Skip to main content

View Claude (claude.ai) usage limits across multiple accounts from your terminal

Project description

claude-seeker

See how much of your Claude (claude.ai) usage you've burned through — the 5-hour and weekly limits, plus the Sonnet / Opus splits — for all your accounts at once, right in the terminal. There's also a small desktop app if you'd rather click than type.

Handy when you're juggling a few accounts and want to know which one still has room before you kick off a long session.

Install

Easiest is pipx (or uv), which keeps cseek in its own tidy environment:

pipx install claude-seeker
uv tool install claude-seeker      # if you prefer uv

Then check it works:

cseek --help

A few optional add-ons, only if you want them:

  • Store your tokens in the OS credential manager (Windows Credential Manager / macOS Keychain) instead of a local file:
    pipx install "claude-seeker[keyring]"
    
  • The desktop app:
    pipx install "claude-seeker[gui]"
    
  • Export to Excel (.xlsx):
    pipx install "claude-seeker[export]"
    

(Already installed and want to add one later? pipx inject claude-seeker keyring — swap in openpyxl for Excel, PySide6 for the app.)

Add an account

You can track as many accounts as you like. There are two ways to add one.

1. With a session token (any claude.ai account)

Grab the token from your browser:

  1. Open claude.ai and log in.
  2. Press F12Application tab.
  3. In the sidebar: Cookieshttps://claude.ai.
  4. Copy the value of the sessionKey cookie (it starts with sk-ant-sid...).

Then add it (the name is just a label — your email, or anything you'll recognize):

cseek --add-session-account sk-ant-sid01-... me@work.com

Prefer not to paste the token on the command line? Run it bare and you'll be prompted:

cseek --add-session-account

Got many accounts in a spreadsheet? Add them all at once (columns are auto-detected; nothing is fetched):

cseek --bulk-add accounts.xlsx     # or .csv

2. From Claude Code (OAuth)

If you're logged into Claude Code on this machine, cseek can borrow that login — no copying tokens:

claude login              # if you haven't already
cseek --add-claude-codeid

Everyday use

cseek --accounts                   # list your accounts + slots (no network)
cseek --list                       # fetch and show usage for everyone
cseek --status --slot 2            # just one account
cseek --refresh                    # verify every login; flags expired ones (exit 1)
cseek --list --watch 30            # re-check every 30 seconds
cseek --list --json                # machine-readable output

--accounts also shows each account's last known state (ok / EXPIRED), so you can spot dead logins without fetching anything.

Got a lot of accounts? Check them in groups instead of all at once:

cseek --list-group                 # preview the groups (no network)
cseek --list-group 2               # fetch usage for group 2 only
cseek --list-group-auto 5          # walk through each group, 5 min apart, then stop

Save a snapshot to a file:

cseek --export csv                         # -> claude-usage-export.csv
cseek --export xlsx --out usage.xlsx       # Excel, with a usage chart

Tidy up:

cseek --remove-account 1
cseek --remove-all

Run cseek --help for the full list. Add --debug to any command for timing and full error details.

Desktop app

If you'd rather not live in the terminal:

cseek-gui          # (same as: cseek --gui)

It shows one card per account — email, org, plan, and the 5h / 7d usage bars with their reset times — laid out in pages of ten. Opening it just lists your saved accounts; nothing is fetched until you hit View usage (one group at a time) or Loop (cycles through them on a timer). From the toolbar you can add accounts one at a time or bulk-import a whole spreadsheet (.xlsx / .csv), and export to CSV or Excel. Usage history builds up quietly over time and feeds the trend line in the Excel export.

Where your data lives

Everything stays on your machine under ~/.claude-usage/ (account list and usage history). Your tokens go into your OS credential store when you install the [keyring] extra; otherwise they sit in a local file, ~/.claude-usage/credentials.json (locked down to your user on macOS/Linux).

A note on security: a sessionKey is a live login to your claude.ai account. If you're using the file fallback, that token is stored in plain text — don't commit it, share it, or sync it anywhere public. The OS credential store ([keyring]) is the safer choice when it's available to you.

Requirements

  • Python 3.9 or newer. (py --version on Windows, python3 --version on macOS / Linux.)
  • That's it — the core tool has no other dependencies.

License

MIT.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

claude_seeker-0.1.4.tar.gz (65.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

claude_seeker-0.1.4-py3-none-any.whl (47.7 kB view details)

Uploaded Python 3

File details

Details for the file claude_seeker-0.1.4.tar.gz.

File metadata

  • Download URL: claude_seeker-0.1.4.tar.gz
  • Upload date:
  • Size: 65.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for claude_seeker-0.1.4.tar.gz
Algorithm Hash digest
SHA256 e1adf4153f13bd98cfb34ea157f48308020121f710dcdd18899c5f22e027c89a
MD5 126a4a9dd2b9d9f3f8230814d3a82f9d
BLAKE2b-256 c7cc9895869a120ce52e25bed0bc1c01eecefa1a5bfbb6e68a55be17a518b36e

See more details on using hashes here.

File details

Details for the file claude_seeker-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: claude_seeker-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 47.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for claude_seeker-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 761a7ce50deb6795b4e59b1dc1a92d5d374157dd3ea39c8d5bdce021bc48b793
MD5 19076a550e1508144b58eb39672ca338
BLAKE2b-256 8d3ecf1590939c083e627dfb5c6e8859808b12473f4946a7d735757e0cfb8c90

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page