From octo
Triggers multi-AI orchestration to build solutions via external providers, generates multiple code implementations, and runs quality gates.
npx claudepluginhub nyldn/claude-octopus --plugin octocommands/# Develop - Development Phase ๐ ๏ธ ## ๐ค INSTRUCTIONS FOR CLAUDE ### MANDATORY COMPLIANCE โ DO NOT SKIP **When the user explicitly invokes `/octo:develop`, you MUST execute the structured workflow below.** You are PROHIBITED from doing the task directly, skipping the development phase with quality gates, or deciding the task is "too simple" for this workflow. The user chose this command deliberately โ respect that choice. ### EXECUTION MECHANISM โ NON-NEGOTIABLE **You MUST execute this command by invoking the corresponding skill via the Skill tool. You are PROHIBITED from:** - โ Using t...
/developBuilds features via multi-phase Research, Plan, Implement, Review & Commit workflow with confidence scoring, validation gates, tests, and conventional commits.
/developFetches next ready_to_develop ticket from board and autonomously implements it: create branch, code, build check, reviews, docs, ship without stopping.
/developRuns 6-phase SDLC pipeline (Discovery to Summary) for feature development, producing plans, code, and summaries. Supports --plan-only, --auto, resume from @path, and --verify-arch/impl flags.
/developPlan and execute a mathematical development with ticket-based project management
/developImplement solution with parallel developers and 4-specialist review team
When the user explicitly invokes /octo:develop, you MUST execute the structured workflow below. You are PROHIBITED from doing the task directly, skipping the development phase with quality gates, or deciding the task is "too simple" for this workflow. The user chose this command deliberately โ respect that choice.
You MUST execute this command by invoking the corresponding skill via the Skill tool. You are PROHIBITED from:
orchestrate.sh calls because "I can do this faster directly"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:develop <arguments>):
โ CORRECT - Use the Skill tool:
Skill(skill: "octo:develop", args: "<user's arguments>")
โ INCORRECT:
Skill(skill: "flow-develop", ...) โ Wrong! Internal skill name, not resolvable by Skill tool
Task(subagent_type: "octo:develop", ...) โ Wrong! This is a skill, not an agent type
CRITICAL: After the skill completes, you MUST ask the user what to do next. Do NOT end the session silently.
AskUserQuestion({
questions: [
{
question: "Development phase complete. What would you like to do next?",
header: "Next Steps",
multiSelect: false,
options: [
{label: "Move to Deliver phase", description: "Validate and review the implementation (/octo:deliver)"},
{label: "Iterate on the implementation", description: "Make adjustments or handle edge cases"},
{label: "Run quality gates again", description: "Re-validate with updated code"},
{label: "Export the implementation", description: "Save a summary of what was built"},
{label: "Done for now", description: "I have what I need"}
]
}
]
})
Auto-loads the develop skill for the implementation phase.
Just use natural language:
"Build a user authentication system"
"Implement OAuth 2.0 flow"
"Create a caching layer for the API"
The Develop phase of the Double Diamond methodology (divergent thinking for solutions):
Use develop when you need:
Develop is phase 3 of 4 in the embrace (full) workflow:
To run all 4 phases: /octo:embrace