aaaaqwq/agent-model-switcher
skills/agent-model-switcher/SKILL.md
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。
$ install --global
skillsauthnpx skillsauth add aaaaqwq/agi-super-team agent-model-switcherInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 1, 2026, 4:19 PM59.2s2 files scanned
SKILL.md
- name:
- agent-model-switcher
- description:
- 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。
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
Related Skills
aaaaqwq/code-exemplars-blueprint-generator
development
VerifiedTrustedCommunity
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods, and documentation formats to establish coding standards and maintain consistency across development teams.
37SKILL.mdUpdated Apr 11, 2026
aaaaqwq/chrome-devtools
tools
VerifiedTrustedCommunity
Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.
37SKILL.mdUpdated Apr 11, 2026
aaaaqwq/breakdown-feature-implementation
data-ai
VerifiedTrustedCommunity
Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.
37SKILL.mdUpdated Apr 11, 2026
aaaaqwq/boost-prompt
tools
VerifiedTrustedCommunity
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the Joyride extension.
37SKILL.mdUpdated Apr 11, 2026