/multi

command: multi
disable-model-invocation: true
description: "[advanced] Force multi-provider parallel execution for any task - manual override mode"

Multi - Multi-Provider Override

**Forces multi-provider execution for any task using all available AI providers.**

🤖 INSTRUCTIONS FOR CLAUDE

EXECUTION MECHANISM — NON-NEGOTIABLE

**You MUST dispatch work to external providers (Codex, Antigravity, etc.) for this command. You are PROHIBITED from:**

• ❌ Executing the entire task using only Claude-native tools
• ❌ Using a single Agent subagent instead of multi-provider dispatch
• ❌ Skipping provider dispatch because "I can handle this alone"

**Multi-LLM orchestration is the purpose of this command.** Single-model execution defeats its purpose.

When the user invokes this command (e.g., `/octo:multi <task>`):

Step 1: Cost Awareness & Intent Confirmation

**CRITICAL: Before forcing multi-provider execution, use AskUserQuestion to confirm intent and cost awareness:**

AskUserQuestion({
  questions: [
    {
      question: "Why do you need multiple AI perspectives?",
      header: "Intent",
      multiSelect: false,
      options: [
        {label: "High-stakes decision", description: "Critical choice requiring comprehensive analysis"},
        {label: "Quality validation", description: "Cross-check important work for accuracy"},
        {label: "Learning different approaches", description: "See how different models think"},
        {label: "Comparing perspectives", description: "Want to see model-specific insights"},
        {label: "Just exploring", description: "Curious about multi-AI capabilities"}
      ]
    },
    {
      question: "Are you aware this uses external API credits?",
      header: "Cost",
      multiSelect: false,
      options: [
        {label: "Yes, proceed", description: "I understand this may use external provider credits or subscriptions"},
        {label: "Tell me more about costs", description: "Explain what I'll be charged"},
        {label: "Use included/local providers only", description: "Use Claude plus providers that do not add per-query API charges"}
      ]
    }
  ]
})

**WAIT for the user's answers before proceeding.**

**After receiving answers:**

• **If user selected "Tell me more about costs"**: Explain the cost breakdown, then ask question 2 again
• **If user selected "Use included/local providers only"**: Use Claude plus available included/local providers such as Antigravity, Copilot, Qwen, Ollama, or already-authenticated CLIs; explain any unavailable providers
• **If user selected "Yes, proceed"**: Continue with multi-provider execution
• **Store intent** in context for provider selection (high-stakes → use all available providers, exploring → maybe skip one if unavailable)

Step 2: Check Provider Availability & Execute

Use the Bash tool to run the shared live readiness check. This command asks for multiple providers, so its provider probe is explicit and bounded:

OCTO_ROOT="${CLAUDE_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}"
provider_helper="$OCTO_ROOT/scripts/helpers/check-providers.sh"
if [[ ! -x "$provider_helper" ]]; then
  echo "ERROR: Claude Octopus provider readiness helper is unavailable. Run /octo:setup." >&2
  exit 1
fi

PROVIDER_STATUS="$(OCTOPUS_PREFLIGHT_PROBE=1 "$provider_helper" 2>/dev/null || true)"
printf '%s\n' "$PROVIDER_STATUS"

READY_EXTERNAL="$(printf '%s\n' "$PROVIDER_STATUS" |
  awk -F: '$1 !~ /^claude($|-)/ && $2 == "available" { print $1 }')"
if [[ -z "$READY_EXTERNAL" ]]; then
  echo "No external provider is ready. Multi-provider mode needs at least one supported external provider."
  echo "Run /octo:setup to configure one, or use Claude directly."
  exit 1
fi

Treat the emitted `provider:status` lines as authoritative. Execute the task with the providers listed in `READY_EXTERNAL`, incorporating the user's intent from Step 1. Do not re-detect binaries or credentials inside this command.

Step 3: Adversarial Synthesis (MANDATORY — do NOT skip)

**After collecting responses from all providers, you MUST synthesize — not concatenate.**

The whole point of multi-provider execution is diversity of opinion. Presenting provider responses back-to-back without synthesis defeats this purpose. You MUST produce a structured synthesis with these sections:

1. **Consensus** — Where providers agree. State the shared conclusion and note how many providers converged on it. 2. **Divergence** — Where providers disagree. Quote each provider's position verbatim so the user sees the actual disagreement, not a smoothed-over summary. 3. **Resolution** — Your confidence-weighted recommendation resolving the conflicts. State your confidence level (high/medium/low) and WHY you side with one position over another. If you cannot resolve, say so — an honest "this depends on your context" is better than a false consensus. 4. **Minority Opinions** — Dissenting views that may be valuable even if outnumbered. A single provider flagging a security risk or edge case that others missed is often the most valuable insight.

**Present this synthesis in the chat using this format:**

## Multi-Provider Synthesis

### Consensus
[Where all providers agree]

### Divergence
- 🔴 **Codex**: "[direct quote or close paraphrase]"
- 🧭 **Antigravity**: "[direct quote or close paraphrase]"
- 🔵 **Claude**: "[direct quote or close paraphrase]"

### Resolution
[Your recommendation with confidence level and reasoning]

### Minority Opinions
[Dissenting views worth preserving — or "None: all providers converged"]

**Skip this step with `--fast` or when user explicitly requests speed over thoroughness.** In fast mode, present raw provider responses without synthesis.

---

Quick Usage

Just use natural language:

"Run this with all providers: What is Redis?"
"I want multiple AI models to look at this architecture"
"Get multiple perspectives on whether to use TypeScript"
"Force multi-provider