octo-plan

octo-plan is a command for Claude Code from CES-Ltd/Lumi. It costs 26 tokens per session (4,091 once invoked), scanned A, original, MIT.

A command that turns a request into a written execution plan and saves it for review. It plans the work but does not perform it until you choose to execute it.

In plain words
What is it for?
Use it to capture requirements, organize a strategy, and save a plan for later execution with the related workflow command.
Why use it?
It gives you a chance to inspect and confirm the intended approach before any changes are made.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Codex; mentions Gemini CLI.

Part of the octo plugin — 10 skills, 47 commands shipped together

Good fit Use it to capture requirements, organize a strategy, and save a plan for later execution with the related workflow command.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ces-ltd/lumi/octo-plan
View source ↗ CES-Ltd/Lumi
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/CES-Ltd/Lumi

Made for: Claude Code.

Or install octo, the plugin that ships this one along with the rest of its 10 skills, 47 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for octo-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-plan/github.svg)](https://agentmods.dev/commands/ces-ltd/lumi/octo-plan)
Your own site
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-plan"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for octo-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-plan"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.04091
Opus 5 $0.00013 $0.02046
Sonnet 5 $0.00005 $0.00818
Haiku 4.5 $0.00003 $0.00409

Measured 10d ago against content hash a747480aa57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

octo-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

resources/seed/octopus/commands/octo-plan.md · 541 lines

How it starts

The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan - Intelligent Plan Builder

Creates strategic execution plans based on user intent. Saves plans for review and optional execution with /octo:embrace.

Key Behavior

  • Creates plans - Captures intent, analyzes requirements, generates weighted execution strategy
  • Saves to files - Stores plan (.claude/session-plan.md) and intent contract (.claude/session-intent.md)
  • Doesn't execute - Plans are saved for review; execution requires user confirmation
  • Optional execution - Can invoke /octo:embrace immediately or user can execute later

🤖 INSTRUCTIONS FOR CLAUDE

MANDATORY COMPLIANCE — DO NOT SKIP

When the user explicitly invokes /octo:plan, you MUST execute the structured planning workflow below. You are PROHIBITED from doing the task directly, skipping the intent capture questions, or deciding the task is "too simple" for structured planning. The user chose this command deliberately — respect that choice.


When the user invokes this command (e.g., /octo:plan <arguments>):

Step 1: Capture Comprehensive Intent

CRITICAL: Start by capturing the user's full intent using structured questions.

Ask 5 comprehensive questions to understand what they're trying to accomplish:

AskUserQuestion({
  questions: [
    {
      question: "What are you ultimately trying to accomplish?",
      header: "Goal",
      multiSelect: false,
      options: [
        {label: "Research a topic", description: "Gather information and options"},
        {label: "Make a decision", description: "Choose between alternatives"},
        {label: "Build something", description: "Create implementation or artifact"},
        {label: "Review/improve existing", description: "Assess and enhance what's there"},
        {label: "I'll describe it", description: "Let me write my own goal"}
      ]
    },
    {
      question: "How much do you already know about this?",
      header: "Knowledge",
      multiSelect: false,
      options: [
        {label: "Just starting", description: "Need to learn the landscape"},
        {label: "Some familiarity", description: "Know basics, need deeper dive"},
        {label: "Well-informed", description: "Know options, need execution"},
        {label: "Expert", description: "Just need implementation/validation"}
      ]
    },
    {
      question: "How clear is the scope?",
      header: "Clarity",
      multiSelect: false,
      options: [
        {label: "Vague idea", description: "Not sure exactly what I need"},
        {label: "General direction", description: "Know the area, need specifics"},
        {label: "Clear requirements", description: "Know what to build"},
        {label: "Fully specified", description: "Have detailed specifications"}
      ]
    },
    {
      question: "What defines success for you?",
      header: "Success",
      multiSelect: true,
      options: [
        {label: "Clear understanding", description: "I know what to do next"},
        {label: "Team alignment", description: "Everyone agrees on approach"},
        {label: "Working solution", description: "Implementation that functions"},
        {label: "Production-ready", description: "Fully tested and validated"}
      ]
    },
    {
      question: "What are your key constraints?",
      header: "Constraints",
      multiSelect: true,
      options: [
        {label: "Time pressure", description: "Need results quickly"},
        {label: "Must fit architecture", description: "Constrained by existing systems"},
        {label: "Team skill set", description: "Limited by team capabilities"},
        {label: "High stakes", description: "Significant risk if wrong"}
      ]
    }
  ]
})

Read the full file on GitHub · 541 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 541 lines · 26 tokens per session scan A a747480aa57c

Subscribe to this mod's changes

octo-plan is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 4,091 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.