Skill Parallel Agents

Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than /octo:* slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, see skills/blocks/codex-host-adapter.md.

Claude Octopus - Multi-Tentacled Orchestrator

MANDATORY COMPLIANCE — DO NOT SKIP

When this skill is invoked, you MUST dispatch work to multiple providers in parallel. You are PROHIBITED from:

• Running tasks sequentially with a single model instead of parallel multi-provider dispatch
• Skipping orchestrate.sh and doing the work directly
• Deciding the task is "simple enough" for a single provider
• Substituting serial Claude-only execution for multi-LLM parallel execution

This skill exists specifically for multi-provider parallel work. If you catch yourself thinking "I'll just do this myself" — STOP.

Multi-tentacled orchestrator for Claude Code - using Double Diamond methodology for comprehensive problem exploration, consensus building, and validated delivery.

    DISCOVER          DEFINE           DEVELOP          DELIVER
      (probe)         (grasp)          (tangle)          (ink)

    \         /     \         /     \         /     \         /
     \   *   /       \   *   /       \   *   /       \   *   /
      \ * * /         \     /         \ * * /         \     /
       \   /           \   /           \   /           \   /
        \ /             \ /             \ /             \ /

   Diverge then      Converge to      Diverge with     Converge to
    converge          problem          solutions        delivery

Quick Start

Note for Claude Code users: You don't need to run these commands! Just talk naturally to Claude:

• "Research OAuth authentication patterns"
• "Build a user authentication system"
• "Review this code for security issues"

The commands below are for direct CLI usage or automation.

# Full Double Diamond workflow (all 4 phases)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh embrace "Build a user authentication system"

# Individual phases
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe "Research authentication best practices"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grasp "Define auth requirements"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh tangle "Implement auth feature"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh ink "Validate and deliver auth implementation"

# Crossfire: Adversarial cross-model review
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple "implement password reset API"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles security "implement JWT auth"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh squeeze "review auth.ts for vulnerabilities"

# Smart auto-routing (detects intent automatically)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "research OAuth patterns"           # -> probe
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "build user login"                  # -> tangle + ink
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "review the auth code"              # -> ink

IMPORTANT: When NOT to Use This Skill

DO NOT use this skill if the user's request involves:

1. Built-in Claude Code commands - Commands starting with / that are part of Claude Code itself:

   • /plugin - Plugin management (add, remove, update, list)
   • /init - Project initialization
   • /help - Help documentation
   • /clear - Clear conversation
   • /commit - Git commit operations
   • /remember - Memory management
   • Any other / command that isn't /parallel-agents or /octo:*

2. Direct tool usage - Simple file operations, git commands, or terminal tasks

   • Reading/writing files
   • Running git commands
   • Basic bash operations
   • These should use built-in tools directly

3. Claude Code configuration - Managing Claude Code itself

   • Changing settings
   • Managing plugins
   • Updating Claude Code

If the user's request matches any of the above, DO NOT activate this skill. Handle the request using standard Claude Code tools and capabilities instead.

Visual Indicators - Know What's Running

Claude Octopus uses visual indicators so you always know which AI is responding:

What Triggers External CLIs vs Subagents

External CLIs execute when:

• Using /parallel-agents command explicitly
• Using /octo:debate command (AI Debate Hub)
• Running orchestrate.sh workflows (probe, grasp, tangle, ink, embrace, grapple, squeeze)
• Knowledge mode deliberation (when Knowledge Mode is ON)
• Natural language that triggers this skill (research, build, review tasks)

Claude Subagents execute when:

• Simple file operations (read, write, edit)
• Git commands and bash operations
• Code reading and navigation
• Tasks that don't need multiple perspectives
• Built-in Claude Code capabilities are sufficient

Why this matters: External CLIs use your OpenAI/Google API quotas and incur costs. Claude subagents are included with Claude Code at no additional charge.

When you see 🐙 CLAUDE OCTOPUS ACTIVATED, external CLI providers such as Codex, Antigravity, and others will be invoked for multi-perspective analysis.

Force Multi-Provider Mode

Sometimes you want multi-provider analysis even for simple tasks that wouldn't normally trigger workflows. This is useful when you need comprehensive perspectives on decisions, want to compare how different models think, or when automatic routing underestimates task complexity.

Explicit Command

Force multi-provider execution using the /octo:multi command:

/octo:multi "Explain how Redis works"
/octo:multi "What is OAuth?"
/octo:multi "Review this simple function"
/octo:multi "Should we use TypeScript?"

