Borrowing it
Nothing to install: this file belongs to saadnvd1/agent-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saadnvd1/agent-os/main/.claude/agents/review-frontend.mdgit clone --depth 1 https://github.com/saadnvd1/agent-osWrote 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/agents/saadnvd1/agent-os/review-frontend)<a href="https://agentmods.dev/agents/saadnvd1/agent-os/review-frontend"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-frontend/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/agents/saadnvd1/agent-os/review-frontend"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-frontend.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 | $0.00065 | $0.01144 |
| Opus 5.5 | $0.00026 | $0.00458 |
| Sonnet 5.5 | $0.00013 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
review-frontend 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 22d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend review
AgentOS is used as much from an iPhone over the tailnet as from a desktop, in both themes. Flag high-confidence problems in UI code introduced or modified by this branch: app/ pages and layouts (not app/api/), components/, hooks/, data/, stores/, contexts/, styles/.
Read first: styles/themes.css (the theme tokens, light and dark), lib/query-client.ts, and a neighbouring data/<domain>/queries.ts for how this repo fetches.
Process
- Changed files: use the list in your prompt. If none was given: with a PR number,
gh pr diff <NUMBER> --name-only; otherwisegit diff main...HEAD --name-status -Mplusgit status --short --untracked-files=all. Read new files whole andgit diff main -- <file>for changed ones. - For each changed component, find where it renders (desktop pane, mobile sheet, both) and which API routes its data comes from.
- Check every rule below.
- Report.
Rules
Phone first
- Touch targets under 44px on anything tappable: buttons, icon buttons, list rows, tabs, chips (
h-11/min-h-11/size-11; an icon can stay small inside a 44px hit area). - Layouts that overflow at 390px wide: fixed widths,
whitespace-nowrapon user text (session names, branches, paths) without truncation, tables with no small-screen form, side-by-side panes with no stacked layout. - Hover-only affordances (actions that appear only on
:hover) with no tap equivalent. - Inputs under 16px font on iOS (it zooms the page), and fixed elements that ignore the safe areas and the on-screen keyboard (
env(safe-area-inset-*), the viewport hooks inhooks/useViewportHeight.ts).
Both themes
Colours come from the theme tokens (bg-background, text-muted-foreground, border-border, ...). Flag a hex/rgb()/arbitrary colour or a raw Tailwind palette colour (text-gray-500, bg-zinc-900) in added lines, a dark: override with no light counterpart or the reverse, and text whose contrast fails in one theme (muted on muted, white on a light surface). Terminal themes in lib/terminal-themes.ts are exempt.
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.
- 22d ago First seen · 66 lines · 65 tokens per session scan A d3e1a16bcf3d
review-frontend is an agent published in the GitHub repository saadnvd1/agent-os (11 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,144 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-07.
Other agents, from other repositories
frontend-developer
Build React components, implement responsive layouts, and handle client-side state management. Optimizes frontend performance and ensures accessibility. Use PROACTIVELY when creating UI components or fixing frontend issues.
frontend-specialist
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
reviewer-bugs
A reviewer for correctness problems in frontend code, including React, JavaScript, TypeScript, HTML, and CSS. React is a library for building user interfaces.
Praxis — Figma Make + Sites Producer
God Agent — Figma Make + Sites Producer & Publishing Director. Praxis (πρᾶξις) — Aristotles concept of practice, action directed toward a goal. Praxis is.
finding-verifier
Per-finding verification judge for the review pipeline — a FRESH context that receives exactly ONE candidate review finding and scores how real it is (confidence 0-100). Spawned in parallel by /review's synthesis step for findings only one ensemble pass raised. Utility agent (no author pair, read-only, never edits…
Validate
Runs build, typecheck, lint and test; reports pass or fail with failure details; never fixes.