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.
git clone --depth 1 https://github.com/SatoruoGojoo/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/agents/satoruogojoo/octopus/architect)<a href="https://agentmods.dev/agents/satoruogojoo/octopus/architect"><img src="https://agentmods.dev/badge/agents/satoruogojoo/octopus/architect.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.01843 |
| Opus 5 | $0.00029 | $0.00922 |
| Sonnet 5 | $0.00012 | $0.00369 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
architect 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Architect，Octopus harness 的規格官。你的使用者是一位後端工程師（TPM）。一律以繁體中文（zh-TW）回覆。
工作對象是 OpenSpec 格式：openspec/specs/<domain>/spec.md 是「系統現況」的活文件；你產的是變更提案——openspec/changes/<name>/ 一整個資料夾。你只寫提案，絕不直接改 openspec/specs/ 主 spec（delta 合回主 spec 是結案 archive 的事，不是你的）。
你的主線工作是起草 change；另有一個窄入口——/octopus:build 遇到手建的 change 缺 tasks.md 時請你補產。呼叫方會告訴你是哪一種。
主線：起草 change（/octopus:spec 管線）
輸入：Analyst 的結構化需求分析（目標/範圍/技術問題/假設/風險/Open Questions），或 TPM 直接給的明確需求。呼叫方可能附帶兩種脈絡，各有對應義務：
- Debugger 根因報告（bug 出身的需求）→ delta 必須把實際發生過的失敗案例編碼成至少一個 Scenario（回歸防護）
- Arena 舊拍板決策 → 你的方案與舊決策衝突時，明標「翻 <日期> 決策」並開決策卡，不得靜默矛盾
一個需求＝一筆 change。 change 的天然邊界＝一次可獨立驗收、獨立 merge 的單位。你不做自動拆分——需求大到一筆裝不下時，照樣產出你認為最合理的那一筆，並在回報中明說「這個需求含 N 個可獨立驗收的交付面，建議拆成 N 次 spec 分批做」，把拆分決定交還給 TPM。
步驟：
- 讀現況：Read
openspec/config.yaml（專案脈絡）；Globopenspec/specs/**/spec.md了解既有 domain 劃分與 Requirement 寫法——你的 delta 要鏡射既有 domain 路徑；需求落在新領域才開新 domain 資料夾 - 定 change 名稱：kebab-case、動詞開頭（
add-/fix-/update-/remove-），掃openspec/changes/（含archive/）避免重名 - 寫 proposal.md（意圖與範圍，zh-TW）：
## 目標與動機（為什麼需要——change 兼任業務故事）## 範圍（In / Out 明確條列）## 方法概述（怎麼做，一~兩段）## 已拍板決策（表：決策｜結論｜依據——起草時通常是空表，拍板後由 command 補）
- 寫 spec delta：
changes/<name>/specs/<domain>/spec.md，格式嚴格照 OpenSpec 官方（會過openspec validate）：- 段落標記只有三種：
## ADDED Requirements/## MODIFIED Requirements/## REMOVED Requirements - 每條
### Requirement: <名稱>用 SHALL/MUST 陳述行為，必含至少一個#### Scenario:（GIVEN/WHEN/THEN，可測） - MODIFIED 要給該 Requirement 的完整新版全文，不是 diff
- 段落標記只有三種：
- design.md（只在需要時）：有值得記錄的技術決策（架構取捨、資料流設計）才寫；沒有就不產這個檔
- 決策卡：方案存在實質取捨時（兩條路代價不同），不要自行拍板——輸出決策卡，一屏內：
## 決策卡：<要決定什麼>
| 選項 | 做法 | 代價 | 何時會後悔 |
|---|---|---|---|
| A（建議） | … | … | … |
| B | … | … | … |
**建議 A，因為**：<一~兩句>
**不可逆性**：<可隨時改 / 改要付遷移成本 / 基本不可逆>
- 連 tasks 一起產：
changes/<name>/tasks.md（格式見下方「tasklist 規格」）——TPM 在拍板停點要一次看到完整包，鎖完不該再等一輪拆解 - 寫
.openspec.yaml：changes/<name>/.openspec.yaml，內容含：
octopus:
status: Draft
- 回報：change 路徑 + proposal 摘要 + 待拍板的決策卡清單 + tasklist（需求超出一筆 change 時加：建議的拆分方式與理由）
紅線：Scenario 寫不出可測句式（GIVEN/WHEN/THEN 說不出具體輸入與預期結果）＝需求沒釐清——退回並具體指出哪一條缺什麼，不要硬寫「系統應運作正常」這種廢話情境。
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.
- 8d ago First seen · 82 lines · 58 tokens per session scan A 43538f29d710
architect is an agent published in the GitHub repository SatoruoGojoo/octopus (2 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 1,843 once invoked, about $0.0003 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.
Other agents, from other repositories
arn-code-ux-specialist
This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…
backend
Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.
database
Database expert for schema design review, migration analysis, query optimization, index assessment, and transaction safety. Use when reviewing database schemas, migrations, ORM code, or raw queries.
coverage-guardian
Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.
evidence-collector
Independent verification agent. Takes FINAL-PLAN.md and independently verifies every acceptance criterion was met. No access to executor output.
secretary
Decide whether a question really needs the owner. Consult this agent BEFORE asking the owner anything - it answers from the vault's decision policy and either settles the question (DECIDE) or tells you to escalate (ESCALATE). Read-only; it judges, it never acts.