Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Instruções da origem · Visualização somente leitura
name
skill-parallel-agents
disable-model-invocation
true
effort
high
description
Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work
trigger
PRIORITY TRIGGERS (always invoke immediately):
- "/octo:multi" (explicit command)
- "run this with all providers", "run with all providers"
- "I want multiple AI models to look at", "use all providers for"
- "get multiple perspectives on", "force multi-provider analysis"
EXPLICITLY USE (without asking user) when the user requests:
- Research, explore, investigate, or analyze topics (e.g., "octo research OAuth patterns", "octo analyze technical debt", "octo explore different approaches")
- Build, implement, create, or develop features (e.g., "octo build a login system", "octo implement caching", "octo create a dashboard")
- Review, validate, test, or check code quality (e.g., "octo review this code", "octo validate the API", "octo check for issues")
- Adversarial review, debate solutions, or red team security (e.g., "octo debate the design", "red team this auth code", "find security flaws")
- Full workflows from research to delivery (e.g., "create a complete notification feature")
DO NOT ask "do you want me to use the plugin?" - JUST USE IT.
The user installed this plugin to use it automatically!
NEVER use for:
- Built-in Claude Code commands (/plugin, /init, /help, /clear, /commit, /remember, etc.)
- Plugin management or Claude Code configuration
- Simple file operations, git commands, or basic terminal tasks
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.
Any other / command that isn't /parallel-agents or /octo:*
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
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:
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:
Provider
Cost per Query
What It Uses
🔴 Codex CLI
~$0.01-0.05
Your OPENAI_API_KEY
🧭 Antigravity CLI
Included with access/subscription
Antigravity CLI auth
🔵 Claude
Included
Claude Code subscription
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 (Automatic - Fast Detection)
IMPORTANT: Once you've determined this skill should activate (user asked to research, build, review, etc.), immediately run the provider detection below. DO NOT ask the user for permission - just check providers and proceed or show welcome message.
Step 1: Automatic Provider Detection
Silently run this fast detection script (completes in <1 second):
IMPORTANT - First Time Setup Detection:
If the detect-providers command shows both Codex and AGY are missing, this is likely a first-time user. Before showing error messages, provide a friendly welcome message:
"👋 Welcome to Claude Octopus! I see this is your first time using the plugin.
To get started, you need to install one AI provider (you don't need both):
Option 2: Google Antigravity CLI (best for analysis)
agy # complete the browser sign-in when prompted
Install agy from Google Antigravity first if it is not already present.
Once you've installed one provider, you can start using Claude Octopus by just talking naturally:
'Research OAuth authentication patterns'
'Build a user authentication system'
'Review this code for security issues'
Need guided setup? Run /octo:setup"
After showing this welcome message, STOP and wait for the user to set up a provider. Do not proceed with the original task until at least one provider is configured.
Expected output format:
Detecting Claude Code version...
CLAUDE_CODE_VERSION=2.1.9
CLAUDE_CODE_STATUS=ok
CLAUDE_CODE_MINIMUM=2.1.9
✓ Claude Code version: 2.1.9 (meets minimum 2.1.9)
Detecting providers...
CODEX_STATUS=ok
CODEX_AUTH=oauth
AGY_STATUS=ok
AGY_AUTH=none
Summary:
✓ Codex: Installed and authenticated (oauth)
⚠ Antigravity: Installed but not authenticated
Step 2: Route Based on Detection Results
Parse the output and route accordingly:
Scenario 0: Claude Code version is outdated (CRITICAL - Check First)
After installing one, run /octo:setup to verify everything works."
Scenario B: One provider working, one missing/partial
CODEX_STATUS=ok
CODEX_AUTH=oauth (or api-key)
AGY_STATUS=missing (or ok with AUTH=none)
Action: IMMEDIATELY proceed with the user's task using the available provider. No need to announce setup status - just execute the task. The user doesn't care about which provider you're using, they just want their task done.
Action: IMMEDIATELY proceed with the user's task using both providers for comprehensive results. No need to announce setup status - just execute the task.
Step 3: Graceful Degradation
If only ONE provider is available:
Automatically use that provider
Tasks that require multiple providers will adapt to use the single provider multiple times
Quality results are still achievable with one provider
You do NOT need both providers to proceed. One is sufficient for most tasks.
Step 4: Cache Results (Optional Optimization)
The detect-providers command writes results to ~/.claude-octopus/.provider-cache with a timestamp. This cache is valid for 1 hour.
If the cache exists and is fresh (<1 hour old), you can skip re-detection.
Step 5: Execute Task
Only proceed when at least ONE provider is available and authenticated. Multi-provider tasks will automatically adapt to available providers.
IMPORTANT: This detection is fast (~1 second) and non-blocking. Always verify provider availability before running octopus commands, but don't require BOTH providers - one is enough!
