octo-parallel

octo-parallel is a command for Claude Code from CES-Ltd/Lumi. It costs 15 tokens per session (478 once invoked), scanned A, a copy of octo-parallel, MIT.

A task-splitting command that divides a large, compound job into separate work packages handled by independent Claude processes. A monorepo or large project can therefore be worked on in parallel.

In plain words
What is it for?
Breaking down work such as authentication, online shops, or CI/CD pipelines into independent parts and delegating each part to its own process.
Why use it?
It helps separate unrelated parts of a complex task so they can be handled at the same time instead of in one long sequence.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

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

Good fit Breaking down work such as authentication, online shops, or CI/CD pipelines into independent parts and delegating each part to its own process.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ces-ltd/lumi/octo-parallel
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-parallel

README.md
[![agentmods](https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-parallel.svg)](https://agentmods.dev/commands/ces-ltd/lumi/octo-parallel)
Your own site
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-parallel"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-parallel.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 478 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 86% copy Near-identical to another mod 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 $0.00015 $0.00478
Opus 5 $0.00008 $0.00239
Sonnet 5 $0.00003 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured 8d ago against content hash a823f258c45c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

octo-parallel 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 8d 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.

Origin

This is a copy

86% identical to octo-parallel — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

resources/seed/octopus/commands/octo-parallel.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel - Team of Teams

INSTRUCTIONS FOR CLAUDE

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

CORRECT - Use the Skill tool:

Skill(skill: "octo:parallel", args: "<user's arguments>")

INCORRECT:

Skill(skill: "flow-parallel", ...)  ❌ Wrong! Internal skill name, not resolvable by Skill tool
Task(subagent_type: "octo:parallel", ...)  ❌ Wrong! This is a skill, not an agent type

Auto-loads the parallel skill for Team of Teams orchestration.

Quick Usage

Describe the compound task you want decomposed:

"Build a full authentication system with OAuth, RBAC, and audit logging"
"Create a complete e-commerce platform with payments, inventory, and shipping"
"Implement CI/CD pipeline with testing, linting, and deployment stages"

What Is Parallel?

Team of Teams orchestration — decomposes compound tasks into independent work packages and delegates each to a separate claude -p process. Each process loads the full Octopus plugin, giving every work package its own Double Diamond, agents, and quality gates.

Key architectural distinction: Task tool subagents don't load plugins. Independent claude -p processes do.

What You Get

  • Work Breakdown Structure (WBS) decomposition
  • Adversarial WBS cross-check to catch missed dependencies and scope overlaps before agents launch
  • Independent claude -p processes per work package
  • Full plugin capabilities in each worker
  • Parallel execution with staggered launch
  • Aggregated results with exit code verification

When To Use

  • Compound tasks with 3+ independent components
  • Tasks that would benefit from parallel execution
  • Projects where each component needs full AI capabilities
  • When you want isolated, non-interfering work streams

Natural Language Examples

"Parallel build auth system with OAuth, sessions, and RBAC"
"Team up on building a dashboard with charts, filters, and export"
"Decompose and parallelize the API migration across 5 services"

Read the full file on GitHub · 64 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. 8d ago First seen · 64 lines · 15 tokens per session scan A a823f258c45c

Subscribe to this mod's changes

octo-parallel is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 478 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to octo-parallel, differing in 9 lines, and is treated as a copy.