nagato-ai: Instructions file for Claude Code

CLAUDE.md

nagato-ai CLAUDE.md is an instructions file for Claude Code from kenshiro-o/nagato-ai. It costs 821 tokens per session, scanned A, original, MIT.

A project guide for Nagato-AI, a Python library for building AI agent systems with several model providers. It describes its agent architecture and commands for installation, formatting, linting, testing, and running individual tests.

In plain words
What is it for?
Use it to install dependencies, format or lint Python code, run the full test suite, debug tests, or test one file or function.
Why use it?
It gives developers the repository’s standard workflow and shows how agents, model providers, conversations, and tool calls are organized.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is kenshiro-o/nagato-ai's own configuration. It tells Claude Code how to work on nagato-ai 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 nagato-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kenshiro-o/nagato-ai. 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/kenshiro-o/nagato-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kenshiro-o/nagato-ai

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 nagato-ai CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kenshiro-o/nagato-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/kenshiro-o/nagato-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 821 This file is loaded in full into every session.
When invoked 821 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 $0.00821 $0.00821
Opus 5 $0.00411 $0.00411
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 10d ago against content hash fd15f7cf0142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nagato-ai 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 10d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 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.

Project Overview

Nagato-AI is a Python library for building multi-LLM AI agent systems. It supports OpenAI, Anthropic, Google Gemini, Groq, and DeepSeek models through a unified agent interface. Agents can be orchestrated via graphs (DAGs), chains (sequential pipelines), or mission/task runners.

Commands

# Install
uv sync

# Format (isort + Black, line-length 120)
make fmt

# Lint (pylint, threshold 6)
make lint

# Run all tests
make test

# Run tests with debug logging
make test-debug

# Run a single test file
uv run pytest tests/nagatoai_core/graph/test_graph.py

# Run a single test
uv run pytest tests/nagatoai_core/graph/test_graph.py::test_function_name

Architecture

Agents (nagatoai_core/agent/)

Abstract Agent base class with provider-specific implementations (OpenAI, Anthropic, Google, Groq, DeepSeek). Use create_agent() and get_agent_type() from factory.py to instantiate agents by model name. Each agent maintains conversation history and supports tool calling. message.py defines Exchange, Message, ToolCall, ToolResult.

Tools (nagatoai_core/tool/)

AbstractTool base class with a _run() method. Tools are registered in ToolRegistry which provides fuzzy name matching via Levenshtein distance. Tool providers (tool/provider/) generate LLM-specific schemas for each tool. Built-in tools live in tool/lib/ (audio, filesystem, human input, web scraping, video, time, Readwise).

Graphs (nagatoai_core/graph/)

DAG-based workflow execution. Graph manages nodes and edges with cycle detection. Node types: AgentNode, ToolNode, ToolNodeWithParamsConversion. Flow types compose nodes: SequentialFlow, ParallelFlow, ConditionalFlow, TransformerFlow, UnfoldFlow. Workflows can also be defined declaratively in XML via graph/plan/xml_parser.py. See graph/README.md for detailed graph documentation.

Read the full file on GitHub · 65 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. 10d ago First seen · 65 lines · 821 tokens per session scan A fd15f7cf0142

Subscribe to this mod's changes

nagato-ai CLAUDE.md is an instructions file published in the GitHub repository kenshiro-o/nagato-ai (119 stars, last pushed 4mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0041 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 2026-08-30.

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens