browser-testing

A browser-based testing guide for checking real user journeys in web applications. It covers visible behavior, loading and network states, keyboard access, responsive layouts, accessibility, and screenshots.

In plain words
What is it for?
Use it for browser bugs, end-to-end tests, responsive checks, accessibility checks, and screenshot comparisons.
Why use it?
It catches problems that a source-code review may miss, such as broken interactions, inaccessible controls, or narrow-screen layout failures. It also encourages stable tests that do not depend on arbitrary waiting.

Skill for Claude CodeCodex

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 skills/thiientv/godmode/browser-testing
Any agent
npx skills add thiientv/godmode --skill browser-testing
Clone the repo
git clone --depth 1 https://github.com/thiientv/godmode

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 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 $0.00068 $0.00378
Opus 5 $0.00034 $0.00189
Sonnet 5 $0.00014 $0.00076
Haiku 4.5 $0.00007 $0.00038

Measured 2d ago against content hash da8dfcaf3962, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-testing 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.

skills/browser-testing/SKILL.md · 44 lines

What it actually says

Browser Testing

Exercise the user boundary with deterministic data and meaningful assertions.

Build the test

  1. Identify the route, user role, starting state, and supported viewport.
  2. Wait on semantic readiness—role, label, URL, response, or visible state—not arbitrary sleeps.
  3. Assert the user outcome, important error path, and relevant network/API behavior. Prefer accessible locators over CSS implementation details.
  4. Cover keyboard flow and at least the narrowest supported viewport for responsive work.
  5. Freeze clocks, animations, random IDs, remote data, and fonts only when the test requires stable visual evidence; do not hide real regressions.
  6. Capture screenshots at stable component/page boundaries and review diffs before updating baselines.

Use browser-checklist.md for Playwright, DevTools, and non-Playwright equivalents. Use frontend-design for design decisions and ui-ux-review for an independent visual pass.

Safety and flake control

Use test accounts and fixtures. Do not send destructive actions to production. Record browser, viewport, locale, timezone, and feature flags. Investigate flakes instead of increasing timeouts until they disappear.

Completion condition

The browser test proves the requested user behavior at the real boundary, is repeatable, covers the relevant state/viewport, and reports visual or environment limits.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 44 lines · 68 tokens per session scan A da8dfcaf3962

Subscribe to this mod's changes

browser-testing is a skill published in the GitHub repository thiientv/godmode (93 stars, last pushed 7d ago), licensed MIT. It adds 68 tokens to every session and 378 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 2026-08-30.