visual-review

A verification process for web interfaces that runs the app, checks accessibility, captures screenshots at phone, tablet, and desktop widths, and compares the result with a design rubric. Accessibility means making an interface usable by people with different abilities.

In plain words
What is it for?
Use it to run automated UI checks, capture breakpoint screenshots, score them against design requirements, classify findings, and iterate on fixes.
Why use it?
It checks the rendered interface rather than trusting generated code and helps find visual, responsive, and accessibility problems before release.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/gosha70/code-copilot-team/visual-review
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Cursor.

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01106
Opus 5 $0.00028 $0.00553
Sonnet 5 $0.00011 $0.00221
Haiku 4.5 $0.00006 $0.00111

Measured 2d ago against content hash 3580862fe35f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-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 2d 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.

adapters/cursor/.cursor/rules/visual-review.mdc · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Review Loop Protocol

Invoke after UI is built against the design-system bundle. Generation alone can't be trusted — this loop verifies the rendered result against the committed DESIGN.md and fails the build until the bar is met.

The loop

build → boot dev server → rubric pre-filter (cheap, deterministic)
      → axe-core a11y gate (fail-fast)
      → Playwright screenshot @ 375 / 768 / 1440
      → CRITIC scores screenshots vs DESIGN.md rubric
      → triage [Blocker/High/Medium/Nitpick] → write critique-feedback.json
      → coding agent applies fixes → re-run → check exit criteria

Deterministic harness + pluggable critic. The harness/ runner does the identical-for-every-copilot parts (boot, screenshot, axe, rubric pre-filter, emit artifacts). The critic (aesthetic judgment) is either:

  • Agent critic (Claude Code): the visual-reviewer agent reads the PNGs directly (a picture is worth 1000 tokens) and scores them.
  • Runner critic (any other copilot): the runner calls a vision-LLM (provider, model, key from env) and writes critique-feedback.json.

Same rubric, same gates, same exit criteria — only the critic swaps.

Running it

From the project root: npm run copilot:review (wraps harness/). It:

  1. runs the a11y + rubric gates; on failure writes tmp/ui-review/critique-feedback.json and exits non-zero;
  2. captures screenshots at the three breakpoints;
  3. runs the critic;
  4. exits 0 only when all exit criteria pass (vision critic), or after emitting artifacts for the agent critic to judge.

The coding agent reads tmp/ui-review/critique-feedback.json ({passed, critiqueSummary, actionableFixes[]}), applies the fixes, and re-runs. Never hand-wave a failing gate — fix the UI.

The critic rubric (score each; source of truth is DESIGN.md)

Phased, adapted from published design-review agents (OneRedOak, Anthropic frontend-design, shiplightai):

  1. Typography — modular scale, real hierarchy, committed pairing (no default fonts).
  2. Spacing & layout — 4/8pt rhythm, internal ≤ external spacing, deliberate layout grammar (no lone centered column, no cardocalypse).
  3. Color & theme — semantic-token discipline, dominant + sharp accent (not evenly distributed), light/dark parity, no banned gradients.
  4. Hierarchy — one primary CTA per screen; attention guided by size/weight/space.
  5. States — empty/loading/error/success/focus present for every data component.
  6. Anti-slop flags — any Step-3 tell from design-system present ⇒ automatic fail.
  7. Domain fit — does it match the archetype/density locked in DESIGN.md.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 2d ago First seen · 90 lines · 57 tokens per session scan A 3580862fe35f

Subscribe to this mod's changes

visual-review is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,106 once invoked, about $0.0003 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.