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)
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.
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"
The auto command detects intent keywords and routes to the appropriate workflow:
Keywords
Routes To
Phases
research, explore, investigate, analyze
probe
Discover
develop, dev, build, implement, create
tangle + ink
Develop + Deliver
qa, test, review, validate, check
ink
Deliver (quality focus)
security audit, red team, pentest
squeeze
Red Team
adversarial, cross-model, debate
grapple
Debate
(other coding keywords)
codex agent
Single agent
(other design keywords)
agy agent
Single agent
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:
Score
Status
Behavior
>= 90%
PASSED
Proceed to ink
75-89%
WARNING
Proceed with caution
< 75%
FAILED
Ink phase flags for review
Command Reference
Double Diamond Commands
Command
Phase
Description
probe <prompt>
Discover
Parallel research with AI synthesis
grasp <prompt>
Define
Consensus building on problem definition
tangle <prompt>
Develop
Enhanced map-reduce with quality gates
ink <prompt>
Deliver
Validation and final delivery
embrace <prompt>
All 4
Full Double Diamond workflow
preflight
-
Validate all dependencies
Crossfire Commands (Adversarial Review)
Command
Description
grapple <prompt>
Codex vs Antigravity debate until consensus
grapple --principles TYPE <prompt>
Debate with domain principles (security, performance, maintainability)
squeeze <prompt>
Red Team security review (Blue Team vs Red Team)
Classic Orchestration Commands
Command
Description
init
Initialize workspace
spawn <agent> <prompt>
Spawn single agent
auto <prompt>
Smart routing (Double Diamond or agent)
fan-out <prompt>
Send to multiple agents
map-reduce <prompt>
Decompose and parallelize
parallel [tasks.json]
Execute task file
status
Show running agents
kill [id|all]
Terminate agents
clean
Reset workspace
aggregate [filter]
Combine results
Options
Option
Default
Description
-p, --parallel
3
Max concurrent agents
-t, --timeout
300
Timeout per task (seconds)
-v, --verbose
false
Verbose logging
-n, --dry-run
false
Show without executing
--context <file>
-
Context from previous phase
Agent Selection (Premium Defaults)
Agent
Model
Best For
codex
gpt-5.6-sol
Frontier implementation and independent review
codex-standard
gpt-5.6-terra
Balanced implementation and review
codex-mini
gpt-5.6-luna
Quick fixes, simple tasks
agy
service-selected default
Deep analysis and external review
agy-research
service-selected default
Research-focused Antigravity seat
codex-review
gpt-5.6-sol
Code review mode
openrouter
Various
Universal fallback (400+ models)
orcarouter
Various
Universal fallback via OrcaRouter gateway
Provider-Aware Routing (v4.8)
Claude Octopus now intelligently routes tasks based on your subscription tiers and costs.
Provider Subscription Tiers
Provider
Tiers
Monthly Cost
Capabilities
Codex/OpenAI
Free, Plus, Pro, API
$0-200
code, chat, review
Antigravity
Google access/subscription
Included with access
code, analysis, external review
Claude
Pro, Max 5x, Max 20x, API
$20-200
code, chat, analysis, long-context
OpenRouter
Pay-per-use
Variable
400+ models, routing variants
OrcaRouter
Pay-per-use
Variable
Single gateway, namespaced model IDs
Cost Optimization Strategies
Strategy
Description
balanced (default)
Smart mix of cost and quality
cost-first
Prefer cheapest capable provider
quality-first
Prefer highest-tier provider
Example: If your Google seat includes Antigravity access, the system can prefer AGY for analysis without invoking the retired Gemini CLI.
Routing CLI Flags
# Force a specific provider${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
version:"2.0"providers:codex:installed:trueauth_method:"oauth"subscription_tier:"plus"# free|plus|pro|api-onlycost_tier:"low"# free|low|medium|high|bundled|pay-per-useagy:installed:trueauth_method:"oauth"subscription_tier:"google"# service-managed Google accesscost_tier:"bundled"openrouter:enabled:falserouting_preference:"default"# default|nitro|floororcarouter:enabled:falsecost_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 keyexport OPENROUTER_API_KEY="sk-or-..."# Re-run setup to configure${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh setup
OrcaRouter Fallback
OrcaRouter provides a single gateway to many models as a universal fallback when direct external CLIs are unavailable:
# Set up OrcaRouter API keyexport ORCAROUTER_API_KEY="sk-orca-..."# Re-run setup to configure${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
Start with embrace for new features requiring exploration
Use probe alone when researching before committing to an approach
Use auto for smart routing based on your intent
Chain phases with --context for incremental workflows
Run preflight before long workflows to verify dependencies
Review quality gates in tangle output before proceeding to ink