agentmods.dev

octopus: Instructions file for Claude Code

CLAUDE.md

octopus CLAUDE.md is an instructions file for Claude Code from SatoruoGojoo/octopus. It costs 3,497 tokens per session, scanned A, original, MIT.

A set of instructions for Octopus, a Claude Code plugin made from Markdown agents and slash commands. It runs work across other software projects and uses OpenSpec, a format for recording current system behavior and proposed changes.

In plain words
What is it for?
Use it when changing Octopus agents, commands, documentation, hooks, or version information. It helps keep the design documents, implementation, tests, and release records aligned.
Why use it?
It gives developers one source of truth for how the plugin should work and in what order to update its design and implementation. It also defines checks needed before releasing a new version.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is SatoruoGojoo/octopus's own configuration. It tells Claude Code how to work on octopus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything octopus configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 2repo changed 6d ago A scan 3,497 tokens original MIT
View source ↗ SatoruoGojoo/octopus
Reuse

Borrowing it

Nothing to install: this file belongs to SatoruoGojoo/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.

Copy the file
curl -O https://raw.githubusercontent.com/SatoruoGojoo/octopus/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SatoruoGojoo/octopus

Made for: Claude Code.

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 octopus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/satoruogojoo/octopus/claude-md/github.svg)](https://agentmods.dev/instructions/satoruogojoo/octopus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/satoruogojoo/octopus/claude-md"><img src="https://agentmods.dev/badge/instructions/satoruogojoo/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.

agentmods 80×15 button for octopus CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/satoruogojoo/octopus/claude-md"><img src="https://agentmods.dev/badge/instructions/satoruogojoo/octopus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,497 This file is loaded in full into every session.
When invoked 3,497 The same file — it is already loaded in full.
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 $0.03497 $0.03497
Opus 5 $0.01749 $0.01749
Sonnet 5 $0.00699 $0.00699
Haiku 4.5 $0.00350 $0.00350

Measured 6d ago against content hash dfc50f1ff7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

octopus CLAUDE.md 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 6d 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.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

這個 repo 是什麼

Octopus 是一個 Claude Code plugin（不是應用程式、沒有 build / runtime）。它本身就是 prompt 工程的成品：一組 markdown 定義的 agent 與 slash command，安裝後在「別的專案」裡用 /octopus:<指令> 驅動一個後端工作流 harness。唯一的可執行程式碼是兩支 hook，附回歸測試——專案根執行 node --test。

世界觀：一顆頭（使用者＝TPM）＋ 七隻腳（專家 agent）。TPM 只做三件不可替代的事——定義意圖、拍板取捨、驗收放行；agent 做其餘的實作、審查、考古、除錯。設計公理：harness 品質取決於三個 TPM 介面（需求進口、決策呈現、驗收出口）的品質，不是 agent 數量。

v0.5 起 spec 格式全面採用 OpenSpec（Fission-AI/OpenSpec）：目標 repo 的 openspec/specs/<domain>/ 是「系統現況」活文件，每筆工作是 openspec/changes/<name>/ 一筆 change；openspec CLI 是管線前置依賴（validate/archive）。

權威來源與修改順序

  • docs/Octopus-功能文件.md 是唯一權威設計文件。 所有 agent/command 行為都從它推導。
  • 改行為時：先改設計文件 → 再改 agents/ 或 commands/。實作與設計文件衝突時，以設計文件為準，回去修訂後再動實作。
  • 改完插件檔案後，在使用端的 Claude Code 對話執行 /reload-plugins 才會生效。

版更收尾紀律（版號提升前必跑）

  1. 本輪對話的設計決定全部落檔（設計文件→實作），不留在對話裡
  2. 反向對帳：本次動過的章節，設計文件宣稱的產物/行為 grep 驗證實作有對應
  3. 砍掉的東西補進 docs/退場紀錄.md（含理由）
  4. 三處同步：plugin.json 版號、設計文件版本標頭、本檔相關摘要

檔案結構與各檔職責

.claude-plugin/plugin.json      插件 manifest（name/version/keywords）
.claude-plugin/marketplace.json  marketplace 條目（source: "."）
commands/*.md                    slash command：主對話讀完後依步驟編排 agent
agents/*.md                      sub-agent persona：frontmatter 宣告 name + tools，body 是行為規格
hooks/hooks.json                 程式化守門註冊（PreToolUse；守門跟著管線走——只在 .octopus-arena/.run marker 有效（TTL 4h）時生效，subagent 也攔；marker 寫入後管線的每條出口都要刪，漏刪＝誤攔使用者日常 merge）
hooks/*.mjs                      hook 實作——慣例：純 node 零相依、fail-open、判斷邏輯 export evaluate() 可獨立驗證、訊息 zh-TW 附解法（見設計文件 §6.2）
hooks/*.test.mjs                 hook 判斷邏輯的回歸測試（node:test，零相依）——兌現「evaluate() 可獨立驗證」
docs/Octopus-功能文件.md          權威設計文件——只寫「現在的行為是什麼」
docs/退場紀錄.md                 被砍掉的方案與理由（非行為規格；加回任何一項前先讀）
docs/使用指南.md                 給使用者的操作手冊（情境→指令決策地圖＋術語表）
docs/實測指標.md                 跨專案指標彙整與讀數判準（數據源：各目標 repo Arena 的 metrics.md）
CHANGELOG.md                     各版本行為變更（版號提升時追加，README 只留 badge 連結）
LICENSE                          MIT 授權全文

Read the full file on GitHub · 111 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. 6d ago Changed · +30 tokens per session dfc50f1ff7d7
  2. 10d ago First seen · 111 lines · 3,467 tokens per session scan A 05a57fdf5cde

Subscribe to this mod's changes

octopus CLAUDE.md is an instructions file published in the GitHub repository SatoruoGojoo/octopus (2 stars, last pushed 9d ago), licensed MIT. It adds 3,497 tokens to every session, about $0.0175 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 2026-08-31.

Building agentsClaude CodeOpenSpecai-agentsclaude-code-pluginclaude-code-plugins-marketplacedeveloper-tools
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens