agent-browser

A command-line browser controller for checking user flows in websites and Electron desktop apps, including navigation, clicks, and form entry.

In plain words
What is it for?
Use it to open pages, inspect available controls, click buttons, fill fields, wait for navigation, and verify flows in a browser or Electron app.
Why use it?
It lets you validate an interaction on the actual interface instead of relying only on source-code inspection or automated tests. It can inspect the page and reuse references to its interactive elements.

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/intelligent-internet/zenith/agent-browser
Any agent
npx skills add Intelligent-Internet/zenith --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/Intelligent-Internet/zenith

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,306 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 $0.00015 $0.06306
Opus 5 $0.00008 $0.03153
Sonnet 5 $0.00003 $0.01261
Haiku 4.5 $0.00002 $0.00631

Measured 3d ago against content hash 30c36dc8436e, 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 3d 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.

zenith/src/zenith_harness/bundled/skills/agent-browser/SKILL.md · 765 lines

How it starts

The opening of the file, as written. The whole thing — 765 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

One-time setup (fresh machines)

If you see an error like "Executable doesn't exist ... chrome-headless-shell", install the bundled Chromium:

agent-browser install

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
  3. Interact using refs from the snapshot
  4. Re-snapshot after navigation or significant DOM changes

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).

Commands

Navigation

agent-browser open <url>      # Navigate to URL (aliases: goto, navigate)
                              # Supports: https://, http://, file://, about:, data://
                              # Auto-prepends https:// if no protocol given
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser (aliases: quit, exit)
agent-browser connect 9222    # Connect to browser via CDP port

Read the full file on GitHub · 765 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. 3d ago First seen · 765 lines · 15 tokens per session scan A 30c36dc8436e

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository Intelligent-Internet/zenith (283 stars, last pushed 26d ago), licensed Apache-2.0. It adds 15 tokens to every session and 6,306 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

browser-qa

Use when validating or debugging a workflow in the embedded browser and you need a reproducible, evidence-first loop.

holaboss-ai/holaOS · 26 tokens

do-discover-paths

Discover happy paths on a target site using BYOB MCP, producing trace JSON for deterministic test generation. Use when asked to discover paths, map site flows, or record browser traces for tests.

tomcounsell/ai · 44 tokens

playwright-skill

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…

Peadarpol/ai-delivery-control · 78 tokens

browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

HKUDS/AutoMemory · 47 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

e2e-deployment-skill

Use this deployment skill to verify shared skills load during Playwright startup.

danny-avila/LibreChat · 22 tokens