Scopeon — AI skill for Claude Code
AI context observability & optimization for Claude Code, Copilot CLI, Codex, Gemini — TUI dashboard, preset optimization, cost tracking, CI gates.
How to install Scopeon
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sorunokoe/Scopeon and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Scopeon does
AI context observability & optimization for Claude Code, Copilot CLI, Codex, Gemini — TUI dashboard, preset optimization, cost tracking, CI gates.
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Proxypal — A desktop app that lets you use your AI subscriptions (Claude, ChatGPT, Gemini, GitHub Copilot) with any codin 1.2k ★
- Openclaw Dashboard — 🔐 Secure, real-time monitoring dashboard for OpenClaw AI agents 654 ★
README
◈ ╔═╗╔═╗╔═╗╔═╗╔═╗╔═╗╔╗╔ ╚═╗║ ║ ║╠═╝║╣ ║ ║║║║ ╚═╝╚═╝╚═╝╩ ╚═╝╚═╝╝╚╝ AI Context Observability & Optimization for Claude Code, Copilot CLI, Codex, Gemini CLI
**The AI context observatory — for every coding agent, every token, every dollar. With one-click optimization presets.**
[](https://github.com/sorunokoe/Scopeon/actions/workflows/ci.yml) [](https://github.com/sorunokoe/Scopeon/releases) [](docs/licenses/LICENSE-MIT) [](https://blog.rust-lang.org/2025/05/15/Rust-1.88.0.html)
[**Install**](#installation) · [**Quick Start**](#quick-start) · [**Docs**](docs/) · [**Contributing**](#contributing)
*You fire up Claude Code and start building. An hour later: **"Context window full."** You have no idea what burned it — was it the MCP tools? The thinking budget? Yesterday's file edits? You're flying blind on a meter that costs real money. And your AI provider runs with default settings that may cost 10x more than needed.*
**Scopeon gives you the instrument panel — and the optimization controls.**
Why Scopeon?
| Without Scopeon | With Scopeon |
|---|---|
| "Why is this session so expensive?" | Turn-by-turn cost breakdown with waste signals |
| "Is the prompt cache actually working?" | Hit-rate gauge, USD saved, optimization suggestions |
| "How close am I to the context limit?" | Real-time fill bar + "~12 turns remaining" prediction |
| "Which project costs the most?" | Per-project / per-branch cost breakdown |
| "What did the agent actually call?" | MCP & Skills tree — every server, tool |
Related Skills
Sidekick Agent Hub
See what your AI coding agent is doing. Multi-provider assistant & session monitor for VS Code and the termina
Devie AI Quota Tracker
Dashboard + macOS menu bar for tracking AI subscription quotas in one place (Claude Code, Codex, Gemini CLI, G
Coding Agent Usage Tracker
Single CLI to monitor LLM provider usage across Codex, Claude, Gemini, Cursor, and Copilot: remaining quota, r
Openclaw Claude Bridge
HTTP bridge powering OpenClaw's AI agents via Claude Code CLI — manages persistent sessions, auto-resume, exte
Nomoreide
AI-native service workbench: MCP server + shared daemon for Claude Code, Codex, and Gemini. CLI, TUI, and web
Agent Optimization
Live token monitor for Claude Code & Codex sessions — cost tracking, optimization analysis, LLM-powered sugges
Related Agents
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
Review UI
gleanery の端末の画面(gleanery dashboard、server/src/tui/)と CLI の出力の変更を、機械で判定できない面から確かめる独立レビュアー。server/src/tui/ か ser
Consult Agent
Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from