agent-browser

A command-line browser control guide for opening web pages, inspecting their interactive elements, filling forms, clicking controls, and checking the resulting page.

In plain words
What is it for?
Use it to test sign-in and forms, verify navigation, inspect page changes, or reproduce browser-specific behavior.
Why use it?
It lets a coding agent test a website through a real browser instead of relying only on source code or automated unit tests.

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

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,593 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 $0.00022 $0.01593
Opus 5 $0.00011 $0.00796
Sonnet 5 $0.00004 $0.00319
Haiku 4.5 $0.00002 $0.00159

Measured 2d ago against content hash 11b5b1f23b5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-browser 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.

.agents/skills/agent-browser/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

Core Workflow

Every browser automation follows this pattern:

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
  3. Interact: Use refs to click, fill, select
  4. Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "[email protected]" && agent-browser fill @e2 "password123" && agent-browser click @e3

# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).

Essential Commands

# Navigation
agent-browser open <url>              # Navigate (aliases: goto, navigate)
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs (recommended)
agent-browser snapshot -i -C          # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser click @e1 --new-tab     # Click and open in new tab
agent-browser fill @e2 "text"         # Clear and type text
agent-browser type @e2 "text"         # Type without clearing
agent-browser select @e1 "option"     # Select dropdown option
agent-browser check @e1               # Check checkbox
agent-browser press Enter             # Press key
agent-browser keyboard type "text"    # Type at current focus (no selector)
agent-browser keyboard inserttext "text"  # Insert without key events
agent-browser scroll down 500         # Scroll page
agent-browser scroll down 500 --selector "div.content"  # Scroll within a specific container

# Get information
agent-browser get text @e1            # Get element text
agent-browser get url                 # Get current URL
agent-browser get title               # Get page title

# Wait
agent-browser wait @e1                # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page"    # Wait for URL pattern
agent-browser wait 2000               # Wait milliseconds

# Downloads
agent-browser download @e1 ./file.pdf          # Click element to trigger download
agent-browser wait --download ./output.zip     # Wait for any download to complete
agent-browser --download-path ./downloads open <url>  # Set default download directory

# Capture
agent-browser screenshot              # Screenshot to temp dir
agent-browser screenshot --full       # Full page screenshot
agent-browser screenshot --annotate   # Annotated screenshot with numbered element labels
agent-browser pdf output.pdf          # Save as PDF

# Diff (compare page states)
agent-browser diff snapshot                          # Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt    # Compare current vs saved file
agent-browser diff screenshot --baseline before.png  # Visual pixel diff
agent-browser diff url <url1> <url2>                 # Compare two pages
agent-browser diff url <url1> <url2> --wait-until networkidle  # Custom wait strategy
agent-browser diff url <url1> <url2> --selector "#main"  # Scope to element

Read the full file on GitHub · 199 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 · 199 lines · 22 tokens per session scan A 11b5b1f23b5e

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository slopus/happy (23,553 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 1,593 once invoked, about $0.0001 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 skills, from other repositories

chrome-devtools-axi

Control a Chrome browser session through the chrome-devtools-axi CLI - navigate, snapshot, click, fill forms, run JavaScript, inspect console and network, take screenshots, audit performance. Use whenever a task needs a real browser: opening or testing a web page, clicking through a flow, extracting page content, or…

meshery/meshery · 74 tokens

2-repro-issue

Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at /.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says…

stickerdaniel/linkedin-mcp-server · 75 tokens

console

Navigate and interact with the ThunderID Console UI. Use when exploring the ThunderID admin console, testing UI changes, creating users/applications/roles, or debugging the frontend.

thunder-id/thunderid · 37 tokens

explore-ui

Standalone Phase 2 of SAP UI testing. Opens the target transaction in a real browser (SAP WebGUI) and explores it live to produce tests/ /test-cases/screens.md — the authoritative map of every on-screen control, its accessible name/label as Playwright will see it, and its initial state. This is about how the UI…

marcellourbani/vscode_abap_remote_fs · 112 tokens

sap-testing

Entry point for the SAP UI test-automation environment. Explains project layout, the configured test folder, available tools, phase workflows, and bounded agent delegation. Use when the user asks about SAP UI testing, Playwright for SAP, writing tests for any ABAP report/transaction/process, generating test evidence…

marcellourbani/vscode_abap_remote_fs · 73 tokens

sap-webgui

Authoritative SAP WebGUI behavior and locator guidance for live exploration and Playwright script generation. Covers iframes, accessible names, generated IDs, selection screens, dialogs, ALV grids, toolbars, uploads, themes, and known SapSession helper limitations. Load before explore-ui live exploration and before…

marcellourbani/vscode_abap_remote_fs · 69 tokens