Agent Monitor: Visualize Codex and Claude Code Subagents, Traces and Costs
Melvin Vivas · X video post · 2026-09-18 · 0:04 · 3,433 views · Open on X
Topics: AI Agents, Tool Use & MCP, LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity · Level: intermediate
Summary
Melvin Vivas shares Agent Monitor, an open-source GitHub project that shows what subagents are doing when you run OpenAI Codex or Claude Code. Besides showing the subagents, it has an advanced traces view, a breakdown of token use, and cost tracking. The post is a short demo video with no speech, and it points to the repo.
Key points
- Agent Monitor (github.com/donvito/agent-monitor) shows the subagents that OpenAI Codex and Claude Code start.
- It has an advanced traces view, so you can see what each subagent did, step by step.
- It breaks down token use, so you can see which agents or steps use the most tokens.
- It also tracks cost, which helps you keep coding-agent spending under control.
- This kind of observability for multi-agent coding tools makes subagent work easier to debug and tune.
- The post is only a 4-second demo video with no narration. Setup and usage details are in the repo README.
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 Coding-Agent 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
Try this
- Look at the donvito/agent-monitor repo and follow its README to connect it to your Codex or Claude Code sessions.
- Use the traces, token and cost views to see where your subagent workflows use the most tokens and money.
More in AI Agents, Tool Use & MCP
- Melvin Vivas's refreshed website: AI agents, local models, workflows
- Running Gemma4-E2B tool calling locally on an iPhone
- Jev + WebMCP Solves 100% of Benchmark Tasks at About 112× Lower Cost
- Intent Classification and Routing in a Multi-Agent Desktop App
- Coworker: Open-Source Desktop App for AI Agents, with Jev
- Agent Monitor: Visualize Coding-Agent Subagents, Traces and Costs