butler-skill
Let an agent choose when to delegate work and verify the result
- Stars
- 0
- Forks
- 0
- Updated
- Updated Jul 8, 2026
Let an agent choose when to delegate work and verify the result
Butler treats the main agent as the execution owner: it understands the goal, makes key judgments, integrates results, and performs final acceptance. It may delegate bounded, verifiable subtasks to a lower-cost model only when the total effort is worthwhile, and it can choose to do the work directly instead. Delegated output must be checked by the main agent, with explicit terminal states for completion, decisions, or a new work window.
Resource types
Use cases
Platforms
Capabilities
Plan and execute multi-step tasks from natural-language requests in Claude Code.
Register for Luma events from a link using your profile and GitHub
Public GitHub facts last synced Jul 10, 2026.
Supervises other skills with visible steps and user-controlled decisions.
Let an agent wake, integrate context, act, and choose its next cadence