.
Step 1 — Establish evidence mode
Before any judgment, determine what you can actually inspect. Pick the strongest mode available; state which one you're in at the top of the report.
| Artifact | Procedure | Evidence tier |
|---|---|---|
| Live URL + browser automation available (claude-in-chrome, agent-browser, Playwright) | Render it. Screenshot at ~375px and ~1440px. Tab through the primary flow checking focus visibility. Trigger reachable error, empty, and loading states. | Observed |
| Live URL, no browser | Fetch the HTML and CSS. You can verify markup semantics, labels, real color/type values, and compute contrast ratios. You cannot see layout, motion, or states — say so. | Computed |
| Codebase | Read the flow's components, styles, and copy. If the project documents a way to run the app, run it and review rendered output (upgrades findings to observed). | Computed |
| Screenshots / mockups | Visual, copy, and hierarchy critique of what's shown. Keyboard behavior, states, and motion are unverifiable — list them under "needs live check", don't guess. | Observed (static only) |
| Figma link | Use Figma MCP tools (get_screenshot, get_design_context) if connected; otherwise ask for exported frames. |
Observed (static only) |
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.
- 12d ago First seen · 121 lines · 161 tokens per session scan A d5cc1c94e151
product-design-review is a skill published in the GitHub repository sanky369/vibe-building-skills (30 stars, last pushed 2mo ago), licensed MIT. It adds 161 tokens to every session and 2,128 once invoked, about $0.0008 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
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
lfe-visual-check
Inspector sub-skill. Renders the changed UI surface, reasons over the result, and writes a text findings record with a human-action instruction and sign-off token — so a human visual sign-off can close a UI change. Artifact-free (saves no image files). Auto-arms on a visual-file touch; written by the Inspector at…
accessibility-compliance-accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.
avalonia-layout-zafiro
Guidelines for modern Avalonia UI layout using Zafiro.Avalonia, emphasizing shared styles, generic components, and avoiding XAML redundancy.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.