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 Harshvardhan86/claude-wave-plugin --skill design-reviewergit clone --depth 1 https://github.com/Harshvardhan86/claude-wave-pluginWrote 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/harshvardhan86/claude-wave-plugin/design-reviewer)<a href="https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/design-reviewer"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/design-reviewer/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/harshvardhan86/claude-wave-plugin/design-reviewer"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/design-reviewer.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 | $0.00050 | $0.00965 |
| Opus 5 | $0.00025 | $0.00483 |
| Sonnet 5 | $0.00010 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
design-reviewer 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Reviewer
You produce the Design Review document for the wave. This phase exists because assumed component APIs and theoretical class names cause more visual bugs than any other failure mode.
Why this skill exists
Past waves burned 20+ iterations on bugs caused by:
- Components misidentified by category ("dropdown" vs "flyout menu") leading to the wrong API being used
- Status attributes that don't render unless paired with a slotted child
- Tailwind classes that look standard but don't compile because the project overrides the config
- Default visual treatments that exist in framework docs but not in the rendered app
You prevent this by reading what the app actually ships, not what it should ship.
Inputs
.wave/ac.mdfrom the AC phase- The project root and its
package.json, design system path (node_modules/<ds>/dist/...or equivalent), and any compiled CSS
Procedure
1. Component API audit
For every design-system component the wave plans to use:
- Read the installed dist files directly. Not the design-system docs site. Not your training data.
- Extract: exact attribute names, slot names, events, shadow-DOM constraints, default styles.
- For each component, write a 5–10 line summary in
.wave/dr.mdlisting the API surface you actually observed. - If a component you assumed exists is missing, say so explicitly in a "Component gaps" section.
2. Compiled CSS audit (visual vocabulary)
- Locate the running app's compiled CSS (e.g.,
dist/,.next/static/css/, or live<style>in dev mode). - Extract the actual color tokens, font weights, spacing values used. Don't trust class-name palettes.
- If the AC phase invented a new token, verify whether it compiles. If not, flag.
3. Per-route mockup
For each route or screen the wave touches, write a markdown mockup like:
## Route: /settings (dark-mode toggle)
Header
└── ThemeToggle (web component: <x-toggle> from your installed design system)
├── attr: aria-pressed → bound to themeStore.isDark
├── attr: variant → "ghost"
└── slot: default → "Dark mode"
Body
└── <body data-theme={theme}>
└── computed style: background-color: var(--color-surface)
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 · 100 lines · 50 tokens per session scan A 21bd1d027d51
design-reviewer is a skill published in the GitHub repository Harshvardhan86/claude-wave-plugin (11 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 965 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
aesthetic-instrument
A committed aesthetic in the sense of skills/committed-aesthetic/SKILL.md: every rule below is checkable, and every value was read out of the source — packages/board/public/index.html and greatcto-site/styles.css — rather than chosen to write this document.
committed-aesthetic
How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick, and it picks the modal option; a committed aesthetic makes it execute one thing precisely, against rules you can check. Use when a design keeps coming out competent and forgettable, when…
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
review
Review the supplied artifact for correctness, security, maintainability, and test coverage. Report concrete findings before general suggestions, and distinguish verified defects from risks.
figma-fetch
Extract frame/component structure and all visible text from a Figma design URL. Use whenever a prompt or a fetched issue contains a figma.com/design or figma.com/file link.
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…