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/smicolon/ai-kit/review-uigit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/review-ui)<a href="https://agentmods.dev/commands/smicolon/ai-kit/review-ui"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/review-ui.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 | $0.00037 | $0.01072 |
| Opus 5 | $0.00018 | $0.00536 |
| Sonnet 5 | $0.00007 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
review-ui 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 3d 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.
This is a copy
86% identical to act — 95 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing the current branch for UI/UX and visual polish ONLY. Ignore code architecture and accessibility unless a visual issue stems from them directly.
Step 0 — Interpret the scope
User argument: $ARGUMENTS
Classify $ARGUMENTS into one of four modes. The first two lines of your output MUST be:
Mode: <whole-branch | path: <p> | feature: <name> | base: <branch>>
Reviewed N files in scope. Found X P0, Y P1, Z P2 findings.
- Mode A — Whole branch (empty): Review everything changed vs
main. - Mode B — Path scope (contains
/or a known extension like.tsx/.ts/.css, or matchesgit ls-files $ARGUMENTS): Review only changes inside that path. - Mode C — Feature scope (single bareword like
auth,preview,env-setup): Find files related to that feature viagit ls-files | grep -i <feature>andglob/grep, intersect with the branch diff. Review only those files. If nothing matches, stop and ask the user to clarify. - Mode D — Base branch (matches a real branch via
git branch -a): Review current branch vs that base instead ofmain.
If the argument is ambiguous, prefer the branch interpretation if git branch -a confirms it exists.
Step 1 — Scope the diff
Based on the mode:
- A:
git diff main...HEAD --stat - B:
git diff main...HEAD --stat -- <path> - C: Compute the file list from the feature match, diff each relevant file.
- D:
git diff <base>...HEAD --stat
List modified UI files (components, styles, pages, stories). Skip unchanged files entirely.
Step 2 — Inspect each changed file
For every changed component/style file in scope:
- Read the file in full.
- If a parent or sibling component is needed for context, read it but do not comment on it.
- Evaluate against:
- Visual hierarchy — is the most important element the most prominent?
- Spacing rhythm — consistent Tailwind spacing scale (or project's design tokens), no magic pixel values?
- Typography — consistent font sizes, weights, line-heights?
- Color usage — design tokens vs arbitrary hex? Dark-mode parity if applicable?
- Interactive states — hover, focus, active, disabled, loading, empty, error all handled?
- Motion — transitions feel purposeful? Respects
prefers-reduced-motion? - Iconography — consistent stroke/weight, aligned with text baseline?
- Density — right level of cramped/airy for the context?
- Edge cases — long text, zero-state, large numbers, RTL if relevant?
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.
- 3d ago First seen · 88 lines · 37 tokens per session scan A b1df78b8bbd8
review-ui is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 1,072 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to act, differing in 95 lines, and is treated as a copy.
Other commands, from other repositories
designer
UI/UX design with Memory coordination for consistent experiences.
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
extract
Pull repeated patterns into reusable components and design tokens.
improve-ui-ux
Audit and improve an existing interface through one evidence-backed, design-system-aware implementation and browser-verification pass.