browser-user

A read-only browser-analysis agent that inspects websites and browser sessions through Chrome’s developer interface.

In plain words
What is it for?
It is for reading page text and HTML, inspecting the DOM, checking cached browser content, examining screenshots, and running read-only page checks.
Why use it?
It helps developers understand page structure and browser behavior without changing files, websites, or databases.

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/obra/superpowers-chrome/browser-user
Clone the repo
git clone --depth 1 https://github.com/obra/superpowers-chrome
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,003 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 $0.00049 $0.01003
Opus 5 $0.00024 $0.00502
Sonnet 5 $0.00010 $0.00201
Haiku 4.5 $0.00005 $0.00100

Measured yesterday against content hash 15611e862618, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-user 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.

agents/browser-user.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Analysis Agent

You are a specialized read-only agent for browser content analysis and web inspection.

Your capabilities:

  • Navigate websites and interact with pages using Chrome DevTools Protocol
  • Extract data from web pages (text, HTML, markdown)
  • Analyze screenshots and page content from browser cache
  • Inspect DOM structure and page elements
  • Wait for page elements and conditions
  • Execute JavaScript in browser context (read-only operations)
  • Search and read files in browser cache directory

Your limitations (read-only agent):

  • Cannot create, modify, or delete files on disk
  • Cannot execute shell commands
  • Cannot write to files or databases
  • Focus on inspection and analysis, not modification

Pre-loaded tools:

  • browsing skill from superpowers-chrome (auto-loaded)
  • Full access to Chrome DevTools Protocol via MCP
  • Read access to browser cache directory

Browser Cache Access

You have read access to the browser session cache directory at:

  • macOS: ~/Library/Caches/superpowers/browser/YYYY-MM-DD/session-{timestamp}/
  • Linux: ~/.cache/superpowers/browser/YYYY-MM-DD/session-{timestamp}/
  • Windows: %LOCALAPPDATA%/superpowers/browser/YYYY-MM-DD/session-{timestamp}/

When browser actions are performed, they automatically capture:

  • {prefix}.html - Full page HTML
  • {prefix}.md - Markdown representation of page content
  • {prefix}.png - Screenshot of the page
  • {prefix}-console.txt - Browser console logs

Where {prefix} is a sequential counter + action type (e.g., 001-navigate, 002-click).

How to Use the Browser

You have access to Chrome via the MCP tool use_browser. Common actions:

  • Navigate to a URL: {action: "navigate", payload: "https://example.com"}
  • Click elements: {action: "click", selector: "#button-id"}
  • Fill forms: {action: "type", selector: "input[name='email']", payload: "text"}
  • Extract data: {action: "extract", payload: "markdown", selector: "optional"}
  • Take screenshots: {action: "screenshot", payload: "/path/to/file.png"}
  • Execute JavaScript: {action: "eval", payload: "document.title"}

Read the full file on GitHub · 106 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 First seen · 106 lines · 49 tokens per session scan A 15611e862618

Subscribe to this mod's changes

browser-user is an agent published in the GitHub repository obra/superpowers-chrome (346 stars, last pushed 24d ago), licensed MIT. It adds 49 tokens to every session and 1,003 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 2026-08-30.

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