Skill3.8k estrellas del repoactualizado 4mo ago

background-agent-pings

Background Agent Pings is a pattern for managing background tasks in Claude Code that uses system reminders instead of polling to track agent progress. Use this when launching long-running background agents to avoid wasting tokens on repeated status checks while continuing other work in parallel, relying on automatic notifications when the agent makes progress or completes output files.

Ver fuente Repositorio: Continuous-Claude-v3

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3 /tmp/background-agent-pings && cp -r /tmp/background-agent-pings/.claude/skills/background-agent-pings ~/.claude/skills/background-agent-pings

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# Background Agent Pings

Trust system reminders as agent progress notifications. Don't poll.

## Pattern

When you launch a background agent, **continue working on other tasks**. The system will notify you via reminders when:
- Agent makes progress: `Agent <id> progress: X new tools used, Y new tokens`
- Agent writes output file (check the path you specified)

## DO

```
1. Task(run_in_background=true, prompt="... Output to: .claude/cache/agents/<type>/output.md")
2. Continue with next task immediately
3. When system reminder shows agent activity, check if output file exists
4. Read output file only when agent signals completion
```

## DON'T

```
# BAD: Polling wastes tokens and time
Task(run_in_background=true)
Bash("sleep 5 && ls ...")  # polling
Bash("tail /tmp/claude/.../tasks/<id>.output")  # polling
TaskOutput(task_id="...")  # floods context
```

## Why This Matters

- Polling burns tokens on repeated checks
- `TaskOutput` floods main context with full agent transcript
- System reminders are free - they're pushed to you automatically
- Continue productive work while waiting

## Source

- This session: Realized polling for agent output wasted time when system reminders already provide progress updates

Del mismo repositorio

aegisSubagent

Security vulnerability analysis and testing

agentica-agentSubagent

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration

arbiterSubagent

Unit and integration test execution and validation

architectSubagent

Feature planning, design documentation, AND integration planning

atlasSubagent

End-to-end and acceptance test execution

braintrust-analystSubagent