background-terminals
Run and manage long-lived shell commands in background terminals. Use for dev servers, watchers, streaming builds, and other commands that should keep running while the agent continues working.
- License 许可
- MIT
- 最近更新
- 2026-10-29
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- background-terminals
- description
- Run and manage long-lived shell commands in background terminals. Use for dev servers, watchers, streaming builds, and other commands that should keep running while the agent continues working.
03 SKILL.md 正文
Background Terminals
Use bg_start for long-running commands; use regular bash for quick commands.
Start
Call bg_start with:
command: shell command to runtitle: short recognizable labelworking_dir: project directory when different from the current directory
Background commands receive no stdin. Never use them for interactive prompts.
After starting, continue useful work instead of polling. The terminal sends one completion message when it exits.
Inspect and stop
- Use
bg_statusonly when current output or status is needed. - Use
bg_listto inventory all tracked terminals. - Use
bg_killwhen a process is no longer needed or is stuck; termination continues even if the tool wait is aborted. - Tell the user they can open
/psto inspect live output and kill terminals interactively.
Prefer meaningful titles and avoid starting duplicate servers or watchers. Full output is captured to spill files; tool and completion output shows a concise tail. Terminals are session-scoped and are stopped during shutdown or reload.
04 同仓库更多 Skills
writing-shape
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
writing-beats
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.