agent-browser

agent-browser is a skill for Claude Code, Codex from HiAi-gg/hiai-opencode. It costs 81 tokens per session (1,956 once invoked), scanned C, original, no licence file.

A browser automation tool for coding agents. It can operate web pages and inspect what happens while using them.

In plain words
What is it for?
Use it to navigate sites, fill in forms, click controls, take screenshots, extract page data, test web apps, and investigate browser bugs.
Why use it?
It removes the need to check browser behavior only by reading code, helping agents observe real pages, forms, errors, and test results.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to navigate sites, fill in forms, click controls, take screenshots, extract page data, test web apps, and investigate browser bugs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hiai-gg/hiai-opencode/vision
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.

Any agent
npx skills add HiAi-gg/hiai-opencode --skill vision
Clone the repo
git clone --depth 1 https://github.com/HiAi-gg/hiai-opencode

Made for: Claude Code, Codex.

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/hiai-gg/hiai-opencode/vision/github.svg)](https://agentmods.dev/skills/hiai-gg/hiai-opencode/vision)
Your own site
<a href="https://agentmods.dev/skills/hiai-gg/hiai-opencode/vision"><img src="https://agentmods.dev/badge/skills/hiai-gg/hiai-opencode/vision/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/hiai-gg/hiai-opencode/vision"><img src="https://agentmods.dev/badge/skills/hiai-gg/hiai-opencode/vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00081 $0.01956
Opus 5.5 $0.00032 $0.00782
Sonnet 5.5 $0.00016 $0.00391
Haiku 4.5 $0.00008 $0.00196

Measured 1mo ago against content hash b5b6d7a14156, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

agent-browser scanned grade C with 2 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 1mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://pkg.lightpanda.io/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://pkg.lightpanda.io/install.sh | bash
skills/vision/SKILL.md · 262 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · -19 lines b5b6d7a14156
  2. 2mo ago First seen · 281 lines · 81 tokens per session scan C e42eb3ca356d

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository HiAi-gg/hiai-opencode (18 stars, last pushed 20d ago), with no licence file. It adds 81 tokens to every session and 1,956 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

agent-browser compared with skills from other repositories

agent-browser next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-browserHiAi-gg/hiai-opencodeSkill1820d agononeC81Claude Code, Codex
annotate-mdkonradmichalik/md-annotatorSkill62mo agoMITA28Claude Code
plannotator-inboxbacknotprop/plannotatorSkill9.9kyesterdayApache-2.0A39Claude Code
southwestborski/travel-hacking-toolkitSkill895yesterdayMITA40Claude Code
horizon-browserpeters/horizonSkill720yesterdayMITA20Claude Code
google-flightsborski/travel-hacking-toolkitSkill895yesterdayMITA32Claude Code
vrboborski/travel-hacking-toolkitSkill895yesterdayMITA97Claude Code