/multi-execute

description: Execute a multi-model implementation plan while preserving Claude as the only filesystem writer.

Execute - Multi-Model Collaborative Execution

Multi-model collaborative execution - Get prototype from plan → Claude refactors and implements → Multi-model audit and delivery.

> **Prerequisite:** Requires the external `ccg-workflow` runtime, which is **not** part of the base ECC install. Initialize it with `npx ccg-workflow` to provision `~/.claude/bin/codeagent-wrapper` and the `~/.claude/.ccg/prompts/*` role files this command depends on. Without that runtime, this command will not run correctly.

$ARGUMENTS

---

Core Protocols

• **Language Protocol**: Use **English** when interacting with tools/models, communicate with user in their language
• **Code Sovereignty**: External models have **zero filesystem write access**, all modifications by Claude
• **Dirty Prototype Refactoring**: Treat Codex/Gemini Unified Diff as "dirty prototype", must refactor to production-grade code
• **Stop-Loss Mechanism**: Do not proceed to next phase until current phase output is validated
• **Prerequisite**: Only execute after user explicitly replies "Y" to `/ccg:plan` output (if missing, must confirm first)

---

Multi-Model Call Specification

**Call Syntax** (parallel: use `run_in_background: true`):

# Resume session call (recommended) - Implementation Prototype
Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}resume <SESSION_ID> - \"$PWD\" <<'EOF'
ROLE_FILE: <role prompt path>
<TASK>
Requirement: <task description>
Context: <plan content + target files>
</TASK>
OUTPUT: Unified Diff Patch ONLY. Strictly prohibit any actual modifications.
EOF",
  run_in_background: true,
  timeout: 3600000,
  description: "Brief description"
})

# New session call - Implementation Prototype
Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}- \"$PWD\" <<'EOF'
ROLE_FILE: <role prompt path>
<TASK>
Requirement: <task description>
Context: <plan content + target files>
</TASK>
OUTPUT: Unified Diff Patch ONLY. Strictly prohibit any actual modifications.
EOF",
  run_in_background: true,
  timeout: 3600000,
  description: "Brief description"
})

**Audit Call Syntax** (Code Review / Audit):

Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}resume <SESSION_ID> - \"$PWD\" <<'EOF'
ROLE_FILE: <role prompt path>
<TASK>
Scope: Audit the final code changes.
Inputs:
- The applied patch (git diff / final unified diff)
- The touched files (relevant excerpts if needed)
Constraints:
- Do NOT modify any files.
- Do NOT output tool commands that assume filesystem access.
</TASK>
OUTPUT:
1) A prioritized list of issues (severity, file, rationale)
2) Concrete fixes; if code changes are needed, include a Unified Diff Patch in a fenced code block.
EOF",
  run_in_background: true,
  timeout: 3600000,
  description: "Brief description"
})

**Model Parameter Notes**:

• `{{GEMINI_MODEL_FLAG}}`: When using `--backend gemini`, replace with `--gemini-model gemini-3-pro-preview` (note trailing space); use empty string for codex

**Role Prompts**:

| Phase | Codex | Gemini | |-------|-------|--------| | Implementation | `~/.claude/.ccg/prompts/codex/architect.md` | `~/.claude/.ccg/prompts/gemini/frontend.md` | | Review | `~/.claude/.ccg/prompts/codex/reviewer.md` | `~/.claude/.ccg/prompts/gemini/reviewer.md` |

**Session Reuse**: If `/ccg:plan` provided SESSION_ID, use `resume <SESSION_ID>` to reuse context.

**Wait for Background Tasks** (max timeout 600000ms = 10 minutes):

TaskOutput({ task_id: "<task_id>", block: true, timeout: 600000 })

**IMPORTANT**:

• Must specify `timeout: 600000`, otherwise default 30 seconds will cause premature timeout
• If still incomplete after 10 minutes, continue polling with `TaskOutput`, **NEVER kill the process**
• If waiting is skipped due to timeout, **MUST call `AskUserQuestion` to ask user whether to continue waiting or kill task**

---

Execution Workflow

**Execute Task**: $ARGUMENTS

Phase 0: Read Plan

`[Mode: Prepare]`

1. **Identify Input Type**:

• Plan file path (e.g., `.claude/plan/xxx.md`)
• Direct task description

2. **Read Plan Content**:

• If plan file path provided, read and parse
• Extract: task type, implementation steps, key files, SESSION_ID

3. **Pre-Execution Confirmation**:

• If input is "direct task description" or plan missing `SESSION_ID` / key files: confirm with user first
• If cannot confirm user replied "Y" to plan: must confirm again before proceeding

4. **Task Type Routing**:

| Task Type | Detection | Route | |-----------|-----------|-------| | **Frontend** | Pages, components, UI, styles, layout | Gemini | | **Backend** | API, interfaces, database, logic, algorithms | Codex | | **Fullstack** | Contains both frontend and backend | Codex ∥ Gemini parallel |

---

Phase 1: Quick Context Retrieval

`[Mode: Retrieval]`

**If ace-tool MCP is available**, use it for quick context retrieval:

Based on "Key Files" list in plan, call `mcp__ace-tool__search_context`:

mcp__ace-tool__search_context({
  query: "<semantic query based on plan content, including key files, modules, function names>",
  project_root_path: "$PWD"
})

**Retrieval Strategy**:

• Extract target paths from plan's "Key Files" table
• Build semantic query covering: entry files, dependency modules, related type definitions
• If results insufficient, add 1-2 recursive retrievals

**If ace-tool MCP is NOT available**, use Claude Code built-in tools as fallback: 1. **Glob**: Find target files from plan's "Key Files" table (e.g., `Glob("src/components/**/*.tsx")`) 2. **Grep**: Search for key symbols, function names, type definitions across the codebase 3. **Read**: Read the discovered files to gather complete context 4. **Task (Explore