메뉴
Switch a Worker Agent's LLM model via hiclaw CLI. Use when the human admin requests changing a Worker's model.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.
Use when TEAMS.md Communication Contract needs detailed routing: Channel / Room Selection Protocol, Requester Report Delivery Protocol, or Message Tool Protocol. It resolves current session vs Team Room vs assignment room vs requester reply_route vs external channel, and explains when to use the message MCP tool. Do not use it to choose Quick Task or Project Work, create rooms, delegate tasks, check results, or accept project state.
Use for TeamHarness shared workspace paths, explicit filesync operations, and shared project/task artifact boundaries.
Use to understand TeamHarness team roles, responsibility boundaries, and who owns project, task, runtime, and control-plane work.
Use only after Project Work mode is selected, before TeamHarness projectflow calls, project DAG or Loop planning, ready-node resolution, iteration recording, project files, result acceptance, or project progress updates.
Use only after Project Work mode is selected, when a TeamHarness Leader delegates ready project nodes, writes task specs, checks Worker results, and routes completion or blocker messages.
| name | worker-model-switch |
| description | Switch a Worker Agent's LLM model via hiclaw CLI. Use when the human admin requests changing a Worker's model. |
Switch a Worker's LLM model using the hiclaw CLI. The controller handles all details: model parameter resolution, openclaw.json generation, storage push, and container recreation.
hiclaw update worker --name <WORKER_NAME> --model <MODEL_ID>
Examples:
hiclaw update worker --name alice --model claude-sonnet-4-6
hiclaw update worker --name alice --model deepseek-chat
The controller automatically:
spec.modelopenclaw.json and pushes it to storageYou do NOT need to specify context window, reasoning, or any model parameters — the controller knows them.
The CLI prints worker/<name> configured. The controller reconciles the change automatically. No manual restart is needed.
Report the CLI error output to the human admin. Common causes:
If the admin requests a model not in the controller's built-in registry, the controller uses safe defaults (contextWindow=150000, maxTokens=128000, reasoning=true, input=["text"]). If the admin needs specific parameters for an unknown model, they should update the controller's model registry rather than overriding at the skill level.