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 plugins/browser-use/browser-harness/marketplace/plugin marketplace add browser-use/browser-harnessgit clone --depth 1 https://github.com/browser-use/browser-harnessGrade A, and why
browser-harness 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 yesterday.
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.
What it actually says
{
"name": "browser-harness",
"description": "Install browser-harness directly from this repo.",
"owner": {
"name": "Browser Use",
"url": "https://browser-use.com"
},
"plugins": [
{
"name": "browser-harness",
"description": "Direct CDP browser control for agents: coordinate clicks, screenshots, persistent Python session, local Chrome or Browser Use cloud. Ships skills only; the `browser-harness` CLI is a one-time install prerequisite.",
"category": "automation",
"source": ".",
"homepage": "https://github.com/browser-use/browser-harness",
"keywords": [
"browser",
"automation",
"cdp",
"chrome",
"scraping",
"screenshot"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- yesterday First seen · 26 lines scan A 418c3475bae7
browser-harness is a plugin published in the GitHub repository browser-use/browser-harness (17,240 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
webcmd
Turn websites, browser sessions, desktop apps, and local tools into deterministic CLI surfaces for humans and AI agents.
webcmd
Turn websites, browser sessions, desktop apps, and local tools into deterministic CLI surfaces for humans and AI agents.
bxc
Complete cross-platform Claude Code plugin for the bxc stack: Bun runtime + Rust FFI (DOM, lolhtml, X clients, algorithms), native keyless @aphrody/x X/Twitter client, keyless @aphrody/xai Grok client with deep native X tool calling, bxc-native-mcp server, monorepo scraper packages, stealth crawling, autopilot loops.
tandem
A shared Chrome browser (human + Claude, CDP + Playwright MCP) that learns how each site is navigated: the human drives with the mouse and clears captchas/logins, Claude operates over CDP, and tandem:map persists per-site navigation memory (durable locators, drift, auto-injection).
quimera-ai
Claude Code plugins by bgmacris. Currently: tandem — a real-time shared Chrome (human + Claude, CDP + Playwright MCP) with per-site navigation memory.
rawtrace
Plugin marketplace listing 1 plugin: rawtrace-mcp.