Updated 6mo ago
by chaokunyang
browser-terminal-use
Browser Terminal Use turns cloud/browser terminals into a locally scriptable command surface for AI Agents. It bridges local agent loops with remote execution, streams verifiable output and exit codes, and includes ready-to-use Agent skills so advanced workflows can be adopted with minimal setup.
26 GitHub stars (26)
Steady at 26 stars — no new stars in the 16 days since Sep 30.
- 1 skill (1 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 6mo ago last update (Last updated 6mo ago)
Install
Skills CLI
npx skills add chaokunyang/browser-terminal-use
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/chaokunyang/browser-terminal-usecp -r "browser-terminal-use/skill/browser-terminal-use-agent" ~/.claude/skills/
Copies the browser-terminal-use-agent skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add chaokunyang/browser-terminal-use
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
browser-terminal-use-agent
Operate Browser Terminal Use as an execution bridge between local CLI and browser-hosted terminals. Use when Codex needs to run or iterate shell commands in non-local environments through a browser terminal, build cloud-side verifiable execution loops for LLM agents, debug remote runtime issues (GPU, containers, bastion-only networks), or manage daemon/extension binding, timeout, cancel, and opti…
skill/browser-terminal-use-agent/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.