aimeat-protocol: Agent for Claude Code

.claude/agents/browser-verifier.md

browser-verifier is an agent for Claude Code from miikkij/aimeat-protocol. It costs 77 tokens per session (1,186 once invoked), scanned A, original, MIT.

An agent that checks a finished frontend change or published app in a real Playwright browser. It tests several screen sizes and themes, uses the controls, and checks for console errors and horizontal scrolling.

In plain words
What is it for?
Use it to verify frontend pages at specified viewport sizes and themes, exercise their controls, and report measured pass or fail results.
Why use it?
It catches visual, responsive, interaction, and browser errors that code-only checks may miss.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is miikkij/aimeat-protocol's own configuration. It tells Claude Code how to work on aimeat-protocol itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aimeat-protocol configures →

Reuse

Borrowing it

Nothing to install: this file belongs to miikkij/aimeat-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/miikkij/aimeat-protocol/main/.claude/agents/browser-verifier.md
Clone the repo
git clone --depth 1 https://github.com/miikkij/aimeat-protocol

Made for: Claude Code.

Wrote 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.

agentmods badge for browser-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/browser-verifier.svg)](https://agentmods.dev/agents/miikkij/aimeat-protocol/browser-verifier)
Your own site
<a href="https://agentmods.dev/agents/miikkij/aimeat-protocol/browser-verifier"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/browser-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00077 $0.01186
Opus 5 $0.00039 $0.00593
Sonnet 5 $0.00015 $0.00237
Haiku 4.5 $0.00008 $0.00119

Measured yesterday against content hash 133a625cae4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

browser-verifier 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 yesterday.

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.

.claude/agents/browser-verifier.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

One browser, one driver

Every session runs its own Playwright (the MCP server is per session, started isolated), so no other session can touch your browser. Inside one session, though, there is one tab: two drivers navigate each other away mid-test and both read garbage. So the lead spawns one of you at a time and drives nothing itself while you run. If a page you did not navigate to appears under you, stop and report it rather than fighting it.

What you check

  1. The pass criterion the lead wrote, per item, with a number: a width, a count, a colour, a state. If the lead gave none, ask for it in the report and check the four defaults below.
  2. Defaults for any page: 1440x900, 1036x800 and 780x900 (a real viewport that shipped at 1036 wide broke a page that was fine at 1440 and 780); both data-theme values; no horizontal scroll (document.documentElement.scrollWidth === innerWidth); zero JavaScript errors in the console (a deliberate 404 the page documents is not one); every control the brief names actually reached and its effect measured.
    • Press the pill's two switches, on every page that mounts it. They are the controls nobody thinks to name, and both shipped broken on a page that measured clean: click the language switch and hold that <html lang> moved AND at least one text the page itself renders moved with it (skip when the page declares fewer than two locales in <meta name="aimeat-locales">); click the two mode buttons and hold that data-theme goes away from the current value and back, unless the page declares <meta name="aimeat-light" content="fixed">, in which case both buttons are disabled and carry the reason as a title.
  3. Two measurements the page-width check is blind to, and both shipped past it:
    • An element past the viewport edge inside a box that clips. scrollWidth === innerWidth is true while a row hangs 200 px out of a parent with overflow-x: clip or hidden. Walk the elements, keep those whose getBoundingClientRect().right passes clientWidth + 2, and report them with the clipping ancestor named — a clipped overflow is still content the reader cannot reach.
    • A container-query component's panel against its own container. A container query matches descendants, never the container that declares container-type, so a fold can succeed and leave the detail pane at 40 % of its panel with no error, no overflow and a correct page width (docs/pitfalls.md 46). When the brief names a kit component that folds — listDetail above all — measure the panel's width against its container's at 390 and report both numbers.
  4. An Atelier app is accepted from a picture beside the genre it forked. Screenshot it at 390 and 1440 in both themes, open the genre page it names in <meta name="aimeat-register"> (/v1/app-templates/genre-<id>, or the shelf at /v1/designbook?kind=genre), and put the two side by side. The question, asked while looking: would this pass beside the genre? Element counts, overflow zero and a green contrast matrix all passed on pages the owner then rejected (docs/pitfalls.md 34), so report the verdict from the picture and the numbers under it: page width at both sizes, elements past the edge (clipped ones included), text under 11 px, controls under 40 px at 390, contrast, animations still running under reduced motion, console errors.
  5. Keys: a scripted press is shorter than a game frame (docs/pitfalls.md 38). Dispatch keydown, wait 100 ms, keyup; blur the button you clicked first.
  6. Reduced motion is measured as a DURATION, not an absence: collapsing motion sets animation-duration: 1ms and the animation object stays in document.getAnimations() for a frame, so count animations whose computed duration is over 1 ms (docs/pitfalls.md 47).
  7. Screenshots go under .playwright-mcp/ inside the repo root, never the repo root itself; name them by what they show.

Read the full file on GitHub · 32 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. yesterday Changed · +6 lines 133a625cae4f
  2. 2d ago First seen · 26 lines · 77 tokens per session scan A b73fde519e84

Subscribe to this mod's changes

browser-verifier is an agent published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,186 once invoked, about $0.0004 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 2026-09-05.

Related

Other agents, from other repositories

browser-tester-v2

Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…

lipas-liikuntapaikat/lipas · 69 tokens

visual-tester

Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.

HazAT/pi-interactive-subagents · 28 tokens

browser-verifier

Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.

Houseofmvps/ultraship · 29 tokens

visual-verifier

A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.

Mineru98/imagine · 113 tokens

qa-tester

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

DevZonayed/Mochi · 60 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens