claude-code-clilisted

# executing-claude ## Purpose Use this skill to perform coding, research, or automation tasks using the `claude` CLI. It maps requests to Claude's native permission modes to balance automation with security. ## Permission Tiers | Tier | Claude Mode | Capability | Approval Required | Plan Requirement | Typical Tasks | | :------ | :------------------ | :------------------------------------------------------------ | :--------------------------------- | :----------------------------------------- | :---------------------------------------- | | **0** | `plan` | Read-only access, analysis, research. | **No** | Any | Code review, audits, web research. | | **1** | `acceptEdits` | Auto-approves file edits; prompts for shell. | **Yes** | Any | Refactoring, documentation, lint fixes. | | **1.5** | `auto` | All actions; background classifier blocks risky operations. | **No (classifier handles it)** | Team / Enterprise / API; Sonnet 4.6+ only | Long-running tasks, reducing prompt fatigue. | | **2** | `bypassPermissions` | Auto-approves ALL tools (edits + shell); respects deny list. | **Yes (High Risk)** | Any