agentpack-operator
Operate agentpack safely in Claude Code. Use /ap-* commands for execution; prefer --json.
安装与使用
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
查看来源 ↗使用指南技能说明
agentpack-operator
Operate Agentpack safely and reproducibly in Claude Code.
When to use Agentpack
- The user asks to check drift, preview changes, apply changes, or explain why changes happened.
- You need a safe, scriptable workflow with stable
--jsonoutput and guardrails.
How to operate (Claude Code)
Prefer the /ap-* slash commands installed by agentpack bootstrap:
-
/ap-doctor: validate environment and target roots -
/ap-update: update lock + fetch (mutating; user-invoked only) -
/ap-preview: plan + optional diff summary (read-only) -
/ap-plan: compute desired state plan (read-only) -
/ap-diff: diff desired vs current (read-only) -
/ap-deploy: apply changes (mutating; user-invoked only) -
/ap-status: compute drift (read-only) -
/ap-explain: explain plan/diff/status (read-only) -
/ap-evolve: propose overlay changes from drift (mutating; user-invoked only)
If the /ap-* commands are missing or outdated, run:
agentpack --target claude_code bootstrap --scope both
Safety rules
- Never run
deploy --applyunless the user explicitly asked to apply. - Always show
preview/planfirst, and includediffwhen useful. - Prefer
--jsonfor automation and keep outputs small and scoped. - For mutating operations in automation, always pass
--yesand require explicit user approval.
使用示例
查看来源仓库中的使用示例与配置说明。
查看来源 ↗来源历史
- 收录时间
- 2026-01-20
- 索引更新时间
- 2026-01-28
- Branch
- main
收录与同步日期属于本站记录。源码修改历史请查看来源仓库。
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!