mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-09 02:24:11 +08:00

Files

catlog22 bc959b1a0f refactor(cli): remove --agent flag and enhance agent execution context

- Remove --agent parameter from all CLI commands (now default behavior)
- Restore and enhance Task() invocation context for cli-execution-agent
- Add detailed execution phases and context discovery strategies
- Simplify documentation by removing redundant CLI command templates
- Consolidate output documentation to unified format

Modified commands:
- /cli:analyze, /cli:chat, /cli:execute
- /cli:mode:plan, /cli:mode:code-analysis, /cli:mode:bug-diagnosis

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-10 16:12:04 +08:00

2.2 KiB

Raw Blame History

name, description, argument-hint, allowed-tools

name	description	argument-hint	allowed-tools
chat	Read-only Q&A interaction with Gemini/Qwen/Codex for codebase questions with automatic context inference	[--tool codex\|gemini\|qwen] [--enhance] inquiry	SlashCommand(), Bash(), Task(*)

CLI Chat Command (/cli:chat)

Purpose

Direct Q&A interaction with CLI tools for codebase analysis. Read-only - does NOT modify code.

Tool Selection:

gemini (default) - Best for Q&A and explanations
qwen - Fallback when Gemini unavailable
codex - Alternative for technical deep-dives

Parameters

--tool <gemini|qwen|codex> - Tool selection (default: gemini)
--enhance - Enhance inquiry with /enhance-prompt
<inquiry> (Required) - Question or analysis request

Tool Usage

Gemini (Primary):

--tool gemini  # or omit (default)

Qwen (Fallback):

--tool qwen

Codex (Alternative):

--tool codex

Execution Flow

Uses cli-execution-agent (default) for automated Q&A:

Task(
  subagent_type="cli-execution-agent",
  description="Codebase Q&A with intelligent context discovery",
  prompt=`
    Task: ${inquiry}
    Mode: chat
    Tool: ${tool_flag || 'gemini'}
    Enhance: ${enhance_flag}

    Execute codebase Q&A with intelligent context discovery:

    1. Context Discovery:
       - Parse inquiry to identify relevant topics/keywords
       - Discover related files using MCP/ripgrep (prioritize precision)
       - Include @CLAUDE.md + discovered files
       - Validate context relevance to question

    2. CLI Command Construction:
       - Tool: ${tool_flag || 'gemini'} (qwen fallback, codex for deep dives)
       - Context: @CLAUDE.md + discovered file patterns
       - Mode: analysis (read-only)
       - Expected: Clear, accurate answer with code references

    3. Execution & Output:
       - Execute CLI tool with assembled context
       - Validate answer completeness
       - Save to .workflow/WFS-[id]/.chat/chat-[timestamp].md (or .scratchpad/)
  `
)

Core Rules

Read-only: Provides answers, does NOT modify code
Context: @CLAUDE.md + inferred or all files (@**/*)
Output: .workflow/WFS-[id]/.chat/chat-[timestamp].md (or .scratchpad/ if no session)

2.2 KiB Raw Blame History