About no-polling-agents
no-polling-agents is a guidance skill for managing parallel background agents without repeated status checks. It recommends continuing other work and checking status files only when results are needed or requested.
Key features
- 01Launch agents in the background
- 02Continue work while agents run
- 03Check status only when needed
- 04Avoid repeated polling loops
Use cases
- 01Run parallel agents during other work
- 02Wait for agent results without sleep loops
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/no-polling-agentsin Claude Code to confirm it loaded.
Details
From the project READMENo Polling for Background Agents
When launching parallel background agents, do NOT poll with sleep loops.
Pattern
Background agents write to status files when complete. Wait for them naturally.
DO
- Launch agents with
run_in_background: true - Continue with other work while agents run
- Check status file only when user asks or when you need results to proceed
- Trust the agent completion system
DON'T
- Run
sleep 10 && cat status.txtin loops - Continuously poll for completion
- Waste tokens checking status repeatedly
- Block on agents unless absolutely necessary
When to Check Status
- User explicitly asks "are they done?"
- You need agent output to proceed with next task
- Significant time has passed and user is waiting
Example
// Launch agents
Task({ ..., run_in_background: true })
Task({ ..., run_in_background: true })
// Continue with other work or conversation
// Agents will write to status file when done
// Only check when needed
cat .claude/cache/status.txt
Source
User feedback: "You can just wait until everyone pings you"
Comments
Markdown supported