A plugin for coordinating multiple language models and coding agents through planning, development, security review, and code review workflows.

Use it for multi-agent orchestration, PRD work, security framing, implementation, and code review with models such as Claude, GPT, Gemini, and Copilot.

It organizes work across different models and review stages when one coding agent or model is not enough for the task.

octo — Plugin for Claude Code by CES-Ltd: A plugin for coordinating multiple language models and coding…

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.

Claude Code

/plugin marketplace add CES-Ltd/Lumi

agentmods

npx agentmods add plugins/ces-ltd/lumi/octopus

Clone the repo

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

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 10 skills, 47 commands cost 1,130 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

octo 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 3d 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/.claude-plugin/plugin.json · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "octo",
  "version": "9.29.2",
  "description": "v9.29.2 \u2014 Model defaults refreshed: Opus 4.7 for planning/strategy/security-review, GPT-5.4 for code-review/implementation. New GPT-5.4 prompting guide. Set OCTOPUS_LEGACY_ROLES=1 to opt out. Run /octo:setup.",
  "author": {
    "name": "nyldn",
    "url": "https://github.com/nyldn"
  },
  "license": "MIT",
  "repository": "https://github.com/nyldn/claude-octopus",
  "homepage": "https://github.com/nyldn/claude-octopus",
  "keywords": [
    "multi-llm",
    "multi-agent",
    "orchestration",
    "claude-code-plugin",
    "double-diamond",
    "codex",
    "gemini",
    "copilot",
    "code-review",
    "automation"
  ],
  "skills": [
    "./.claude/skills/skill-prd.md",
    "./.claude/skills/skill-security-framing.md",
    "./.claude/skills/skill-content-pipeline.md",
    "./.claude/skills/skill-thought-partner.md",
    "./.claude/skills/skill-meta-prompt.md",
    "./.claude/skills/skill-native-escalation-routing.md",
    "./.claude/skills/skill-context-detection.md",
    "./.claude/skills/flow-discover.md",
    "./.claude/skills/flow-define.md",
    "./.claude/skills/flow-develop.md",
    "./.claude/skills/flow-deliver.md",
    "./.claude/skills/sys-configure.md",
    "./.claude/skills/skill-debate.md",
    "./.claude/skills/skill-code-review.md",
    "./.claude/skills/skill-architecture.md",
    "./.claude/skills/skill-security-audit.md",
    "./.claude/skills/skill-deep-research.md",
    "./.claude/skills/skill-writing-plans.md",
    "./.claude/skills/skill-tdd.md",
    "./.claude/skills/skill-debug.md",
    "./.claude/skills/skill-doc-delivery.md",
    "./.claude/skills/skill-finish-branch.md",
    "./.claude/skills/skill-parallel-agents.md",
    "./.claude/skills/skill-knowledge-work.md",
    "./.claude/skills/skill-task-management-v2.md",
    "./.claude/skills/skill-visual-feedback.md",
    "./.claude/skills/skill-decision-support.md",
    "./.claude/skills/skill-iterative-loop.md",
    "./.cla

Read the full file on GitHub · 128 lines

Contents

What it installs

The manifest is a name and a version. 10 skills, 47 commands travel with it, and installing the plugin installs all of them — 1,130 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

4 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 128 lines scan A 858408c7cb23

Subscribe to this mod's changes

octo is a plugin published in the GitHub repository CES-Ltd/Lumi (30 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agents Code review agent-framework agents ai ai-agents anthropic claude

octo

Getting it into your agent

Grade A, and why

Nothing flagged

How it starts

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

rn-dev-agent

humanizer

nextjs

claude-plugins-official marketplace

knowledge-work-plugins marketplace

ecc