tsumugi AGENTS.md

A set of project instructions for developing tsumugi, including where code belongs, which existing utilities to reuse, and how its layers may depend on one another.

In plain words
What is it for?
Use it before implementing tsumugi features to follow the project’s directory, dependency, identifier, database, embedding, and search rules.
Why use it?
It prevents new code from being placed in the wrong part of the project or duplicating existing ID, database, embedding, and search logic.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/archfill/tsumugi/agents-md
Clone the repo
git clone --depth 1 https://github.com/archfill/tsumugi

Made for: Codex, OpenCode.

Per session 1,844 This file is loaded in full into every session.
When invoked 1,844 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01844 $0.01844
Opus 5 $0.00922 $0.00922
Sonnet 5 $0.00369 $0.00369
Haiku 4.5 $0.00184 $0.00184

Measured yesterday against content hash ccff415af410, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tsumugi 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 yesterday.

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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tsumugi — AI 開発ガイド(必読)

新規実装の前に必ず最初に読むこと。書く場所と再利用ルールを規定する。

ディレクトリ構造(書く場所のルール)

役割 何を書く
core/ ビジネスロジック(純粋) use case、検索アルゴリズム
data/ 永続化 Drizzle schema、repository
external/ 外部 I/O embeddingなどの非LLMアダプタ
interfaces/ 入力アダプタ MCP tool、REST handler、transport
lib/ 横断ユーティリティ id、errors、config

依存方向: interfaces → core → (data, external) → lib

逆方向の import 禁止(lib は循環依存禁止)。

詳細なファイル一覧はソースツリーを正とし、このガイドでは固定しない。新しい機能も上記の 依存方向と責務に従って配置する。external/llm/ や同等のserver-side LLM clientは作らない。

既存資産(再実装禁止)

ID 生成

lib/id.tsnewId(prefix) を必ず使う。

import { newId } from "../lib/id.js";
const id = newId("obs");

DB アクセス

data/repos/<entity>.ts 経由で行う。db を直接触らない(schema 定義 / migration ファイル以外)。

import { observationRepo } from "../../data/repos/observation.js";
await observationRepo.insert(row);

Embedder

external/embedding/singleton.tsgetEmbedder()

import { getEmbedder } from "../../external/embedding/singleton.js";
const embedding = await getEmbedder().embed(text);

検索

core/search/hybrid.tshybridSearch()。bigm/vector を直接呼ばない。

import { hybridSearch } from "../../core/search/hybrid.js";
const hits = await hybridSearch(input);

設定

lib/config.tsloadConfig()process.env 直接読み禁止。

エラー

lib/errors.tsTsumugiError 派生を使う。new Error() しない。

import { ValidationError, ExternalError } from "../../lib/errors.js";
throw new ValidationError("content is required");

採用パターン

Use case の形

  • ファイル: core/<domain>/<verb>.ts(例: core/observation/save.ts
  • 入口で Zod parse、出力は型付きオブジェクト
  • repo / external を直接 import で呼ぶ(DI コンテナ不要)
  • 副作用は use case 内で完結

Repository の形

  • ファイル: data/repos/<entity>.ts
  • export const xxxRepo = { method1, method2 } で集約
  • Drizzle の $inferSelect / $inferInsert で型を取り出す

Read the full file on GitHub · 171 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. yesterday First seen · 171 lines · 1,844 tokens per session scan A ccff415af410

Subscribe to this mod's changes

tsumugi AGENTS.md is an instructions file published in the GitHub repository archfill/tsumugi (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 1,844 tokens to every session, about $0.0092 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 instructions, from other repositories

ariadne AGENTS.md

Instructions for mclaut/ariadne, covering agents.md — ariadne, what this is, build / test / lint, architecture and runtime layout (not the repo).

mclaut/ariadne · 1,052 tokens

searching-apple-notes AGENTS.md

Instructions for yinanli1917-cloud/searching-apple-notes, covering codex project instructions, apple-notes-mcp, tech stack, directory structure and conventions.

yinanli1917-cloud/searching-apple-notes · 473 tokens

searching-apple-notes CLAUDE.md

Instructions for yinanli1917-cloud/searching-apple-notes, covering apple-notes-mcp, tech stack, directory structure, conventions and codex harness.

yinanli1917-cloud/searching-apple-notes · 529 tokens

kb-mcp-server CLAUDE.md

Claude Code instructions for code-runner-xx/kb-mcp-server, covering claude.md — kb-mcp-server 开发手册(规则书), 0. 项目铁律(必读), 1. 版本与技术选型(锁定), 2. 环境变量(.env.example) and 3. 目录结构.

code-runner-xx/kb-mcp-server · 1,706 tokens

Graft CLAUDE.md

Instructions for AEndrix03/Graft, a project described as: Local-first semantic cache for AI agents. A small C daemon + CLI that remembers what your agent learned across sessions. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop / ChatGPT via MCP. No LLM calls, no SaaS, no API key.

AEndrix03/Graft · not measured

ariadne CLAUDE.md

Instructions for mclaut/ariadne, covering claude.md — ariadne, what this is, build / test / lint, architecture and runtime layout (not the repo).

mclaut/ariadne · 1,053 tokens