AI Quota Meter — AI skill for Claude Code
Claude Code knows how much quota you have left on nearly every turn, and only shows you if you ask.
How to install AI Quota Meter
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sigiletlabs/ai-quota-meter and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Quota Meter does
Claude Code knows how much quota you have left on nearly every turn, and only shows you if you ask. This puts the percentages on your status line where you can see them. The numbers are Anthropic's own. Run it once and it sets itself up, and it turns on Codex's built in quota display too.
Alternatives in AI
- Daymon — Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team 372 ★
- Tokentab — A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, p 226 ★
- Cross Agent Session Resumer — Resume AI coding sessions across providers: converts Codex, Claude, Gemini, and other session formats through 71 ★
README
AI Quota Meter
You can't see how much Claude quota you have left. Claude Code is told, on nearly every turn, and doesn't show you unless you stop and ask. So you work around a number that is sitting right there.
This puts it on the status line, where you can glance at it:
Opus 5 (1M context) ai-quota-meter 228k/1M 5h 62% (1h52m left) 7d 41% (4d left)
Left to right: the model, the directory, how full the context window is, then each quota window with how much you have used and how long until it resets.
**Those percentages are Anthropic's own.** Claude Code already receives them and hands them to whatever you set as your status line. This program reports them and calculates nothing. The numbers are as good as the vendor's, because they *are* the vendor's.
Install
Download the binary for your platform from [releases](https://github.com/sigiletlabs/ai-quota-meter/releases), or:
go install github.com/sigiletlabs/ai-quota-meter@latest
Every released binary is built by GitHub Actions and carries a signed record of which commit and workflow produced it. Check it before you trust it:
gh attestation verify ai-quota-meter-linux-amd64 --repo sigiletlabs/ai-quota-meter
It prints nothing and exits 0 when the binary is genuine. A file that has been altered exits 1.
Then run it:
ai-quota-meter
Run by hand with nothing set up yet, it installs itself: it points Claude Code at the binary, keeps your other settings, backs the file up first, and prints what your bar will look like. There is nothing else to configure.
Claude Code picks it up within about 30 seconds, with no restart.
If anything looks wrong:
ai-quota-meter --doctor
Six checks, each one saying how to fix what it found. Worth running before you go hunting yourself, because Claude Code shows nothing at all — no error, no stale line — for a status line command it cannot run.
Linux, macOS and Windows. No dependencies: standard library only, static bina
Related Skills
SentriPet AI
A desktop pet that shows how much of your AI plan is left (Claude, Codex, Copilot…) and nudges you to use it b
Pi Usage Live
Always-on subscription usage card for Pi: see how much of your Claude, ChatGPT Codex, OpenCode Zen, DeepSeek,
Autoclaw
autoclaw — ambient AI for macOS. It sees what you see, knows what to do, and does it. No prompts, no chat. You
Herdr Agents Tracker
Herdr plugin that shows your AI subscription usage: account limits in the tab bar, a context meter per agent,
Local Time Tracker macOS
Fully-local, featherweight macOS time tracker — runs in the background (~15 MB), auto-files time into projects
Pwe AI Bar
Menu-bar quota meter for AI coding tools on macOS. Claude Code and Codex from the real endpoints, plus five mo
Related Agents
SEO Crawl Analyst
Reads a crawl export from any tool and returns the site-level findings, ordered by how much traffic each one p
10x Tool Calls
Cursor and Windsurf meter usage by requests and tool calls rather than tokens, which means a finished or stall
Half Fix
Review angle "half-fix & consistency" of the user's §6 adversarial-review gate — hunts the sins tests cannot s