worker-model-switch

worker-model-switch is a skill for Claude Code, Codex from agentscope-ai/AgentTeams. It costs 29 tokens per session (355 once invoked), scanned A, original, Apache-2.0.

A skill for changing the language model used by a worker agent through a command-line tool. The controller updates the worker configuration and recreates its container.

In plain words
What is it for?
Use it when an administrator wants to switch a worker to another supported model or needs to report an update failure.
Why use it?
It handles the related model settings and restart process automatically, so they do not need to be configured separately.

Skill for Claude CodeCodex

About the project

AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.

agentscope-ai/AgentTeams · 5,564 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentscope-ai/agentteams/worker-model-switch
Any agent
npx skills add agentscope-ai/AgentTeams --skill worker-model-switch
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/AgentTeams

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for worker-model-switch

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentscope-ai/agentteams/worker-model-switch.svg)](https://agentmods.dev/skills/agentscope-ai/agentteams/worker-model-switch)
Your own site
<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/worker-model-switch"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/worker-model-switch.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00355
Opus 5 $0.00015 $0.00178
Sonnet 5 $0.00006 $0.00071
Haiku 4.5 $0.00003 $0.00036

Measured 5d ago against content hash caa3095605ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worker-model-switch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

manager/agent/skills/worker-model-switch/SKILL.md · 45 lines

What it actually says

Worker Model Switch

Switch a Worker's LLM model using the agt CLI. The controller handles all details: model parameter resolution, openclaw.json generation, storage push, and container recreation.

Usage

agt update worker --name <WORKER_NAME> --model <MODEL_ID>

Examples:

agt update worker --name alice --model claude-sonnet-4-6
agt update worker --name alice --model deepseek-chat

What happens

The controller automatically:

  1. Updates the Worker CR's spec.model
  2. Resolves model parameters (contextWindow, maxTokens, reasoning, input modalities) from its built-in model registry
  3. Regenerates openclaw.json and pushes it to storage
  4. Recreates the Worker container

You do NOT need to specify context window, reasoning, or any model parameters — the controller knows them.

On success

The CLI prints worker/<name> configured. The controller reconciles the change automatically. No manual restart is needed.

On failure

Report the CLI error output to the human admin. Common causes:

  • Worker name does not exist
  • Controller API is unreachable

Unknown models

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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 45 lines · 29 tokens per session scan A caa3095605ea

Subscribe to this mod's changes

worker-model-switch is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,564 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 355 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…

GCWing/BitFun · 88 tokens

plan-ceo-review

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…

GCWing/BitFun · 143 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…

GCWing/BitFun · 74 tokens