Cyuneo Agent Monitor — Design skill for Claude Code
VS Code extension: see each Claude Code and Codex agent's status, current step and context usage in a terminal-style panel.
How to install Cyuneo Agent Monitor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open cyuneo/cyuneo-agent-monitor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cyuneo Agent Monitor does
VS Code extension: see each Claude Code and Codex agent's status, current step and context usage in a terminal-style panel. Reads local session logs only. Unofficial; not affiliated with Anthropic or OpenAI.
Alternatives in Design
- Brand Guidelines — Apply Anthropic's official brand colors and typography to artifacts 94.1k ★
- Deepclaude — Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend 2.3k ★
- Claude Design Card — Claude Code skill for generating design cards in 14 formats — platform covers, social sharing cards, and edito 461 ★
README
CYUNEO Agent Monitor
**English** · [简体中文](README.zh-CN.md) · [繁體中文](README.zh-TW.md) · [한국어](README.ko.md) · [日本語](README.ja.md)
See all your Claude Code and Codex chats in one place, next to your terminal: which agents are working, which ones need you, and how full each context is.
[**Install in VS Code**](https://vscode.dev/redirect?url=vscode:extension/cyuneo.cyuneo-agent-monitor) · [View on the Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=cyuneo.cyuneo-agent-monitor)
**Preview (0.3.1).** This is the first public version. Please report anything that looks wrong in [GitHub Issues](https://github.com/cyuneo/cyuneo-agent-monitor/issues).

Why I built it
Claude Code and Codex now run several agents at once: subagents, background agents, whole workflows. In VS Code, most of that work is invisible:
- You can't see who is doing what. The agent view only appears when you open it, so an agent waiting for your approval can sit there unnoticed.
- Context fills up quietly. You find out when auto-compact starts at a bad moment, or when a long chat starts forgetting things.
- The cache runs out while you're away. Come back after an hour and the next message re-reads the whole context at full price.
- Usage limits stop work halfway. Agents stop, and you have to notice, wait for the reset and restart them yourself.
What it does for you
- Every chat at a glance. A panel next to the terminal lists every open and recent chat with a status light. Click one to see its agents, the step each one is on, and its tokens and cost.
- Know when you're needed. A chat waiting for your approval or answer gets a magenta light. Finished and failed chats have their own colors, in the status bar to
Related Skills
CometixCode
An unofficial Rust reimplementation of Anthropic's Claude Code terminal UI, built on iocraft
Agent View
One VS Code panel for Claude Code & Codex: every chat with status, cost and subagents, live usage bars, unread
Pi Tasks
A pi extension that brings Claude Code-style task tracking and coordination to pi. Track multi-step work with
Gemini CLI Skillz
Gemini CLI extension for Anthropic-style Agent Skills via skillz MCP server
Design System Status
Show a plain-language summary of the current design system state — what's set up, what's not, and sensible nex
Sdd Status
Print the current GSD planning state (roadmap phases, active milestone, pending phase) for career-ops-ui.
Related Agents
Abtop
AI agent monitor for your terminal. Like btop++, but for AI coding agents. Supports Claude Code and Codex CLI.
Token Tracker
Logs token usage estimates for each agent run to .claude/token-stats.json. Call this after any agent completes
Dx Engineer
Use for the verdict output surface (human line, --json, truncation notices), CLI ergonomics, error message qua