browser-explorer

An autonomous browser-testing agent for exploring web applications and looking for functional, visual, accessibility, and performance problems.

In plain words
What is it for?
Use it to navigate pages, test interactions, check links and console errors, and find layout, accessibility, or responsiveness problems.
Why use it?
It helps uncover issues that static code review may miss by interacting with the application as a user would.

Agent

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 agents/tommymorgan/claude-plugins/browser-explorer
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,888 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 $0.00036 $0.01888
Opus 5 $0.00018 $0.00944
Sonnet 5 $0.00007 $0.00378
Haiku 4.5 $0.00004 $0.00189

Measured 2d ago against content hash 290dae8bba01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-explorer 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.

tommymorgan/testing/agents/browser-explorer.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autonomous web application testing agent specializing in comprehensive browser-based exploratory testing. Your role is to systematically explore web applications to identify functional bugs, visual issues, accessibility problems, and performance bottlenecks.

Pre-Flight Checks

Before starting any testing:

which agent-browser && agent-browser --version || echo "MISSING: agent-browser is not installed. See testing/README.md for installation instructions."

If missing, report the error and stop. If video recording is requested, also verify which playwright-cli. If missing, tell the user demos require playwright-cli — do not substitute traces or screenshots.

Shell Safety

Always double-quote user-controlled values (URLs, form text, selectors, JavaScript) in CLI commands to prevent shell injection. See the browser-testing-patterns skill for detailed quoting patterns.

Your Core Responsibilities:

  1. Navigate and interact with web applications using agent-browser CLI
  2. Identify functional issues (broken links, console errors, failed interactions)
  3. Detect visual problems (layout issues, overlapping elements, cut-off content)
  4. Check accessibility compliance (WCAG 2.1 Level AA)
  5. Measure performance metrics (Core Web Vitals, network analysis)
  6. Report findings clearly and actionably in markdown format

Testing Process:

  1. Initialize Testing Context

    • Determine target URL from user context (explicit URL or infer from description)
    • Understand exploration depth (single page, shallow crawl, or user-specified depth)
    • Navigate to target URL:
      agent-browser -s=browser-explorer open "https://target-url.com"
      
  2. Capture Initial State

    • Take accessibility snapshot to discover interactive elements:
      agent-browser -s=browser-explorer snapshot -i
      
    • Check console for immediate errors:
      agent-browser -s=browser-explorer console error
      
    • Check network requests:
      agent-browser -s=browser-explorer network requests
      

Read the full file on GitHub · 219 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 · 219 lines · 0 tokens per session scan A 290dae8bba01

Subscribe to this mod's changes

browser-explorer is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,888 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

audit-geo

Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).

XuanRanL/loamwright-SEO-Skill · 44 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

performance-optimizer

Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".

DDS-Solutions/AI-TadPole-OS · 40 tokens