agentmods.dev

browser

browser is a skill for Claude Code, Codex from wecode-ai/Wegent. It costs 32 tokens per session (980 once invoked), scanned A, original, Apache-2.0.

A browser automation skill that completes tasks on real websites by opening pages, interacting with controls, waiting for changes, and extracting results.

In plain words
What is it for?
Use it to navigate websites, fill in forms, click or select items, wait for pages to update, and collect information from them.
Why use it?
It helps an agent carry out multi-step web tasks reliably instead of only describing what a person should click.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 872repo +2 yesterday A scan SkillSpector: pass 32 tokens original Apache-2.0

Good fit Use it to navigate websites, fill in forms, click or select items, wait for pages to update, and collect information from them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wecode-ai/wegent/browser
View source ↗ wecode-ai/Wegent wecode-ai.github.io
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 wecode-ai/Wegent --skill browser
Clone the repo
git clone --depth 1 https://github.com/wecode-ai/Wegent

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 browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/wecode-ai/wegent/browser/github.svg)](https://agentmods.dev/skills/wecode-ai/wegent/browser)
Your own site
<a href="https://agentmods.dev/skills/wecode-ai/wegent/browser"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/browser/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 browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/wecode-ai/wegent/browser"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00032 $0.00980
Opus 5.5 $0.00013 $0.00392
Sonnet 5.5 $0.00006 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 1mo ago against content hash 13323cee9ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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.

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.

backend/init_data/skills/browser/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Control Skill

Goal

Finish the user’s real task reliably.
Prioritize successful completion and correct results over aggressive call minimization.

Operating Rules

  1. Start with the intended action directly (navigate/open/act/evaluate). Do not run status as a pre-check.
  2. Use snapshot only when refs are required for interaction (click/type/select/drag/scrollIntoView).
  3. Prefer evaluate for extraction. Return structured data in one comprehensive call when possible.
  4. Use condition waits by default (loadState/url → selector/text/textGone → fn). Avoid timeMs unless explicitly needed.
  5. Before clicking potentially off-screen elements, run act.scrollIntoView on the ref first.
  6. Keep context stable: once targetId is known, pass it in follow-up calls when supported.
  7. Avoid blind loops: every extra call must have a clear purpose.

Reliability and Recovery

  1. If Ref not found, do not reuse stale refs. Take one fresh snapshot, retry once, then stop if still failing.
  2. For repeated failures with the same cause, stop and explain the blocker clearly instead of retrying endlessly.
  3. Connection recovery is built into the tool. Allow auto-recovery once; if still disconnected, instruct user to install/connect extension.

Screenshot Policy

  1. Default: no screenshot.
  2. Use screenshots only when user asks, or when visual proof is required.
  3. Prefer element screenshots (ref or element) over full-page screenshots.
  4. Use full-page screenshots only for page-level evidence.
  1. Direct action first (navigate/open or immediate act/evaluate).
  2. If interaction needs refs, run snapshot (interactive: true preferred).
  3. Wait for readiness using act.wait with explicit conditions.
  4. Interact (scrollIntoView → click/type/select/drag as needed).
  5. Extract/verify with evaluate (preferred) or snapshot.
  6. Provide screenshot evidence only when necessary.

Connection Handling

Connection recovery is built into the tool. On connection failure, let the tool auto-attach/launch/retry once. If still disconnected, stop and instruct the user to install/connect the extension.

Read the full file on GitHub · 96 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. 1mo ago First seen · 96 lines · 32 tokens per session scan A 13323cee9ddd

Subscribe to this mod's changes

browser is a skill published in the GitHub repository wecode-ai/Wegent (872 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 980 once invoked, about $0.0001 per session on Opus 5.5. 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.

Browser automationClaude Codeagentaichatbotcodexwework
Related

Other skills, from other repositories

ha-browser

Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…

shiwenwen/hope-agent · 140 tokens

web-access

A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.

open-octo/octo-agent · 139 tokens

in-app-browser

A guide for using Proma’s built-in controlled web browser to open, view, search, or operate websites.

proma-ai/Proma · 170 tokens

playwright

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.

netease-youdao/LobsterAI · 45 tokens

agent-browser

A browser-automation guide for controlling web pages and interacting with websites through scripted steps.

KroMiose/nekro-agent · 33 tokens

actionbook

MUST USE AUTOMATICALLY when user sends URLs from x.com, twitter.com, or any site that webfetch fails on. Do NOT ask the user — just load this skill and use it. Browser automation and web scraping with anti-detection stealth mode. Capabilities: (1) Scrape Twitter/X content without login, (2) Extract data from…

longzhi/clawhive · 134 tokens