high perf orchestration a la oh my codex & gastown
by @jkobject
Hybrid orchestration skill where OpenClaw stays the control plane and ACP Claude Code is the default execution backend for coding work.
clawhub install orchestration-setupsπ About This Skill
name: claude-code-control-plane description: "Hybrid orchestration skill where OpenClaw stays the control plane and ACP Claude Code is the default execution backend for coding work." metadata: {"openclaw":{"emoji":"π§"}}
Claude Code Control Plane
Use this when the user wants multi-step coding orchestration without making the main OpenClaw session carry the execution load.
Core idea
This skill is for hybrid orchestration, not pure OpenClaw swarms.
When to use
Use this skill when:
Do not use this skill when:
Default architecture
Roles
State
Every workstream must have: 1. a task/spec file 2. a shared artifact path 3. a clear handoff packet written before spawn 4. a rolling worker summary file for context rolloverLaunch policy
Default spawn
For a real coding worker, prefer:sessions_spawnruntime: "acp"agentIdthread: truemode: "session"This gives a persistent coding worker instead of a fragile short-lived chat worker.
Suggested defaults
Orchestration modes
1. Single builder
Use when one worker can do the task.Pattern:
2. Builder + reviewer
Use by default for non-trivial code changes.Pattern:
3. Project builder
Use when there is a real repo/worktree with multiple steps.Pattern:
4. Hybrid swarm
Use only when the work is large enough to justify multiple workers.Pattern:
Guardrails
1. Do not keep complex run state only in session chat. 2. Do not spawn workers before writing the handoff file. 3. Do not let the orchestrator become the builder. 4. Use worktrees for parallel builders. 5. Prefer fewer persistent workers over many throwaway workers. 6. If OpenClaw runtime looks unhealthy, stop spawning and continue with ACP sessions already alive. 7. Every long-running worker should maintain a rolling summary file covering: - what it has done - what it is doing now - what it learned / what matters next 8. When a worker nears context pressure, compress to file first, then resume or replace the worker from that file instead of letting it drift into a weak soft-stop.
Recommended file layout
project-specs/
shared-specs/
shared-artifacts/
runs//
worker-state/
Prompt template for ACP workers
## TASK
EXPECTED OUTPUT
MUST DO
read the listed files first
write artifacts before claiming completion
report only the concise delta MUST NOT
do not overwrite unrelated files
do not self-approve
do not hide uncertainty CONTEXT
repo/worktree:
files to read first:
artifact path:
Recommended starting default
For now, the safest default is:
That is the baseline setup this skill assumes.