/define
Definition phase - Clarify and scope problems with multi-AI consensus
> /plugin marketplace add nyldn/claude-octopus
Command definition
define.mdcommand: define
disable-model-invocation: true
description: "Definition phase - Clarify and scope problems with multi-AI consensus"
aliases:
- grasp
- scope-phase
Define - Definition Phase 🎯
Load `skills/blocks/engineering-method-selection.md` from the installed plugin and apply only the methods relevant to this task. Preserve this entry point's execution contract and output format. Read referenced skills as instructions; do not invoke the current command recursively or add provider calls from a seat.
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY COMPLIANCE — DO NOT SKIP
**When the user explicitly invokes `/octo:define`, you MUST execute the structured workflow below.** You are PROHIBITED from doing the task directly, skipping the definition/scoping phase, or deciding the task is "too simple" for this workflow. The user chose this command deliberately — respect that choice.
EXECUTION MECHANISM — NON-NEGOTIABLE
**You MUST execute this command by reading and following the corresponding workflow source. You are PROHIBITED from:**
- ❌ Using the Agent tool to research/implement yourself instead of invoking the skill
- ❌ Using WebFetch/Read/Grep as a substitute for multi-provider dispatch
- ❌ Skipping `orchestrate.sh` calls because "I can do this faster directly"
- ❌ Implementing the task using only Claude-native tools (Agent, Write, Edit)
**Multi-LLM orchestration is the purpose of this command.** If you execute using only Claude, you've violated the command's contract.
---
When the user invokes this command (e.g., `/octo:define <arguments>`):
**✓ CORRECT - Read the explicit workflow source:**
Read ${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}}/.claude/skills/flow-define/SKILL.md, then execute it with <user's arguments>**✗ INCORRECT:**
Skill(skill: "flow-define", ...) ❌ Wrong! Octopus skills are model-invocation disabled
Task(subagent_type: "octo:define", ...) ❌ Wrong! This is a skill, not an agent type
Post-Completion — Interactive Next Steps
**CRITICAL: After the skill completes, you MUST ask the user what to do next. Do NOT end the session silently.**
AskUserQuestion({
questions: [
{
question: "Definition phase complete. What would you like to do next?",
header: "Next Steps",
multiSelect: false,
options: [
{label: "Move to Develop phase", description: "Start building based on defined requirements (/octo:develop)"},
{label: "Refine the definition", description: "Adjust scope or requirements"},
{label: "Run the full workflow", description: "Continue through all remaining phases (/octo:embrace)"},
{label: "Export the definition", description: "Save requirements as a document"},
{label: "Done for now", description: "I have what I need"}
]
}
]
})---
**Auto-loads the define skill for the definition/scoping phase.**
Quick Usage
Just use natural language:
"Define the requirements for user authentication"
"Clarify the scope of the caching feature"
"What exactly does the notification system need to do?"
What Is Define?
The **Define** phase of the Double Diamond methodology (convergent thinking):
- Clarify and scope problems using external CLI providers
- Technical requirements analysis
- Problem synthesis and requirement definition
What You Get
- Multi-AI consensus on requirements (Claude + Antigravity + Codex)
- Clear problem statement
- Scoped requirements
- Edge case identification
- Constraint analysis
When to Use Define
Use define when you need:
- **Requirements**: "Define the requirements for X"
- **Clarification**: "Clarify the scope of Y"
- **Scoping**: "What exactly does X need to do?"
- **Problem Understanding**: "Help me understand the problem with Y"
Part of the Full Workflow
Define is phase 2 of 4 in the embrace (full) workflow: 1. Discover 2. **Define** <- You are here 3. Develop 4. Deliver
To run all 4 phases: `/octo:embrace`
Read more
command: define disable-model-invocation: true description: "Definition phase - Clarify and scope problems with multi-AI consensus" aliases: - grasp - scope-phase
Define - Definition Phase 🎯
Load `skills/blocks/engineering-method-selection.md` from the installed plugin and apply only the methods relevant to this task. Preserve this entry point's execution contract and output format. Read referenced skills as instructions; do not invoke the current command recursively or add provider calls from a seat.
