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 dorayo/orchestrix-skills --skill design-reviewgit clone --depth 1 https://github.com/dorayo/orchestrix-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/dorayo/orchestrix-skills/design-review)<a href="https://agentmods.dev/skills/dorayo/orchestrix-skills/design-review"><img src="https://agentmods.dev/badge/skills/dorayo/orchestrix-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/dorayo/orchestrix-skills/design-review"><img src="https://agentmods.dev/badge/skills/dorayo/orchestrix-skills/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 | $0.00035 | $0.02984 |
| Opus 5 | $0.00017 | $0.01492 |
| Sonnet 5 | $0.00007 | $0.00597 |
| Haiku 4.5 | $0.00003 | $0.00298 |
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 7d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Review a built UI with a senior designer's eye. The visual counterpart of
review-code: three verdicts, in order — does it match the spec, does it
actually render correctly, and is it world-class.
Core principle: You cannot review design from source. Render it and look at the pixels. A claim about how it looks, without a screenshot, is a guess — the visual equivalent of claiming tests pass without running them.
The Iron Law
UNRENDERED IS NOT PASSED. Every check ends in exactly one of:
pass (with evidence) | fail (with evidence) | untested (with the reason)
A review run without a browser is a partial review, and says so. It is never a clean one.
Inputs
built_ui— the running app (a live URL, or a dev server this skill starts).ui_spec—specs/<slug>-ui.mdit must satisfy, including its declared treatment (utility/product/editorial).ui_artboards?— the artboards the human approved at thedesign-uigate (specs/design/<slug>/). They are the visual bar for Verdict 3: a built screen that departs from its approved artboard in hierarchy, spacing, or treatment is a finding, at the same severity as a deviation from the system.screenshots?— captures a priorsmoke-testalready took. Use them instead of relaunching the app for the same screen.- Read
taste/design-system+taste/brand— the bar to calibrate against. Deviations from the system are higher severity, not lower.
How to render (do this before any verdict)
Prefer what already exists: if screenshots covers a screen, do not relaunch
the app for it. When you must launch it yourself, follow the same protocol
smoke-test uses — it is the same hazard.
- Discover how to run it.
registry/appfirst; else the project's manifest (package.jsonscripts,Makefile,README). Genuinely unguessable → every render-dependent check isuntested: cannot launch. Do not invent a server. - Launch in the background, capture logs to
.orchestrate/verify/design-review-server.log. Record the PID. Pick a free port if configurable, to avoid colliding with anything already running. - Wait for readiness, bounded — poll the health endpoint / port / ready
line for up to ~60s. Not ready → the checks are
failed: app did not start, attach the server log, skip to cleanup. - Render every screen and state in the spec (loading, empty, error too), in
every mode under the system's
theme.modes, with the best driver available:- Browser automation (a Playwright/Chrome MCP tool, if available in this session) — the only driver that can reach computed style, keyboard focus, a media-query override, or a viewport change.
- Handed-in screenshots — enough for layout, hierarchy, contrast, and the greyscale check; not enough for focus, computed font, or media queries.
- No driver at all — state it once, mark the dependent checks
untested, and still deliver Verdict 1 and every judgment call the spec supports.
- Capture evidence per screen to
.orchestrate/verify/design-review-<screen>-<mode>.png(or.log). - ALWAYS clean up — kill only the processes you started, and remove temp state you created. Cleanup runs even when checks fail.
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.
- 7d ago Changed · +5 lines 2eb313fe9277
- 11d ago First seen · 230 lines · 35 tokens per session scan A 29ac12418acd
design-review is a skill published in the GitHub repository dorayo/orchestrix-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 2,984 once invoked, about $0.0002 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
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.