Natural Language Triggers

You can also force multi-provider mode with natural language:

"Run this with all providers: What is JWT?"
"I want multiple AI models to look at our architecture"
"Get multiple perspectives on this design decision"
"Use all providers for explaining caching strategies"
"Force multi-provider analysis of our API design"

When to Force Parallel Mode

Use forced parallel mode when:

• High-stakes decisions require comprehensive analysis from multiple models
• Comparing perspectives - you want to see how different models approach the same problem
• Simple questions with depth - seemingly simple questions that deserve thorough multi-model analysis
• Learning different approaches - exploring how each model thinks about a topic
• Automatic routing underestimates complexity - task appears simple but has nuance

Don't force parallel mode when:

• Task already auto-triggers workflows (octo research, octo build, octo review)
• Simple factual questions Claude can answer reliably
• Cost efficiency is important (see cost awareness below)
• File operations or code navigation (use built-in tools)

Cost Awareness

Forcing parallel mode uses external CLIs for every task, which incurs API costs:

Total cost per forced query: ~$0.02-0.08

Use forced parallel mode judiciously for tasks where multiple perspectives genuinely add value. For routine work, let automatic routing decide when multi-provider analysis is beneficial.

Visual Indicator

When you force parallel mode, you'll see this banner:

🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider mode
Force parallel execution

Providers:
🔴 Codex CLI - [Role in this task]
🧭 Antigravity CLI - [Role in this task]
🔵 Claude - [Role in this task]

Followed by results from each provider marked with their indicators (for example 🔴 🟡 🧭 🔵).

Prerequisites check

Once this skill activates, run the local provider check:

OCTO_ROOT="${CLAUDE_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}"
"$OCTO_ROOT/scripts/orchestrate.sh" detect-providers

This check reads local commands, credentials, and the one-hour cache. It does not call provider APIs. Current output includes the Claude Code version contract and one status per provider:

Detecting Claude Code version...

CLAUDE_CODE_VERSION=2.1.219
CLAUDE_CODE_STATUS=ok
CLAUDE_CODE_MINIMUM=2.1.14

CODEX_STATUS=ok
AGY_STATUS=unauthenticated

Provider values are ok, unauthenticated, quota, not-installed, or a specific reason such as model-invalid.

Route based on the result

If Claude Code is outdated, stop and show the version and update instructions reported by the command:

CLAUDE_CODE_VERSION=2.1.13
CLAUDE_CODE_STATUS=outdated
CLAUDE_CODE_MINIMUM=2.1.14

If one non-Claude provider reports ok, use it. Parallel execution needs at least one ready non-Claude provider, but ordinary Claude-only commands still work without one. If none reports ok, stop the parallel workflow, direct the user to /octo:setup, and do not simulate provider agreement by running one provider repeatedly. One ready provider can supply an additional perspective, but it is not multi-provider consensus.

The command writes ~/.claude-octopus/.provider-cache. Reuse it for up to one hour; after that, run detection again.

Double Diamond Workflow

Phase 1: PROBE (Discover)

Diverge then converge on understanding

Parallel research from 4 perspectives:

• Problem space analysis (constraints, requirements, needs)
• Existing solutions research (what worked, what failed)
• Edge cases exploration (potential challenges)
• Technical feasibility (prerequisites, dependencies)

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe "What are the best approaches for real-time notifications?"

Phase 2: GRASP (Define)

Build consensus on the problem

Multi-tentacled problem definition:

• Core problem statement
• Success criteria
• Constraints and boundaries

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grasp "Define requirements for notification system" --context probe-synthesis-*.md

Phase 3: TANGLE (Develop)

Diverge with multiple solutions

Enhanced map-reduce with validation:

• Task decomposition via LLM
• Parallel execution across agents
• Quality gate (75% success threshold)

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh tangle "Implement notification service" --context grasp-consensus-*.md

Phase 4: INK (Deliver)

Converge to validated delivery

Pre-delivery validation:

• Quality gate verification
• Result synthesis
• Final deliverable generation

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh ink "Deliver notification system" --context tangle-validation-*.md

Full Workflow: EMBRACE

Run all 4 phases sequentially with automatic context passing:

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh embrace "Create a complete user dashboard feature"

Crossfire: Adversarial Cross-Model Review

Different models have different blind spots. Crossfire commands force models to critique each other's work, catching more issues than single-model review.

GRAPPLE - Adversarial Debate

Two tentacles wrestling until consensus

Available providers each propose solutions, then critique each other's work. A synthesis determines the winner.

┌─────────────┐     ┌─────────────┐
│   Codex     │     │ Antigravity │
│ (Proposer)  │     │ (Proposer)  │
└──────┬──────┘     └──────┬──────┘
       │                   │
       ▼                   ▼
┌─────────────┐     ┌─────────────┐
│ PROPOSAL A  │ ←─→ │ PROPOSAL B  │
└──────┬──────┘     └──────┬──────┘
       │                   │
       ▼                   ▼
┌─────────────┐     ┌─────────────┐
│ Antigravity │     │   Codex     │
│ (Critic)    │     │  (Critic)   │
└──────┬──────┘     └──────┬──────┘
       │                   │
       └─────────┬─────────┘
                 ▼
       ┌─────────────────┐
       │   SYNTHESIS     │
       │ (Winner + Fix)  │
       └─────────────────┘

# Basic grapple
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple "implement password reset API"

# Grapple with security principles
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles security "implement JWT authentication"

# Grapple with performance principles
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles performance "optimize database queries"

SQUEEZE - Red Team Security Review

Octopus squeezes prey to test for weaknesses

Blue Team (Codex) implements secure code. Red Team (Antigravity) attacks to find vulnerabilities. Then remediation and validation.

