search-docs: Instructions file for Codex

AGENTS.md

search-docs AGENTS.md is an instructions file for Codex, OpenCode from otolab/search-docs. It costs 2,614 tokens per session, scanned A, original, MIT.

A repository guide for search-docs, a local-document search system that finds relevant text using vector search. Vector search compares the meaning of text, rather than only matching exact words.

In plain words
What is it for?
Use it when working on the search-docs codebase, its MCP or HTTP servers, document storage, indexing, embedding service, or related architecture.
Why use it?
It explains the project structure and operating model, so an agent can understand how the MCP server, document watcher, database, and embedding service fit together.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code.

This is otolab/search-docs's own configuration. It tells Codex and OpenCode how to work on search-docs 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 search-docs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to otolab/search-docs. 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/otolab/search-docs/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/otolab/search-docs

Made for: Codex, OpenCode.

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 search-docs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/otolab/search-docs/agents-md/github.svg)](https://agentmods.dev/instructions/otolab/search-docs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/otolab/search-docs/agents-md"><img src="https://agentmods.dev/badge/instructions/otolab/search-docs/agents-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 search-docs AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/otolab/search-docs/agents-md"><img src="https://agentmods.dev/badge/instructions/otolab/search-docs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,614 This file is loaded in full into every session.
When invoked 2,614 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 $0.02614 $0.02614
Opus 5.5 $0.01046 $0.01046
Sonnet 5.5 $0.00523 $0.00523
Haiku 4.5 $0.00261 $0.00261

Measured 23d ago against content hash 89aaa8c9be76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

search-docs AGENTS.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 23d 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.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🐕️ search-docs - Claude Code用プロジェクトガイド

プロジェクト概要

search-docsは、ローカル文書のVector検索システムです。プロジェクト毎に起動される検索サーバと、複数のクライアント形式で構成されています。

アーキテクチャ

プロセス構成

MCP Server (stdio)
  ├─ in-process: SearchDocsServer (read-only)
  ├─ in-process: WatcherProcess (write, heartbeat調停)
  ├─ in-process: DBEngine
  └─ subprocess: Embedding Server (stateless, 共有可能)
           │
           ▼
       LanceDB (共有ストレージ)

詳細: docs/client-server-architecture.md

アーキテクチャ構成

search-docsは以下の構成で動作します:

  1. MCP Server (packages/mcp-server/)

    • Claude Code統合、stdio通信
    • SearchDocsServerをin-processで直接保持(HTTPデーモン不要)
    • SearchDocsServiceインターフェイス経由でサーバ機能を利用
  2. JSON-RPC Server (packages/server/src/bin/server.ts)

    • search-docs server start コマンドでHTTPサーバとしてexposeする用途
    • WatcherProcess内蔵、Heartbeat調停で複数インスタンス間を自動協調
    • MCPサーバからは使用されない(外部クライアント向け)
  3. Embedding Server (packages/db-engine/src/python/embedding_server.py)

    • Ollama API互換のHTTP埋め込みサーバ
    • 複数プロセスから共有利用可能

詳細: docs/architecture.md

データモデル

  • DocumentStorage: 文書の永続化(パス形式のキー)
  • SearchIndex: Vector検索(LanceDB + Ruri Embedding)
  • Section: 分割データ(depth 0-3、トークン数ベース)

詳細: docs/data-model.md

システム全体

  • TypeScript: サーバ、クライアント、CLI、MCP Server
  • Python: LanceDB操作、Vector化(uvで管理)
  • pnpm: モノレポ管理

詳細: docs/architecture.md

プロジェクト構造

search-docs/
├── packages/              # モノレポパッケージ
│   ├── server/           # 検索サーバ
│   ├── client/           # クライアントライブラリ
│   ├── cli/              # CLIツール
│   ├── mcp-server/       # Claude Code統合
│   ├── storage/          # DocumentStorage
│   └── db-engine/        # LanceDB Pythonラッパー
├── docker/               # Docker関連
│   ├── entrypoint.sh    # モード分岐(MCP/Embedding、簡素化済み)
│   └── compose.yaml     # 共有Embeddingサーバ構成例
├── docs/                 # ドキュメント
├── prompts/              # Claude Code設定
│   └── tasks/           # 作業メモ・計画
├── Dockerfile            # マルチステージビルド
├── pyproject.toml        # Python依存関係(uv)
├── pnpm-workspace.yaml   # pnpmワークスペース
└── package.json          # ルートパッケージ

Read the full file on GitHub · 232 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. 23d ago Changed · +6 lines · +102 tokens per session 89aaa8c9be76
  2. 2mo ago First seen · 226 lines · 2,512 tokens per session scan A a1fbed33b923

Subscribe to this mod's changes

search-docs AGENTS.md is an instructions file published in the GitHub repository otolab/search-docs (1 stars, last pushed 24d ago), licensed MIT. It adds 2,614 tokens to every session, about $0.0105 per session on Opus 5.5. 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

search-docs AGENTS.md compared with instructions from other repositories

search-docs AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
search-docs AGENTS.mdotolab/search-docsInstructions file124d agoMITA2,614Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode