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 agentmods add commands/taewooopark/uiforge/scoregit clone --depth 1 https://github.com/TaewoooPark/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/score)<a href="https://agentmods.dev/commands/taewooopark/uiforge/score"><img src="https://agentmods.dev/badge/commands/taewooopark/uiforge/score.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 | $0.00043 | $0.00628 |
| Opus 5 | $0.00022 | $0.00314 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
score 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score the UI in $ARGUMENTS (default: the current project) for slop and report a grade. This is UIForge as a reviewer, not a generator.
Local directory / current project
node ${CLAUDE_PLUGIN_ROOT}/tools/uiforge-score.mjs <dir>
It prints a letter grade on one coherent 0–100 scale (a BLOCKER is heavy — a single one caps the grade at C; 0 tells → A+; an empty/non-standard scan → N/A, never a fake A+), plus the top tells. Then summarize: the grade, the blockers (each with the one-line why + a fix), and the two or three highest-leverage changes to raise it.
A pull request
If $ARGUMENTS is a PR number or GitHub URL, check it out and score the change:
gh pr checkout <pr> # or: git fetch origin pull/<pr>/head && git checkout FETCH_HEAD
node ${CLAUDE_PLUGIN_ROOT}/tools/uiforge-score.mjs .
Post the grade + the specific tells as review feedback (optionally
gh pr comment <pr> --body …). Frame each finding as "tell → fix", not a nitpick.
A live URL
You have no source, but you have the render — so use the deep tier. Grade the rendered page on real craft metrics (WCAG contrast per text node, accent surface-area, spacing rhythm, type-scale coherence, AI layout patterns):
node ${CLAUDE_PLUGIN_ROOT}/tools/uiforge-render-audit.mjs <url> --viewport 1440x900
node ${CLAUDE_PLUGIN_ROOT}/tools/uiforge-attention.mjs <url> --viewport 1440x900
The render audit grades the craft; attention predicts the gaze order and flags a
flat hierarchy (add --overlay shot.png to attach the annotated punch list). Then
render + screenshot it (webapp-testing / Playwright) and run the adversarial
slop-detector
on the pixels: the render-audit gives the objective numbers (a 2.9:1 contrast is a
fact), the detector gives the gestalt — "could an adversary prove it's AI." Report
both, with the tells.
Keep it useful and specific: a grade nobody can act on is noise.
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.
- 4d ago First seen · 54 lines · 43 tokens per session scan A 93a49ca5fd76
score is a command published in the GitHub repository TaewoooPark/UIForge (7 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 628 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 commands, from other repositories
ux-audit
Run a combined usability + accessibility audit on a page, component, or screenshot and produce a single scored report.
ux-bootstrap
Scaffold a UX baseline (design tokens, accessible primitives, a11y linting, metrics, and a UX checklist) into the current project, adapted to its stack.
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-review
Quick, scored UX review of a single component or screen — from code, a screenshot, or a live page — via the ux-reviewer agent.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.