Phase 1: Blue Team implements secure solution
Phase 2: Red Team finds vulnerabilities
Phase 3: Remediation fixes all issues
Phase 4: Validation verifies all fixed

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh squeeze "implement user login form"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh squeeze "review auth.ts for vulnerabilities"

Constitutional Principles

Grapple supports domain-specific critique principles:

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles security "implement password reset"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles performance "optimize search API"
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grapple --principles maintainability "refactor user service"

Smart Auto-Routing

The auto command detects intent keywords and routes to the appropriate workflow:

Examples:

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "research best practices for caching"     # -> probe
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "build the caching layer"                 # -> tangle + ink
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "review the cache implementation"         # -> ink
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "security audit the auth module"          # -> squeeze
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "have both models debate the API design"  # -> grapple
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "fix the cache invalidation bug"          # -> codex

Quality Gates

The tangle phase enforces quality gates:

Command Reference

Double Diamond Commands

Crossfire Commands (Adversarial Review)

Classic Orchestration Commands

Options

Agent Selection (Premium Defaults)

Provider-Aware Routing (v4.8)

Claude Octopus now intelligently routes tasks based on your subscription tiers and costs.

Provider Subscription Tiers

Cost Optimization Strategies

Example: If your Google seat includes Antigravity access, the system can prefer AGY for analysis without invoking the retired Gemini CLI.

Routing CLI Flags

# Force a specific provider
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh --provider agy auto "analyze code structure"

# Prefer cheapest option
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh --cost-first auto "research best practices"

# Prefer highest quality
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh --quality-first auto "complex refactoring task"

# OpenRouter routing variants
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh --openrouter-nitro auto "quick task"  # Fastest
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh --openrouter-floor auto "bulk task"   # Cheapest

Configuration

Provider tiers are configured during setup or via the providers config file:

# Run setup wizard (includes provider tier steps)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh setup

# View current provider status
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh status

Configuration file: ~/.claude-octopus/.providers-config

version: "2.0"
providers:
  codex:
    installed: true
    auth_method: "oauth"
    subscription_tier: "plus"    # free|plus|pro|api-only
    cost_tier: "low"             # free|low|medium|high|bundled|pay-per-use

  agy:
    installed: true
    auth_method: "oauth"
    subscription_tier: "google"     # service-managed Google access
    cost_tier: "bundled"

  openrouter:
    enabled: false
    routing_preference: "default"   # default|nitro|floor

  orcarouter:
    enabled: false

cost_optimization:
  strategy: "balanced"  # cost-first|quality-first|balanced

OpenRouter Fallback

OpenRouter provides 400+ models as a universal fallback when direct external CLIs are unavailable:

# Set up OpenRouter API key
export OPENROUTER_API_KEY="sk-or-..."

# Re-run setup to configure
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh setup

OrcaRouter Fallback

OrcaRouter provides a single gateway to many models as a universal fallback when direct external CLIs are unavailable:

# Set up OrcaRouter API key
export ORCAROUTER_API_KEY="sk-orca-..."

# Re-run setup to configure
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh setup

Workspace Structure

~/.claude-octopus/
├── results/
│   ├── probe-synthesis-*.md      # Research findings
│   ├── grasp-consensus-*.md      # Problem definitions
│   ├── tangle-validation-*.md    # Quality gate reports
│   └── delivery-*.md             # Final deliverables
├── logs/                         # Execution logs
├── plans/                        # Execution plan history
└── .gitignore

Example Workflows

Research-First Development

# 1. Explore the problem space
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe "Authentication patterns for microservices"

# 2. Define the approach (with probe context)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh grasp "OAuth2 with JWT for our API" \
  --context ~/.claude-octopus/results/probe-synthesis-*.md

# 3. Implement with validation
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh tangle "Implement OAuth2 authentication"

# 4. Deliver with quality checks
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh ink "Finalize auth implementation"

Quick Build (Auto-Routed)

# Auto-detects "build" intent -> runs tangle + ink
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "build a rate limiting middleware"

Full Feature Development

# All 4 phases in one command
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh embrace "Create a user notification system with email and push support"

Best Practices

1. Start with embrace for new features requiring exploration
2. Use probe alone when researching before committing to an approach
3. Use auto for smart routing based on your intent
4. Chain phases with --context for incremental workflows
5. Run preflight before long workflows to verify dependencies
6. Review quality gates in tangle output before proceeding to ink

Troubleshooting

Pre-flight check fails

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh preflight
# Verify: codex CLI, agy CLI, and task-relevant provider credentials

Quality gate failures

Tangle phase requires 75% success rate. If failing:

• Break task into smaller subtasks
• Increase timeout with -t 600
• Check individual agent logs in ~/.claude-octopus/logs/

Reset workspace

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh clean
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh init