Agent Browser
Automate a real browser via inference.sh: navigate, interact, screenshot, record
- What
- Automate a real browser via inference.sh: navigate, interact, screenshot, record
- Cost
- Free
- Needs
- the belt CLI (inference.sh) installed and logged in; install the belt CLI skill first with: npx skills add belt-sh/cli
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — browser automation for AI agents via inference.sh: navigate web pages, interact with elements through a simple @e ref system (click, fill, drag-drop, file upload), take screenshots, record video, and execute JavaScript — Playwright under the hood, driven through the belt CLI. Every automation follows the same loop: open (get element refs), interact, re-snapshot after DOM changes, close (returns video if recording). Kept as the canonical one of three byte-identical forks on skills.sh — the skills-shell and its-a-skill-issue copies were dropped as duplicates. License transparency: this fork ships no LICENSE file of its own, so the MIT license is inherited from the upstream obra/superpowers repository. By @magentosh, listed here with credit to its creator. Honest caveats: requires the belt CLI installed and logged in (`belt login`); browser sessions run through inference.sh infrastructure — check their terms and pricing before heavy use; it automates — it doesn't bypass logins or paywalls for you. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: the belt CLI (inference.sh) installed and logged in; install the belt CLI skill first with: npx skills add belt-sh/cli Install "Agent Browser" for me. Automate a real browser via inference.sh: navigate, interact, screenshot, record Repository: https://github.com/magentosh/superpowers/blob/main/tools/utilities/agent-browser/SKILL.md 1. Fetch the SKILL.md file for the magentosh-agent-browser skill from the repository into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "magentosh-agent-browser". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.