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY COMPLIANCE — DO NOT SKIP
**When the user explicitly invokes `/octo:define`, you MUST execute the structured workflow below.** You are PROHIBITED from doing the task directly, skipping the definition/scoping phase, or deciding the task is "too simple" for this workflow. The user chose this command deliberately — respect that choice.
EXECUTION MECHANISM — NON-NEGOTIABLE
**You MUST execute this command by reading and following the corresponding workflow source. You are PROHIBITED from:**
- ❌ Using the Agent tool to research/implement yourself instead of invoking the skill
- ❌ Using WebFetch/Read/Grep as a substitute for multi-provider dispatch
- ❌ Skipping `orchestrate.sh` calls because "I can do this faster directly"
- ❌ Implementing the task using only Claude-native tools (Agent, Write, Edit)
**Multi-LLM orchestration is the purpose of this command.** If you execute using only Claude, you've violated the command's contract.
---
When the user invokes this command (e.g., `/octo:define <arguments>`):
**✓ CORRECT - Read the explicit workflow source:**
Read ${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}}/.claude/skills/flow-define/SKILL.md, then execute it with <user's arguments>**✗ INCORRECT:**
Skill(skill: "flow-define", ...) ❌ Wrong! Octopus skills are model-invocation disabled Task(subagent_type: "octo:define", ...) ❌ Wrong! This is a skill, not an agent type
Post-Completion — Interactive Next Steps
**CRITICAL: After the skill completes, you MUST ask the user what to do next. Do NOT end the session silently.**
AskUserQuestion({
questions: [
{
question: "Definition phase complete. What would you like to do next?",
header: "Next Steps",
multiSelect: false,
options: [
{label: "Move to Develop phase", description: "Start building based on defined requirements (/octo:develop)"},
{label: "Refine the definition", description: "Adjust scope or requirements"},
{label: "Run the full workflow", description: "Continue through all remaining phases (/octo:embrace)"},
{label: "Export the definition", description: "Save requirements as a document"},
{label: "Done for now", description: "I have what I need"}
]
}
]
})---
**Auto-loads the define skill for the definition/scoping phase.**
Quick Usage
Just use natural language:
"Define the requirements for user authentication" "Clarify the scope of the caching feature" "What exactly does the notification system need to do?"
What Is Define?
The **Define** phase of the Double Diamond methodology (convergent thinking):
- Clarify and scope problems using external CLI providers
- Technical requirements analysis
- Problem synthesis and requirement definition
What You Get
- Multi-AI consensus on requirements (Claude + Antigravity + Codex)
- Clear problem statement
- Scoped requirements
- Edge case identification
- Constraint analysis
When to Use Define
Use define when you need:
- **Requirements**: "Define the requirements for X"
- **Clarification**: "Clarify the scope of Y"
- **Scoping**: "What exactly does X need to do?"
- **Problem Understanding**: "Help me understand the problem with Y"
Part of the Full Workflow
Define is phase 2 of 4 in the embrace (full) workflow: 1. Discover 2. **Define** <- You are here 3. Develop 4. Deliver
To run all 4 phases: `/octo:embrace`
Every AI model has blind spots. Claude Octopus supports twelve external provider integrations — Codex, Antigravity CLI, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OrcaRouter, OpenCode, Cursor CLI, Grok, and Kimi Code — alongside the built-in Claude Code
Other commands on octo.
More commands from other plugins.
setup
CommandOne-time setup after installing ARIS as a Claude Code plugin — registers the Codex reviewer MCP server from the plugin directory…
autoresearch
CommandAutonomous iteration loop: modify, verify, keep/discard against any metric
agent
Commandname: sc:agent description: SC Agent — session controller that orchestrates investigation, implementation, and review category:…

