scopes CLAUDE.md

scopes CLAUDE.md is an instructions file for coding agents from kamiazya/scopes. It costs 3,097 tokens per session, scanned A, original, Apache-2.0.

A project guide for Claude Code, an AI coding assistant, that points to the Scopes project's architecture, domain model, API, tests, common tasks, and current implementation status.

In plain words
What is it for?
Use it when adding features, running tests or builds, working with the project's MCP server, or finding the right architecture and reference documents.
Why use it?
It gives the assistant the project context and working rules in one place, reducing guesswork about where code belongs, how to test it, and which parts are unfinished.

Instructions file

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/kamiazya/scopes/claude-md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/scopes

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 scopes CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kamiazya/scopes/claude-md.svg)](https://agentmods.dev/instructions/kamiazya/scopes/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kamiazya/scopes/claude-md"><img src="https://agentmods.dev/badge/instructions/kamiazya/scopes/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,097 This file is loaded in full into every session.
When invoked 3,097 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 $0.03097 $0.03097
Opus 5 $0.01548 $0.01548
Sonnet 5 $0.00619 $0.00619
Haiku 4.5 $0.00310 $0.00310

Measured 4d ago against content hash 7520a293ef47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scopes 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 4d 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 · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - AI Context Engineering Hub

This file provides comprehensive context and guidance to Claude Code (claude.ai/code) when working with the Scopes project. It serves as the primary navigation hub for AI collaboration.

🗺️ Quick Navigation

Essential Documents

  • Project Architecture: @docs/explanation/clean-architecture.md
  • Domain Model: @docs/reference/domain-model/
  • API Reference: @docs/reference/api/
  • Testing Guide: @docs/guides/architecture-testing-guide.md

For Common Tasks

  • Adding Features: @docs/guides/use-case-style-guide.md
  • Running Tests: ./gradlew test or ./gradlew konsistTest
  • Building Project: ./gradlew build
  • MCP Server: @docs/reference/mcp-implementation-guide.md

Implementation Status

  • Working: Basic CRUD, Aliases, Aspects, Contexts (backend), MCP Server
  • 🚧 Partial: Context CLI commands, Complex aspect queries
  • Not Implemented: Focus management, Tree display, Status command
  • 📦 Infrastructure Only: Event Sourcing, Device Sync (no user features)

📂 Project Structure Map

scopes/
├── contexts/               # Bounded Contexts (DDD)
│   ├── scope-management/   # Core scope operations
│   ├── user-preferences/   # User settings
│   ├── device-synchronization/ # (Infrastructure only)
│   └── event-store/        # (Infrastructure only)
├── interfaces/
│   ├── cli/               # CLI commands implementation
│   └── mcp/               # MCP server (11 tools implemented)
├── platform/              # Cross-cutting concerns
│   ├── observability/     # Logging, metrics
│   └── application-commons/
├── apps/
│   ├── scopes/           # CLI application
│   └── scopesd/          # Daemon (skeleton only)
└── quality/
    └── konsist/          # Architecture tests

🎯 Project Overview

Scopes is a next-generation local-first task and project management tool designed for symbiotic collaboration between developers and AI assistants.

Vision

Create a unified, recursive task management system where AI and human developers work together seamlessly, eliminating context loss and maximizing productivity through intelligent workspace management.

Read the full file on GitHub · 334 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. 4d ago First seen · 334 lines · 3,097 tokens per session scan A 7520a293ef47

Subscribe to this mod's changes

scopes CLAUDE.md is an instructions file published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 3,097 tokens to every session, about $0.0155 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.