Borrowing it
Nothing to install: this file belongs to coleam00/dark-factory-experiment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coleam00/dark-factory-experiment/main/.claude/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/coleam00/dark-factory-experimentWrote 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/coleam00/dark-factory-experiment/agent-browser)<a href="https://agentmods.dev/skills/coleam00/dark-factory-experiment/agent-browser"><img src="https://agentmods.dev/badge/skills/coleam00/dark-factory-experiment/agent-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.
<a href="https://agentmods.dev/skills/coleam00/dark-factory-experiment/agent-browser"><img src="https://agentmods.dev/badge/skills/coleam00/dark-factory-experiment/agent-browser.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.02169 |
| Opus 5 | $0.00026 | $0.01085 |
| Sonnet 5 | $0.00010 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
agent-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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 9d ago First seen · 272 lines · 51 tokens per session scan A 1b2d268c7aba
agent-browser is a skill published in the GitHub repository coleam00/dark-factory-experiment (151 stars, last pushed 25d ago), with no licence file. It adds 51 tokens to every session and 2,169 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
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.
web-e2e
Full end-to-end browser testing for local web apps with a persistent logged-in session. Log in once into a named Chrome profile, then drive real flows with trace evidence against your locally served app - Laravel/Herd, docker compose, FastAPI+SPA, Vite. Adds per-project orchestration via .e2e/config.json - boot +…
browser-proof
Browser-visible verification — route smoke, screenshots, console errors. Receipt required.
dev-browser
CIEL's framework for browser automation with persistent page state. Navigates URLs, fills forms, takes screenshots, scrapes data, and tests web apps via sandboxed JavaScript scripts.