Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add TaewoooPark/UIForge/plugin install uiforgeWrote 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/commands/taewooopark/uiforge/critique)<a href="https://agentmods.dev/commands/taewooopark/uiforge/critique"><img src="https://agentmods.dev/badge/commands/taewooopark/uiforge/critique.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01397 |
| Opus 5 | $0.00014 | $0.00698 |
| Sonnet 5 | $0.00006 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
critique scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run UIForge's critique on the current UI ($ARGUMENTS if it names a view/path,
otherwise the view you just built). Follow the uiforge:design-director skill's
critique.md. Judge it coldly, as if someone else built it — self-graders skew
positive.
1. See it (never verify visually from code alone)
If a browser is available — the webapp-testing skill or a Playwright MCP — render the running app and screenshot it:
- Start/confirm the dev server; open the view at a desktop width (~1440px).
- Screenshot it twice: normally, and with
prefers-reduced-motion: reduceemulated. - Critique the images. Confirm the static frame is already excellent and that only the one intended element moves.
If no browser is available, say so, and critique the code + rendered structure instead — but do not claim visual verification.
2. Score the rubric
Walk the critique.md checklist across every axis — direction & intent,
typography, color, space & surface, motion, states & copy, accessibility. Each is
pass/fail; a "yes, but…" is a fail. List every fail with the fix.
3. Run the Gate — two tiers (this is the real check)
Tier A — source (grep, always). Exits non-zero on slop + token violations, so it's a hard gate, not a vibe:
node ${CLAUDE_PLUGIN_ROOT}/tools/uiforge-lint.mjs <project-dir> --strict
Every BLOCKER must be fixed (default font like Inter/system-ui, AI purple/indigo, gradient headline, emoji-as-UI, hype copy, motion without a reduced-motion path). Resolve or explicitly justify each warning (raw hex, arbitrary values, off-grid spacing, maxed radius+shadow, gradient overuse, slate/zinc defaults, infinite loops, missing tokens). Re-run until it exits 0.
Tier B — the render (deep, whenever a browser is available). Grep can't see contrast, accent coverage, spacing rhythm, or layout patterns — those live only in the rendered result. Point it at the running view from step 1 (the dev-server URL or the built file):
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.
- 6d ago First seen · 113 lines · 28 tokens per session scan A fef34aab2cc5
critique is a command published in the GitHub repository TaewoooPark/UIForge (7 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,397 once invoked, about $0.0001 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 commands, from other repositories
cloudflare-workers:optimize
Analyze and optimize Cloudflare Workers performance. Checks bundle size, caching, memory usage, and provides actionable recommendations.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
bun:migrate
Migrate existing Node.js/npm projects to Bun.
ux-onboarding
Get familiar with a project's UX/design choices and patterns — a guided, part-by-part walkthrough that sends you to read the real code, checks your understanding with questions, and has you reimplement a small recent change.
ux-help
Explain the ux-design plugin — everything it offers, or a specific skill, command, agent, or tool if you name one.