agent-browser

A command-line tool that lets an AI agent control a web browser. It can open pages, use forms and buttons, take screenshots, and read website data.

In plain words
What is it for?
Opening websites, filling in forms, clicking controls, taking screenshots, extracting information, and testing web applications.
Why use it?
It removes the need to describe browser steps manually or switch between the agent and a browser. It also supports repeatable website checks and actions.

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/rtgs2017/nagaagent/agent-browser
Any agent
npx skills add RTGS2017/NagaAgent --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/RTGS2017/NagaAgent

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 4,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00108 $0.04219
Opus 5 $0.00054 $0.02109
Sonnet 5 $0.00022 $0.00844
Haiku 4.5 $0.00011 $0.00422

Measured 3d ago against content hash 2c7dab0e7898, 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.

apiserver/skills_templates/agent-browser/SKILL.md · 501 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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 · 501 lines · 108 tokens per session scan A 2c7dab0e7898

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository RTGS2017/NagaAgent (1,543 stars, last pushed 22d ago), licensed AGPL-3.0. It adds 108 tokens to every session and 4,219 once invoked, about $0.0005 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

cross-validated-search

OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. Use it to verify factual answers with live search results and explicit source handling.

InternLM/WildClawBench · 39 tokens

agent-browser

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection.

InternLM/WildClawBench · 21 tokens

playwright

Use when the task requires capturing or automating a real browser from the terminal.

openai/openai-agents-python · 19 tokens

computer-use

Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…

kirodotdev/KiroCrew · 105 tokens

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

browser-recording

Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…

kirodotdev/KiroCrew · 85 tokens