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.
npx agentmods add skills/sshh12/claude-plugins/brwnpx skills add sshh12/claude-plugins --skill brwgit clone --depth 1 https://github.com/sshh12/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/sshh12/claude-plugins/brw)<a href="https://agentmods.dev/skills/sshh12/claude-plugins/brw"><img src="https://agentmods.dev/badge/skills/sshh12/claude-plugins/brw.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00068 | $0.04327 |
| Opus 5 | $0.00034 | $0.02164 |
| Sonnet 5 | $0.00014 | $0.00865 |
| Haiku 4.5 | $0.00007 | $0.00433 |
Grade A, and why
brw scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brw — Browser Automation
Setup
Step 1 — one-time bootstrap (the only command that uses a node path):
node "${SKILL_DIR}/scripts/brw.js" install
This symlinks brw into ~/.local/bin. If ~/.local/bin is not yet on your PATH, the command prints a nextSteps block containing an exportLine — append that exportLine to your shell profile (the printed profile path), then restart the session so brw resolves.
Step 2 — HARD ASSERT before any brw use (checks both that brw is on PATH and that it is this exact build — an older/shadowing brw earlier on PATH would silently run stale code):
[ "$(brw --version 2>/dev/null)" = "$(node "${SKILL_DIR}/scripts/brw.js" --version 2>/dev/null)" ] && echo BRW_OK || echo BRW_STALE
If this prints BRW_STALE (bare brw is missing, or an older/different brw is winning on PATH), run node "${SKILL_DIR}/scripts/brw.js" install and apply its nextSteps (it reports shadowedBy / onPathVersion and how to fix), restart the session, then re-run this check. DO NOT proceed using node or absolute paths for real work — once BRW_OK, every command MUST be the bare brw ....
Prerequisites: Node.js 18+, a Chromium-based browser (Chrome, Chromium, Edge, or Brave).
Proxy Lifecycle
The proxy is a per-user daemon listening on a private Unix domain socket (mode 0600) at ~/.config/brw/proxy.sock — there is no TCP port. It starts automatically on first command and stays running for 4 hours of idle time (configurable via BRW_IDLE_TIMEOUT). You do not need to restart it between commands. Intercept rules, console captures, and network captures all persist within a session. Chrome is driven over --remote-debugging-pipe (no debug port is opened).
brw server status # Check if proxy is running
brw server start # Manually start (usually not needed)
brw server start --clean # Kill all debug-mode browsers, then start fresh
brw server stop # Stop proxy and Chrome
brw server restart # Relaunch the proxy and Chrome
brw server clean # Kill all debug-mode browsers and clean up state
What ships with it
7 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.
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.
- 4d ago First seen · 374 lines · 68 tokens per session scan A fa7a062f9981
brw is a skill published in the GitHub repository sshh12/claude-plugins (22 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 4,327 once invoked, about $0.0003 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.
Other skills, from other repositories
obo
Control the user's real Chrome browser with their logged-in sessions, cookies, and extensions. Triggers include "open a website", "click a button", "fill a form", "take a screenshot", "check my email", "browse as me", or any task requiring the user's authenticated browser.
firecrawl-mcp
Auto-generated skill for firecrawl-mcp tools via OneKey Gateway.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.