Skip to content
Back to skills

Background Work

ASecurity

Run a bounded research, analysis, writing, coding, or file task asynchronously and rely on {{product}}'s automatic completion notification instead of polling.

  • 13 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 20, 2026
ai-agents

Security analysis

A100/100

Scanned October 5, 2026

npx -y skills add manishiitg/coding-agent-loop --skill background-work --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Background Work?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Background Work
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/manishiitg-background-work/badge)](https://www.skillsdirectory.com/skills/manishiitg-background-work)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: background-work
description: Run a bounded research, analysis, writing, coding, or file task asynchronously and rely on {{product}}'s automatic completion notification instead of polling.
---

# Background work

Use `run_in_background` when a self-contained task can continue independently while this chat remains available. Give it a short name, complete instructions, the smallest useful reasoning level, and any extra skill names it needs. The child already inherits this project's workspace access and attached skills.

After the tool returns, tell the user the task is running and end the turn. Do not poll with `query_agent` or sleep loops. {{product}} automatically sends an `[AUTO-NOTIFICATION]` into this same chat when the child completes or fails; then summarize the result and continue only if more work is required.

Use `query_agent` only when the user explicitly asks for live status, `list_agents` to identify running work, and `terminate_agent` when the user asks to stop it.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.