use-dev-browser

use-dev-browser is a command for Claude Code from yechao-zhang/red-team-agent-skills. It costs 12 tokens per session (298 once invoked), scanned A, original, MIT.

A rule set for using a particular browser-automation tool for website tasks. Browser automation means controlling a website through scripted actions such as opening pages and clicking buttons.

In plain words
What is it for?
Use it when browsing, testing, visiting, or automating websites where persistent browser sessions are preferred.
Why use it?
It prevents the wrong browser tool from being used and tells the agent to stop if the preferred tool is unavailable.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Good fit Use it when browsing, testing, visiting, or automating websites where persistent browser sessions are preferred.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yechao-zhang/red-team-agent-skills/use-dev-browser
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.

Clone the repo
git clone --depth 1 https://github.com/yechao-zhang/red-team-agent-skills

Made for: Claude Code.

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 use-dev-browser

README.md
[![agentmods](https://agentmods.dev/badge/commands/yechao-zhang/red-team-agent-skills/use-dev-browser/github.svg)](https://agentmods.dev/commands/yechao-zhang/red-team-agent-skills/use-dev-browser)
Your own site
<a href="https://agentmods.dev/commands/yechao-zhang/red-team-agent-skills/use-dev-browser"><img src="https://agentmods.dev/badge/commands/yechao-zhang/red-team-agent-skills/use-dev-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 use-dev-browser

Your own site · 80×15
<a href="https://agentmods.dev/commands/yechao-zhang/red-team-agent-skills/use-dev-browser"><img src="https://agentmods.dev/badge/commands/yechao-zhang/red-team-agent-skills/use-dev-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 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.
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 $0.00012 $0.00298
Opus 5 $0.00006 $0.00149
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 10d ago against content hash 3940826da8c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

use-dev-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 10d 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.

.claude/commands/use-dev-browser.md · 28 lines

What it actually says

Context

The user explicitly prefers the dev-browser-skill (persistent sessions, stealth) over the generic plugin:playwright (stateless, detectable).

Your Task

When the user asks to "browse", "visit", "test", or "automate" a website, you must:

  1. Verify that dev-browser-skill is being used, NOT playwright.
  2. Guide the agent to use the correct tool if it attempts to use the wrong one.

Guardrails

  • NEVER use plugin:playwright or playwright-skill unless explicitly requested.
  • ALWAYS use dev-browser for web interaction tasks.
  • If dev-browser is not installed, prompt the user to install it (refer to CLAUDE.md).

Steps

  1. If a web task is requested, check available tools.
  2. Select dev-browser toolset (e.g., dev_browser_navigate, dev_browser_click).
  3. If only playwright is available, stop and inform the user: "I see you want to browse, but only Playwright is available. Please install dev-browser as per your preference."

Generated by /reflect-skills from repeated user corrections

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. 10d ago First seen · 28 lines · 12 tokens per session scan A 3940826da8c3

Subscribe to this mod's changes

use-dev-browser is a command published in the GitHub repository yechao-zhang/red-team-agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 298 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 2026-08-31.