agent-browser

agent-browser is a skill for Claude Code, Codex from gvkhosla/compound-engineering-pi. It costs 108 tokens per session (5,899 once invoked), scanned A, a copy of agent-browser, MIT.

A command-line browser automation tool that lets an agent open websites, inspect pages, interact with controls, and capture results.

In plain words
What is it for?
It helps navigate sites, fill forms, click buttons, take screenshots, extract information, and test web applications.
Why use it?
It provides a repeatable way to perform website tasks without manually operating the browser.

Skill for Claude CodeCodex

Part of the compound-engineering plugin — 41 skills, 1 MCP server shipped together

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/gvkhosla/compound-engineering-pi/agent-browser
Any agent
npx skills add gvkhosla/compound-engineering-pi --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/gvkhosla/compound-engineering-pi

Made for: Claude Code, Codex.

Or install compound-engineering, the plugin that ships this one along with the rest of its 41 skills, 1 MCP server.

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 agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/agent-browser.svg)](https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/agent-browser"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/agent-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% copy Near-identical to another mod 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 $0.00108 $0.05899
Opus 5 $0.00054 $0.02950
Sonnet 5 $0.00022 $0.01180
Haiku 4.5 $0.00011 $0.00590

Measured 5d ago against content hash 25aacfdbee52, 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (templates/authenticated-session.sh, templates/capture-workflow.sh, templates/form-automation.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

83% identical to agent-browser — 125 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/compound-engineering/skills/agent-browser/SKILL.md · 687 lines

How it starts

The opening of the file, as written. The whole thing — 687 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Run agent-browser upgrade to update to the latest version.

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).

Handling Authentication

When automating a site that requires login, choose the approach that fits:

Read the full file on GitHub · 687 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. 5d ago First seen · 687 lines · 108 tokens per session scan A 25aacfdbee52

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository gvkhosla/compound-engineering-pi (51 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 5,899 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to agent-browser, differing in 125 lines, and is treated as a copy.

Related

Other skills, from other repositories

webapp-testing

Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.

Hmbown/CodeWhale · 32 tokens

unix_computer_use

Local and remote desktop observation/input tools with coordinate normalization (local macOS/Linux by default; optional OSWorld HTTP and SSH Mac backends).

razzant/ouroboros · 33 tokens

fabric-exec

Troubleshooting and advanced API reference for fabricexec TypeScript programs, dynamic providers, agents, and schema recovery. Routine pi. coding calls are documented by ambient guidance; load this skill only after an argument-shape error or when an advanced surface needs exact contracts.

monotykamary/pi-fabric · 61 tokens

fabric-fusion

Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Act mode runs 1–4 read-only references, then one actor reconciles and executes. Use when the cost of being wrong justifies…

monotykamary/pi-fabric · 74 tokens

fabric-rlm

Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.

monotykamary/pi-fabric · 44 tokens

fabric-schema

Uses Fabric's typed Schema evidence loop and, when enabled, its bounded local-file transaction channel. Use when surprise must void a plan and mutation claims need explicit postconditions.

monotykamary/pi-fabric · 37 tokens