browserbase-ui-test

browserbase-ui-test is a skill for Claude Code from strikersam/autonomous-ai-agency. It costs 56 tokens per session (857 once invoked), scanned A, original, MIT.

An adversarial UI-testing skill that uses browser automation to look for defects in a web app. It tests normal flows as well as empty inputs, invalid data, rapid actions, network failures, accessibility, mobile layouts, and console errors.

In plain words
What is it for?
Use it before merging interface changes to test login, saving, forms, payments, keyboard access, small screens, and failure cases.
Why use it?
It is designed to expose problems that a simple happy-path check can miss. It can focus on code changed in a Git diff or audit the full deployed app before a merge.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it before merging interface changes to test login, saving, forms, payments, keyboard access, small screens, and failure cases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strikersam/autonomous-ai-agency/browserbase-ui-test
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.

Any agent
npx skills add strikersam/autonomous-ai-agency --skill browserbase-ui-test
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

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 browserbase-ui-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/browserbase-ui-test/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/browserbase-ui-test)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/browserbase-ui-test"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/browserbase-ui-test/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.

agentmods 80×15 button for browserbase-ui-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/browserbase-ui-test"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/browserbase-ui-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00056 $0.00857
Opus 5 $0.00028 $0.00428
Sonnet 5 $0.00011 $0.00171
Haiku 4.5 $0.00006 $0.00086

Measured 8d ago against content hash 3996d9352aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

browserbase-ui-test 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 8d 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.

.claude/skills/browserbase-ui-test/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: browserbase-ui-test — Adversarial UI Testing

Core philosophy

Your job is to try to break things, not confirm they work. If the happy path passes, immediately try edge cases, empty states, rapid interactions, and unexpected inputs.

Three planning rounds (REQUIRED before any browser interaction)

Round 1 — Core flow mapping

List every user flow that exists. For each flow: what does success look like? What does failure look like? Which flows are critical (login, data save, payment)?

Round 2 — Adversarial scenarios

For each flow: what happens with empty input? Invalid format? Very long strings? Clicking submit twice? Going back mid-flow? Network timeout simulation?

Round 3 — Accessibility + mobile

Does each screen work at 375px width? Are form labels connected to inputs? Can keyboard-only users complete every flow? Any console errors?

Execution pattern

export BROWSERBASE_API_KEY="bb_live_..."
export PLATFORM_URL="https://local-llm-server.strikersam.workers.dev"

# --- Flow 1: Unauthenticated access ---
browse open "$PLATFORM_URL" --remote
browse snapshot
# Verify: login page or landing, no sensitive data exposed
browse screenshot   # Evidence

# --- Flow 2: Login ---
browse fill "@eN" "[email protected]"
browse fill "@eN" "wrong-password"
browse click "@eN"    # Submit
browse snapshot       # Verify: error message shown, not logged in
browse screenshot     # Evidence of error state

# --- Flow 3: Correct login ---
browse fill "@eN" "[email protected]"
browse fill "@eN" "correct-password"
browse click "@eN"
browse snapshot       # Verify: dashboard visible
browse screenshot

# --- Flow 4: Core feature test ---
# Navigate to Agents screen
browse click "@eN"
browse snapshot
# Try creating an agent with empty name
browse click "@eN"    # New agent button
browse click "@eN"    # Submit without filling
browse snapshot       # Verify: validation error, not 500

browse stop

Reporting

For each test step, mark:

  • STEP_PASS: <description> — with snapshot/screenshot evidence
  • STEP_FAIL: <description> — with screenshot, reproduction steps, suggested fix

Read the full file on GitHub · 112 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. 8d ago First seen · 112 lines · 56 tokens per session scan A 3996d9352aa0

Subscribe to this mod's changes

browserbase-ui-test is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 857 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 2026-09-03.