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.
npx agentmods add instructions/kamiazya/scopes/claude-mdgit clone --depth 1 https://github.com/kamiazya/scopesWrote 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.
[](https://agentmods.dev/instructions/kamiazya/scopes/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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 testor./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.
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.
- 4d ago First seen · 334 lines · 3,097 tokens per session scan A 7520a293ef47
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.
Other instructions, from other repositories
zscaler-mcp-server CLAUDE.md
Instructions for zscaler/zscaler-mcp-server, covering zscaler mcp server, architecture overview, core components, request flow and service architecture.
zscaler-mcp-server GEMINI.md
Instructions for zscaler/zscaler-mcp-server, covering zscaler mcp server, tool naming & discovery, critical gotchas, write operations — safety rules and zdx filtering.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.