auto
Smart router - Single entry point with natural language intent detection
Delivery phase - Review, validate, and test with multi-AI quality assurance
> /plugin marketplace add nyldn/claude-octopusHow it fires
How this command gets triggered: by you, by Claude, or both.
/deliverContext preview
What this command does when you run it.
Delivery phase - Review, validate, and test with multi-AI quality assurance
command: deliver disable-model-invocation: true description: "Delivery phase - Review, validate, and test with multi-AI quality assurance" aliases: - ink - review-phase
**When the user explicitly invokes `/octo:deliver`, you MUST execute the structured workflow below.** You are PROHIBITED from doing the task directly, skipping the validation/review phase, or deciding the task is "too simple" for this workflow. The user chose this command deliberately — respect that choice.
**You MUST execute this command by reading and following the corresponding workflow source. You are PROHIBITED from:**
**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:deliver <arguments>`):
**✓ CORRECT - Read the explicit workflow source:**
Read ${HOME}/.claude-octopus/plugin/.claude/skills/flow-deliver/SKILL.md, then execute it with <user's arguments>**✗ INCORRECT:**
Skill(skill: "flow-deliver", ...) ❌ Wrong! Octopus skills are model-invocation disabled Task(subagent_type: "octo:deliver", ...) ❌ Wrong! This is a skill, not an agent type
**Before presenting results, launch two verification agents in parallel:**
Agent(model: "sonnet", subagent_type: "feature-dev:code-reviewer", run_in_background: true, description: "Code review: deliver phase", prompt: "Review code changes from this session. Check git diff. Report only high-confidence bugs, security issues, and convention violations.") Agent(model: "sonnet", run_in_background: true, description: "E2E test: deliver phase", prompt: "Run the project's test suite. Report tests passed/failed and any regressions.")
Include findings in the results below. Flag test failures or HIGH-confidence issues prominently.
**CRITICAL: After the skill completes, you MUST present review/test findings AND ask the user what to do next. Do NOT end the session silently.**
AskUserQuestion({
questions: [
{
question: "Delivery/validation phase complete. What would you like to do next?",
header: "Next Steps",
multiSelect: false,
options: [
{label: "Address findings", description: "Fix issues identified in the review"},
{label: "Run another review pass", description: "Re-validate after fixes"},
{label: "Ship it", description: "Findings are acceptable, proceed to deployment"},
{label: "Export the review", description: "Save validation results as a document"},
{label: "Done for now", description: "I have what I need"}
]
}
]
})---
**Auto-loads the deliver skill for the validation/review phase.**
Just use natural language:
"Review the authentication code for security" "Validate the caching implementation" "Test the notification system"
The **Deliver** phase of the Double Diamond methodology (convergent thinking):
Use deliver when you need:
Deliver is phase 4 of 4 in the embrace (full) workflow: 1. Discover 2. Define 3. Develop 4. **Deliver** <- You are here
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
Repo: nyldn/claude-octopus
Smart router - Single entry point with natural language intent detection
Start a creative thought partner brainstorming session
Switch Octopus model routing to the configured budget tier
[advanced] Activate destructive command warnings for the session
[advanced] Compatibility view of the deterministic Octopus usage report
Multi-LLM council for advice, decision support, implementation plans, and gated implementation