Agent model switcher
批量查看和切换子 agent 的模型配置，用于统一调整多 agent 的 provider/model 设置。From its SKILL.md
npx -y skills add aAAaqwq/AGI-Super-Team --skill agent-model-switcherAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- runs commandsInstructs the agent to run 5 commands, including `python3 ~/clawd/skills/agent-model-switcher/switch_model.py list` and 4 more.
SKILL.md
2.4 KB, 750 tokens by cl100k_base, as published. Nobody here has run it
Agent Model Switcher
批量切换所有子 agent 的模型配置。
用途
- 批量更换所有子 agent 的 model
- 同步所有 agent 的 models.json 配置
- 查看所有 agent 当前的 model 配置
使用方式
1. 查看所有 agent 的 model 配置
python3 ~/clawd/skills/agent-model-switcher/switch_model.py list
2. 更换所有子 agent 的 model（不包括 main）
python3 ~/clawd/skills/agent-model-switcher/switch_model.py set <provider>/glm-5
3. 更换指定 agent 的 model
python3 ~/clawd/skills/agent-model-switcher/switch_model.py set <provider>/glm-5 --agents code,ops,quant
4. 同步所有 agent 的 models.json（从 main 复制）
python3 ~/clawd/skills/agent-model-switcher/switch_model.py sync-models
5. 同步指定 agent 的 models.json
python3 ~/clawd/skills/agent-model-switcher/switch_model.py sync-models --agents batch,law,xiaotu
参数说明
| 参数 | 说明 |
|---|---|
list | 列出所有 agent 的 model 配置 |
set <model> | 设置 agent 的 model |
sync-models | 从 main 复制 models.json 到其他 agent |
--agents <names> | 指定要操作的 agent（逗号分隔） |
--include-main | 包括 main agent（默认不包括） |
--dry-run | 只显示将要执行的操作，不实际执行 |
常用模型
| 别名 | 完整名称 |
|---|---|
| glm5 | <provider>/glm-5 |
| glm47 | <provider>/glm-4.7 |
| opus46 | <provider>/claude-opus-4-6 |
| sonnet46 | <provider>/claude-sonnet-4-6 |
| kimi | <provider>/kimi-k2.5 |
示例
# 查看当前配置
python3 ~/clawd/skills/agent-model-switcher/switch_model.py list
# 全部子 agent 切换到 glm-5
python3 ~/clawd/skills/agent-model-switcher/switch_model.py set glm5
# 只切换 code 和 quant 到 opus-4-6
python3 ~/clawd/skills/agent-model-switcher/switch_model.py set opus46 --agents code,quant
# 同步 models.json 配置
python3 ~/clawd/skills/agent-model-switcher/switch_model.py sync-models
注意事项
- 修改配置后，agent 需要重新启动或等待新 session 才能生效
- 同步 models.json 会覆盖目标 agent 的 models.json，确保 main 的配置是最新的
- 建议先用
--dry-run查看将要执行的操作
What ships with it: 1 file
5.7 KB alongside SKILL.md, 1 of them executable
- switch_model.pyruns5.7 KB
Gives 0 of the 12 instructions most context ai engineering skills give in 750 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- List current agent model configurations
- Set model for all sub-agents
- Sync models.json from main to agents
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.