📄 skillActivePromisingcritical

ColeMurray/background-agents

An open-source background agents coding system

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

1.9k

Skill Type

🚀 CI/CD & Deployment

Quality Score

116/200

License

MIT

Forks

294

Last Updated

Jun 11, 2026

Discovered

Apr 15, 2026

Validation

Passed

github.com/ColeMurray/background-agents

Quality Breakdown

116/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

✓Verification/Safety+20

✓Code Examples+15

✓Composability+15

Repo Health

✓Recent Activity+15

✓Scripts/Automation+10

✓Real Usage (Issues)+10

✓Single Responsibility+10

✓Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

critical

Manual security review required. Use with extreme caution.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Multi-agent spawning capability: Repository explicitly implements background agents that can 'spawn parallel sub-tasks that work in separate sandboxes simultaneously' (AGENTS.md, router.spawn-child.test.ts)
Autonomous execution without human approval gates: System runs tasks in background and via webhooks/cron without per-execution human approval
Full system access capabilities: Agents have access to 'full development environments (Node.js, Python, git, browser automation, VS Code)' and can execute arbitrary code in sandboxes
Persistent configuration modification: .claude/ directory with SKILL.md and CLAUDE.md files indicates persistent agent configuration and behavior storage
External code execution: System integrates with GitHub Apps, OpenAI, webhooks, and can clone/execute arbitrary repositories
Sandbox escape risk: Multiple sandbox-related files (packages/control-plane/src/sandbox/) indicate sandbox management, but sandboxes can be compromised