QianYuan.AIAgenticFramework: Skill for Claude Code

.agents/skills/agent-browser-automation/SKILL.md

agent-browser-automation is a skill for Claude Code, Codex from zhouguoqing/QianYuan.AIAgenticFramework. It costs 22 tokens per session (3,103 once invoked), scanned A, original, Apache-2.0.

A skill for controlling a web browser from the command line without displaying a browser window. It uses Chrome's developer connection to navigate pages, interact with elements, inspect accessibility information, take screenshots, and monitor network activity.

In plain words
What is it for?
Use it to open websites, click controls, fill forms, capture accessibility snapshots or screenshots, and inspect browser network activity.
Why use it?
It lets coding agents perform and check browser tasks without requiring a Node.js or Playwright setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is zhouguoqing/QianYuan.AIAgenticFramework's own configuration. It tells Claude Code and Codex how to work on QianYuan.AIAgenticFramework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything QianYuan.AIAgenticFramework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zhouguoqing/QianYuan.AIAgenticFramework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zhouguoqing/QianYuan.AIAgenticFramework/main/.agents/skills/agent-browser-automation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zhouguoqing/QianYuan.AIAgenticFramework

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-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation/github.svg)](https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation)
Your own site
<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation/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-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/agent-browser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,103 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 97
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 $0.00022 $0.03103
Opus 5 $0.00011 $0.01551
Sonnet 5 $0.00004 $0.00621
Haiku 4.5 $0.00002 $0.00310

Measured 11d ago against content hash cd287bd0fc49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-browser-automation 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 11d 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.

.agents/skills/agent-browser-automation/SKILL.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-browser

Skill by ara.so — Daily 2026 Skills collection.

agent-browser is a headless browser automation CLI built in Rust, designed for AI agents. It wraps Chrome via the Chrome DevTools Protocol (CDP) and exposes a fast, ergonomic command-line interface for navigation, interaction, accessibility snapshots, screenshots, network interception, and more — with no Node.js or Playwright runtime required.

Installation

Recommended (npm global)

npm install -g agent-browser
agent-browser install  # Download Chrome for Testing (first time only)

macOS (Homebrew)

brew install agent-browser
agent-browser install

Rust / Cargo

cargo install agent-browser
agent-browser install

Local project dependency

npm install agent-browser
# Add to package.json scripts or invoke via npx

Linux (with system dependencies)

agent-browser install --with-deps

Quick Start

agent-browser open https://example.com
agent-browser snapshot                        # Accessibility tree with @refs (best for AI)
agent-browser click @e2                       # Click by ref from snapshot
agent-browser fill @e3 "[email protected]"   # Fill by ref
agent-browser get text @e1                    # Get text content
agent-browser screenshot page.png
agent-browser close

Core Commands

Navigation

agent-browser open <url>           # Navigate (aliases: goto, navigate)
agent-browser get url              # Get current URL
agent-browser get title            # Get page title
agent-browser close                # Close browser (aliases: quit, exit)

Accessibility Snapshot (recommended for AI agents)

agent-browser snapshot             # Returns accessibility tree with @ref IDs
agent-browser snapshot -i          # Interactive / compact mode

Snapshot output includes @eN refs you can use directly:

@e1 [button] "Submit"
@e2 [textbox] "Email" value=""
@e3 [link] "Sign in"

Read the full file on GitHub · 438 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. 11d ago First seen · 438 lines · 22 tokens per session scan A cd287bd0fc49

Subscribe to this mod's changes

agent-browser-automation is a skill published in the GitHub repository zhouguoqing/QianYuan.AIAgenticFramework (36 stars, last pushed 25d ago), licensed Apache-2.0. It adds 22 tokens to every session and 3,103 once invoked, about $0.0001 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.