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 julianoczkowski/designer-skills --skill design-reviewgit clone --depth 1 https://github.com/julianoczkowski/designer-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/julianoczkowski/designer-skills/design-review)<a href="https://agentmods.dev/skills/julianoczkowski/designer-skills/design-review"><img src="https://agentmods.dev/badge/skills/julianoczkowski/designer-skills/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/julianoczkowski/designer-skills/design-review"><img src="https://agentmods.dev/badge/skills/julianoczkowski/designer-skills/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00053 | $0.03070 |
| Opus 5 | $0.00026 | $0.01535 |
| Sonnet 5 | $0.00011 | $0.00614 |
| Haiku 4.5 | $0.00005 | $0.00307 |
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 13d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill runs a structured design review of what has been built, measured against the design brief and the chosen aesthetic philosophy.
CRITICAL — Visual Screenshot Capture
You MUST capture screenshots of the running application as part of every design review. Code review alone is insufficient — you need to see what the user sees. Follow the screenshot capture protocol in Step 3 below. This is not optional.
Example prompts
- "Review what I just built"
- "Run a design critique on the landing page"
- "Check this against the brief"
- "Here's a screenshot. How does it look?" [paste screenshot]
- "QA pass before I ship this"
Process
-
Read the brief. Look for the active feature's brief at
.design/<feature-slug>/DESIGN_BRIEF.md. If multiple feature folders exist under.design/, ask the user which feature to review. If no.design/folder exists, fall back toDESIGN_BRIEF.mdin the project root. If neither exists, ask the user what the intended design direction was. -
Explore the built code. Examine every component, page, and style file that was created or modified. Scan specifically for:
- All new or modified components and their relationship to pre-existing components
- Token/variable usage: are components using shared tokens or hardcoding values?
- Duplicate components that should be consolidated
- File naming and organization: do new files follow the project's conventions?
- Understand what was actually built, not what was planned.
-
Capture screenshots of the running application.
This step is mandatory. Do not skip it. Do not rely only on user-provided screenshots.
Screenshot Tool Priority
Try each option in order. Use the first one that is available:
- Playwright MCP (preferred). Check if the
plugin-playwright-playwrightMCP server is available. If it is, use it — it gives you precise control over viewport sizing, full-page captures, and file naming. - Cursor IDE Browser (second choice). If Playwright MCP is not available, use the
cursor-ide-browserMCP server'sbrowser_take_screenshottool instead. It has the same core capabilities. - Ask the user (last resort). If neither MCP server nor in-app browser is available, you MUST ask the user to provide screenshots manually. Be specific about what you need:
- "I don't have access to a browser tool. To complete the visual review I need screenshots of the running application. Please provide:"
- A full-page screenshot at desktop width (1280px)
- A full-page screenshot at tablet width (768px)
- A full-page screenshot at mobile width (375px)
- Dark mode variants (if applicable)
- Any specific component or interactive state you want reviewed
- Ask the user to paste/attach the images directly in chat, or to save them into the
screenshots/folder themselves. - Do not skip the visual review. Wait for the user to provide screenshots before proceeding with the checklist.
- Playwright MCP (preferred). Check if the
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.
- 13d ago First seen · 250 lines · 53 tokens per session scan A 009a4312e410
design-review is a skill published in the GitHub repository julianoczkowski/designer-skills (551 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,070 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 $ultragoal 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.