Skip to content

SuperInstance/baton-skill

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Baton Skill

Pass the work before you run out of context. Every subagent is the next generation.

OpenClaw agents hit context limits. When you can feel the ceiling approaching — around 70-80% token usage — you don't crash. You don't truncate. You hand off.

Baton packages everything a subagent needs: current state, task description, known constraints, pending decisions. The subagent becomes the next generation. They don't report back until they're done.


Core Principle

One agent does not solve a large problem from start to finish. One agent breaks off a piece, passes the baton, and trusts the next agent to carry it.

How It Works

baton:
  generation: 3
  parent: "forge-2"
  task: "Complete CUDA benchmark analysis"
  state:
    completed: ["int8-x4", "fp16-unsafe"]
    pending: ["tensor-core", "bank-padding"]
    artifacts: "/tmp/bench-results/"
  constraints:
    - "max-tokens: 8000"
    - "deadline: 15min"
  decisions:
    - "Use INT8 for all production kernels (proven sound)"

The subagent picks up state, completes pending, adds their own decisions, and passes to generation 4.


Why "Baton"?

Because a relay race is the right metaphor. You don't run the whole race yourself. You run your leg as fast as you can, then hand off. The baton is the continuity — the work never stops, it just changes carriers.


How It Fits


License

MIT

About

Generational workload orchestration skill for OpenClaw agents. Proactive context handoff at ~70-80% token usage to prevent context overflow and preserve work continuity.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors