Claude Octopus is an orchestration project that sends research, design, and coding tasks to Claude Code and other AI model providers so their results can be compared. Developers use it for multi-model work, disagreement detection, reviews, persistent context, and an optional workflow that moves from discovery through delivery. The catalogue entries are its commands, skills, agents, instructions, hooks, plugins, and settings.
Borrowing it
Nothing to install: this file belongs to nyldn/claude-octopus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nyldn/claude-octopus/main/CLAUDE.mdgit clone --depth 1 https://github.com/nyldn/claude-octopusWrote 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.
[](https://agentmods.dev/instructions/nyldn/claude-octopus/claude-md)<a href="https://agentmods.dev/instructions/nyldn/claude-octopus/claude-md"><img src="https://agentmods.dev/badge/instructions/nyldn/claude-octopus/claude-md/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.
<a href="https://agentmods.dev/instructions/nyldn/claude-octopus/claude-md"><img src="https://agentmods.dev/badge/instructions/nyldn/claude-octopus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04900 | $0.04900 |
| Opus 5.5 | $0.01960 | $0.01960 |
| Sonnet 5.5 | $0.00980 | $0.00980 |
| Haiku 4.5 | $0.00490 | $0.00490 |
Grade B, and why
claude-octopus CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
echo "Progress: 50%" > ~/.claude/scratchpad/$(cat ~/.claude/session-id)/phase1-progress.md How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Octopus - System Instructions
Note: This file provides context when working directly in the claude-octopus repository. For deployed plugins, visual indicator instructions are embedded in each skill file (flow-discover.md, flow-define.md, flow-develop.md, flow-deliver.md, skill-debate.md).
Visual Indicators (MANDATORY)
When executing Claude Octopus workflows, you MUST display visual indicators so users know which AI providers are active and what costs they're incurring.
Indicator Reference
| Indicator | Meaning | Cost Source |
|---|---|---|
| 🐙 | Claude Octopus multi-AI mode active | Multiple APIs |
| 🔴 | Codex CLI executing | User's OPENAI_API_KEY |
| 🧭 | Antigravity CLI executing | User's Antigravity access/subscription |
| 🟣 | Perplexity Sonar web search | User's PERPLEXITY_API_KEY |
| 🔵 | Claude subagent processing | Included with Claude Code |
When to Display Indicators
Display indicators when:
- Invoking any
/octo:command - Running
orchestrate.shwith any workflow (probe, grasp, tangle, ink, embrace, etc.) - User triggers workflow with "octo" prefix ("octo research X", "octo build Y")
- Executing multi-provider operations
Provider emoji are required in status banners, provider rows, compact banners, and result attribution labels. Narrative prose may use provider names without emoji.
Required Output Format
Before starting a workflow, output this banner:
🐙 **CLAUDE OCTOPUS ACTIVATED** - [Workflow Type]
[Phase Emoji] [Phase Name]: [Brief description of what's happening]
Providers:
🔴 Codex CLI - [Provider's role in this workflow]
🧭 Antigravity CLI - [Provider's role in this workflow]
🔵 Claude - [Your role in this workflow]
Phase emojis by workflow:
- 🔍 Discover/Probe - Research and exploration
- 🎯 Define/Grasp - Requirements and scope
- 🛠️ Develop/Tangle - Implementation
- ✅ Deliver/Ink - Validation and review
- 🐙 Debate - Multi-AI deliberation
- 🐙 Embrace - Full 4-phase workflow
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.
- 20d ago Changed · +25 tokens per session 9609c046de3d
- 29d ago Changed · +1 lines · +89 tokens per session c6e4abb63b13
- 1mo ago Changed · -51 lines · -634 tokens per session 7e619ca98cc7
- 1mo ago Changed · +7 lines · +228 tokens per session 24fd3fafaa39
- 1mo ago First seen · 417 lines · 5,192 tokens per session scan B d63a37e28df4
claude-octopus CLAUDE.md is an instructions file published in the GitHub repository nyldn/claude-octopus (4,285 stars, last pushed today), licensed MIT. It adds 4,900 tokens to every session, about $0.0196 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.