🔌 pluginActivePromisinghigh

babysitter

Babysitter enforces obedience to agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

Stars

1.3k

Skill Type

🚀 CI/CD & Deployment

Quality Score

112/200

License

MIT

Forks

Last Updated

Jun 11, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/a5c-ai/babysitter

Quality Breakdown

112/ 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.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

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

Risk Assessment

Repository implements multi-agent orchestration and spawning system ('agentic workforces', 'self-orchestration') with ability to manage agent execution flows
Contains persistent configuration modifications across multiple tool integrations (.claude/, .cursor-plugin/, .a5c/ directories with settings and agent definitions)
Includes Docker containerization with entrypoint scripts and CI/CD pipelines that could automate execution without explicit approval gates
Contains orchestrator scripts (.a5c/orchestrator_scripts/) that manipulate prompts, events, and outputs - enabling meta-level control of agent behavior
Designed to enforce 'obedience' to agents with deterministic execution paths, suggesting capability to override normal approval mechanisms
Plugin system across multiple AI platforms (Claude, Cursor) enables integration hooks and command execution