agent-browser

A command-line browser controller for opening websites, inspecting pages, entering information, clicking controls, taking screenshots, and extracting content.

In plain words
What is it for?
Automating browser tasks, filling forms, testing web applications, navigating pages, capturing screenshots, and collecting website data.
Why use it?
It lets an agent interact with websites through a real browser instead of only reading page text.

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

Made for: Claude Code, Codex.

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% 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 $0.05393
Opus 5 $0.00054 $0.02697
Sonnet 5 $0.00022 $0.01079
Haiku 4.5 $0.00011 $0.00539

Measured yesterday against content hash b8d5e02bd590, 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 yesterday.

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

89% identical to agent-browser — 71 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.

.agents/skills/agent-browser/SKILL.md · 633 lines

How it starts

The opening of the file, as written. The whole thing — 633 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.

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:

Option 1: Import auth from the user's browser (fastest for one-off tasks)

Read the full file on GitHub · 633 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 · 633 lines · 108 tokens per session scan A b8d5e02bd590

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository ReflexioAI/reflexio (338 stars, last pushed 2d ago), licensed Apache-2.0. It adds 108 tokens to every session and 5,393 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to agent-browser, differing in 71 lines, and is treated as a copy.

Related

Other skills, from other repositories

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

ReflexioAI/claude-smart · 108 tokens

review

Rigorous code review of all uncommitted changes. Analyzes architecture, code quality, security, and engineering best practices. Embeds questions and assumptions inline, then summarizes all proposed changes as a plan for user approval before any edits are made.

ReflexioAI/claude-smart · 52 tokens

fastapi

FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.

ReflexioAI/claude-smart · 57 tokens

commit

Git commit workflow with precommit hook handling, lint/type checking, README updates, and API reference updates. Use when the user wants to commit changes. Handles precommit hooks that modify files (formatting, linting) by re-staging and retrying. Runs ruff lint and pyright type checks on staged Python files, and…

ReflexioAI/claude-smart · 122 tokens

check-and-test

Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does…

ReflexioAI/claude-smart · 97 tokens

update-pr

Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.

ReflexioAI/claude-smart · 71 tokens