See what your coding sessions really cost, subagents included
LunoPeak is an open-source local dashboard for Claude Code, Codex and Cursor sessions with live view, replay, transcript search and per-session token cost. Version 2.1.0 rolls subagent tokens into the parent session across your history.
Source
@idevtim on X · 2026-10-22
Written in our own words. Credit to the original author. Link checked 2026-10-24.
What they did
LunoPeak is an open-source local dashboard for Claude Code, Codex and Cursor sessions with live view, replay, transcript search and per-session token cost. Version 2.1.0 rolls subagent tokens into the parent session across your history.
Result (as claimed)
He found a typical subagent session was hiding about a sixth of its tokens.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; Cursor: free plan, paid from $8/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex, Cursor, Tauri. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: See what your coding sessions really cost, subagents included What the original author did: LunoPeak is an open-source local dashboard for Claude Code, Codex and Cursor sessions with live view, replay, transcript search and per-session token cost. Version 2.1.0 rolls subagent tokens into the parent session across your history. Reported result (as claimed by the author): He found a typical subagent session was hiding about a sixth of its tokens. Source: https://x.com/idevtim/status/2113365100388118666 Tools they used: Claude Code, OpenAI Codex, Cursor, Tauri Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: See what your coding sessions really cost, subagents included What the original author did: LunoPeak is an open-source local dashboard for Claude Code, Codex and Cursor sessions with live view, replay, transcript search and per-session token cost. Version 2.1.0 rolls subagent tokens into the parent session across your history. Reported result (as claimed by the author): He found a typical subagent session was hiding about a sixth of its tokens. Source: https://x.com/idevtim/status/2113365100388118666 Tools they used: Claude Code, OpenAI Codex, Cursor, Tauri Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: See what your coding sessions really cost, subagents included What the original author did: LunoPeak is an open-source local dashboard for Claude Code, Codex and Cursor sessions with live view, replay, transcript search and per-session token cost. Version 2.1.0 rolls subagent tokens into the parent session across your history. Reported result (as claimed by the author): He found a typical subagent session was hiding about a sixth of its tokens. Source: https://x.com/idevtim/status/2113365100388118666 Tools they used: Claude Code, OpenAI Codex, Cursor, Tauri Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to save, share and resume coding agent sessions · How to run multiple coding agents together · How to vibe code an app with Claude Code · How to build a dashboard with AI agents
Related use cases
See which coding agent chat is waiting on you from one local board
DHI Orbit is one local board for Claude Code, Codex, Cursor, Gemini CLI and Antigravity that shows what needs you, what is working, your usage limits and a reply box.
Coordinate coding agents in one group chat with xMatrix
xMatrix is a group chat for people and coding agents across your own machines and repos. Mention Claude Code, Codex, Cursor Agent or Gemini CLI in a channel and it runs locally in your checkout with your own login, each launch in its own git worktree so parallel agents do not overwrite each other.
Make coding agents ask before they delete, push, deploy or migrate
A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check.
Keep working when one coding plan hits its limit by handing off to the next agent
A developer built codemax, one terminal for Claude Code, Codex, Grok and Cursor. When one plan runs out mid-task, the next agent picks up the same task with the same context.