Agent Monitor: Track Token Usage and Cost for Codex and Claude Code Agents
Melvin Vivas · X video post · 2026-09-16 · 0:01 · 2,236 views · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity, AI Agents, Tool Use & MCP · Level: intermediate
Summary
Melvin Vivas shows Agent Monitor, his open-source dashboard for watching coding-agent sessions. It shows token usage with a per-agent breakdown and an estimated cost for the main agent and its subagents. It works with OpenAI Codex, Claude Code and Pi. The project is still in development, but you can already use it.
Key points
- Agent Monitor is an open-source GitHub project (donvito/agent-monitor) for visualizing coding-agent sessions.
- It shows a dashboard of the main Codex agent and its subagents.
- It shows token usage broken down per agent, plus an estimated cost.
- It supports Codex, Claude Code and Pi.
- According to the repo description, it also has an advanced traces view.
- It is still in development but already usable. It's a practical way to see where tokens and money go in multi-agent coding workflows.
Resources mentioned
- donvito/agent-monitor · repo · github.com · free
Open-source tool that visualizes Codex and Claude Code subagents, with an advanced traces view, token breakdown and cost tracking.
Also in: Agent Monitor: Visualize Codex, Claude Code and Pi Agent Traces (Melvin Vivas on X · notes), Monitor Codex and Claude Code Subagents with agent-monitor (Melvin Vivas on X · notes), Agent Monitor: see traces, tokens and costs of your coding agents (Melvin Vivas on X · notes), Agent Monitor: Visualize Codex and Claude Code Subagents, Traces and Costs (Melvin Vivas on X · notes) and 3 more - OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more - Claude Code · tool · code.claude.com · paid · recommended by both Bashiri Smith & Melvin Vivas
Build agents and pipelines from the terminal; the guide's main agentic coding tool.
Also in: First impressions: Claude Code in the cloud is good and fast (Melvin Vivas on X · notes), Why Claude Code feels faster: gzipped turns and instant cloud sessions (Melvin Vivas on X · notes), Watch What Fills Your Coding Agent's Context and When to Clear (Melvin Vivas on X · notes), Claude Code's Right Sidebar and Context Breakdown (Melvin Vivas on X · notes) and 124 more - Pi · tool · x.com · free
A customizable coding agent that can be extended through its Extensions API and connected to several model providers.
Also in: 100-Iteration Autonomous Coding Loop with Local Qwen on an RTX 3090 (Melvin Vivas on X · notes), Pi Agent: A Highly Customizable Agent with Durable Sessions (Melvin Vivas on X · notes), Prompting an Autonomous Agent Loop: Be Specific, Show Visible Progress (Melvin Vivas on X · notes), Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes) and 54 more
Try this
- Try Agent Monitor from the GitHub repo to see token usage and estimated cost for your Codex, Claude Code or Pi sessions.
More in LLMOps, Deployment & Monitoring
- Hugging Face Cache Deduplication with Xet in huggingface_hub v1.32
- Agent Monitor: see traces, tokens and costs of your coding agents
- Agent Monitor: Per-Model Usage Stats for Codex and Claude Code Agents
- Agent Monitor: Dashboard for Codex Subagents, Tokens and Cost
- Concept Demo: An Agent Monitor Built on OpenAI Codex Traces
- Running Local Models on NVIDIA DGX Sparks (Alex Ellis)