design

CodexBar: Track AI Usage

See OpenAI Codex and Claude Code stats without logging in, for founders using AI
20,697 stars1,793 forksSwiftGuide quality 9/10Updated 8/29/2026100% free · open source
What it does

CodexBar displays usage statistics for OpenAI Codex and Claude Code without requiring a login, providing insights for founders leveraging AI in their projects.

When to use it
  • When exploring AI-powered coding tools for your startup
  • To compare usage statistics between OpenAI Codex and Claude Code
  • For staying updated on the popularity of AI coding tools in the developer community
Ready-to-paste prompt
swift run --stat codex to see the current statistics for OpenAI Codex
Heads up: Ensure you have Swift installed on your system, as CodexBar is written in Swift and requires it to run
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/codexbar && curl -fsSL https://workflowstacks.com/api/skills/codexbar/claude-skill -o ~/.claude/skills/codexbar/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How CodexBar: Track AI Usage works
Codeflow
Free to inspect

CodexBar: Track AI Usage is a very large Swift project (~360k lines across 1326 code files, plus 935 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~360k lines · 1326 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Swift
No API keys detected
Swift 89%C 9%Shell 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/docs-list
    Where the program starts running
What's in each folder
bin/Command-line entry points2 files
docs/Documentation259 files
Sources/Folder1308 files
Scripts/Helper scripts76 files
TestsLinux/Folder50 files
TestsPlugin/Folder9 files
WidgetExtension/Folder5 files
Icon.icon/Folder2 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
steipete
Language
Swift
Category
design
Published
11/16/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.