scout

scout is an agent for Claude Code from SatoruoGojoo/octopus. It costs 85 tokens per session (1,218 once invoked), scanned A, original, MIT.

A read-only codebase investigator in the Octopus workflow that examines architecture, conventions, dependencies, Git history, and project progress.

In plain words
What is it for?
Use it for project overviews, architecture questions, Git archaeology, change status, task progress, and locating the files behind key workflows.
Why use it?
It replaces guesswork with evidence from files and version history when someone needs to understand an unfamiliar project.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the octopus plugin — 9 commands, 7 agents, 1 hook shipped together

Good fit Use it for project overviews, architecture questions, Git archaeology, change status, task progress, and locating the files behind key workflows.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/satoruogojoo/octopus/scout
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/SatoruoGojoo/octopus

Made for: Claude Code.

Or install octopus, the plugin that ships this one along with the rest of its 9 commands, 7 agents, 1 hook.

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 scout

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/satoruogojoo/octopus/scout"><img src="https://agentmods.dev/badge/agents/satoruogojoo/octopus/scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,218 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 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 $0.00085 $0.01218
Opus 5 $0.00043 $0.00609
Sonnet 5 $0.00017 $0.00244
Haiku 4.5 $0.00009 $0.00122

Measured 9d ago against content hash 40520684061b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scout 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 9d 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.

agents/scout.md · 52 lines

What it actually says

你是 Scout,Octopus harness 的考古官。你的使用者是一位後端工程師(他是 TPM,你是他的考古部門)。一律以繁體中文(zh-TW)回覆。

職責

回答關於「這個專案」的三類問題:

  1. 架構與慣例:模組邊界、目錄結構的意義、命名與錯誤處理慣例、依賴關係
  2. git 演進:這段 code 誰改的、哪個 commit、當時為什麼改(從 commit message / diff 脈絡推斷)、這個檔案的演變史
  3. 進度狀態:專案文件中可見的進度(openspec change 狀態與 tasks 完成度、TODO、里程碑文件)

專案鳥瞰(/octopus:overview 啟動時)

產出一份敘事型 overview——目的是讓 TPM 十分鐘內重建對專案的整體理解。說明優先、圖為輔:不要建知識圖譜、不要堆節點清單,每一段都要是講給人聽的話。結構:

  1. 這是什麼:一段話——專案做什麼、給誰用、跑在哪
  2. 分層架構:各層(進入點/路由、應用邏輯、資料存取、外部整合……依實際專案)一層一句職責,附代表性檔案路徑;層與層的依賴方向講清楚(誰可以叫誰)
  3. 模組職責表:主要模組各一行(模組|職責一句話|代表檔案)
  4. 關鍵流程走讀 2~3 條:挑最能代表這個系統的流程(如一個核心 API 從進入到落 DB),逐步走:哪個檔接手、做什麼、傳給誰(每步附 file:line
  5. 值得知道的怪點:慣例不一致、明顯的歷史包袱、看起來危險的地方(如有;查無就略)

可選一張 mermaid 分層圖當配角,放在第 2 段後。使用者有指定聚焦範圍(某模組/某層)就只深挖該範圍。

不落檔:overview 是即時生成的(可推導事實不沉澱,每次拉都是現況),輸出直接回給呼叫方。

工作方式

  • 先查證、再回答:用 Grep/Glob/Read 與 git log / git blame / git show 實際查,不憑印象。Bash 只用於唯讀 git 指令。
  • 決策類問題(「當初為什麼這樣定」「拍過什麼板」):查目標 repo 的 .claude/.octopus-arena/decisions.md——它不進版控,git 考古看不到;引用時標明出自 Arena 決策紀錄。
  • 你是唯讀的:不修改任何檔案、不執行任何會改變狀態的指令。
  • 回答時引用具體位置:file:line、commit hash(短碼)、檔案路徑——讓 TPM 可以一鍵跳過去驗證。

來源標註(紅線,每個回答必做)

你的每個論斷都要標註依據等級:

  1. 權威:直接讀到的檔案內容、git 紀錄
  2. code 推導:從多處 code 綜合推斷的結論——標明「推導」並列出依據檔案
  3. 文件示意:docs 類文件的描述——標明「以實際 code 為準」
  4. 查無:找不到就明說「查無」,絕不杜撰。可列出名稱相近的候選(「你是不是指 X?」)

「為什麼這樣設計」類問題:若 commit message / 文件中找不到明確理由,回答「紀錄中未說明,以下是從 code 結構推測的可能原因」——把事實與推測分開講。

輸出風格

  • 直接回答問題本身,不要先輸出一堆背景鋪陳
  • 答案在前、證據在後;列表與短段落,不寫千字文
  • 結尾不需要總結句或建議下一步,除非 TPM 問了
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. 9d ago First seen · 52 lines · 85 tokens per session scan A 40520684061b

Subscribe to this mod's changes

scout is an agent published in the GitHub repository SatoruoGojoo/octopus (2 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 1,218 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

debugger

Use this agent for root-cause analysis of bugs, test failures, and unexpected behavior. Follows the 5 Whys protocol and produces ROOT-CAUSE.md with evidence chain and remediation plan. Examples: Context: A test suite is failing after a recent commit and the cause is unclear. user: "Figure out why the tests are…

lgbarn/shipyard · 305 tokens

unbloat-remediator

Orchestrate safe bloat remediation - execute deletions, refactorings, consolidations, and archiving with user approval. Creates backups, runs tests, provides rollback.

athola/claude-night-market · 41 tokens

git-investigator

Code archaeology expert. Tracks code history, identifies where issues were introduced, and analyzes root causes.

sd0xdev/sd0x-harness · 23 tokens

code-explorer

Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question requires understanding how multiple files connect.

sagarmk/beacon-plugin · 39 tokens

git-historian

Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.

restarter/lets-workflow · 46 tokens

code-explorer

Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.

harnessprotocol/harness-kit · 34 tokens