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/browser-use/browser-harness/browser_harnessnpx skills add browser-use/browser-harness --skill browser_harnessgit clone --depth 1 https://github.com/browser-use/browser-harnessWrote 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/browser-use/browser-harness/browser_harness)<a href="https://agentmods.dev/skills/browser-use/browser-harness/browser_harness"><img src="https://agentmods.dev/badge/skills/browser-use/browser-harness/browser_harness.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 | $0.00000 | $0.00004 |
| Opus 5 | $0.00000 | $0.00002 |
| Sonnet 5 | $0.00000 | $0.00001 |
| Haiku 4.5 | $0.00000 | $0.00000 |
Grade 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 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- soul-guardian — 100% identical, 2 lines differ
- duckdb — 100% identical, 0 lines differ
- council — 100% identical, 0 lines differ
- deeptutor — 100% identical, 2 lines differ
- investment-analysis — 100% identical, 2 lines differ
- mykg — 100% identical, 0 lines differ
- readydesign-skill — 100% identical, 2 lines differ
- market-sages — 100% identical, 2 lines differ
What it actually says
../../SKILL.md
What ships with it
14 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.
- __init__.py 37 B runs code
- _ipc.py 8.9 KB runs code
- admin.py 51 KB runs code
- auth.py 18 KB runs code
- daemon.py 38 KB runs code
- helpers.py 23 KB runs code
- macos.py 4.1 KB runs code
- paths.py 1.5 KB runs code
- recorder.py 11 KB runs code
- run.py 14 KB runs code
- telemetry.py 8.8 KB runs code
- video_render.py 20 KB runs code
- video-template.html 69 KB
- video.py 29 KB runs code
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 · 1 lines · 0 tokens per session scan A 51e5cba874c5
browser_harness is a skill published in the GitHub repository browser-use/browser-harness (17,240 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4 tokens. 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
browser-use-terminal
Direct browser control via the Browser Use Terminal CLI. Use when the user wants to automate, scrape, test, or interact with web pages — you drive the browser yourself with Python helpers.
Chrome
Browser automation for the user's Chrome browser. Use for browser tasks that require the user's cookies, logged-in sessions, existing tabs, extensions, or remote authenticated sites.
open-browser-use
Platform-neutral guidance for using Open Browser Use, the open-source Chrome automation stack for AI agents. Use when an agent needs to install, verify, troubleshoot, or operate Open Browser Use through its browser extension, native CLI, JavaScript SDK, Python SDK, Go SDK, or Browser Use style JSON-RPC methods; use…
deep-reverse
Use only for explicit web or API protocol reverse engineering: endpoint discovery, request replay, signature/token/encryption analysis, JavaScript runtime tracing, browser-independent reproduction, or crawler implementation that must not depend on browser automation. Do not use for one-off visible-page extraction or…
web-crawl
Get data from websites with the least necessary complexity. Use for quick lookups, visible-page extraction, search results, tables, pagination, detail-page traversal, downloadable files (Excel/CSV/PDF/ZIP), embedded page state, internal JSON/XHR APIs, bulk collection, reusable crawler generation, and delivery in any…
tidesurf-browser
Drive a real Chromium browser through the tidesurf CLI or MCP tools. Use when a task needs live web browsing: reading pages as compact, token-efficient text with action IDs; clicking, typing, selecting, and scrolling elements by ID; taking screenshots of the full page, viewport, or one element; managing tabs; handling…