How Much Claude Left?

Check how much Claude Max / Claude Pro subscription quota you have LEFT — not how much you spent. Most usage tools track API billing or token costs. This one...

Security Scan

The skill's files and runtime instructions match its stated purpose (automating the local Claude Code CLI via tmux to read /usage); it doesn't request unrelated credentials, installs, or network endpoints beyond running your local claude binary.

Purpose & Capability

Name and description say it will check Claude subscription quota. The script only requires tmux, git, and the 'claude' CLI and uses them to run '/usage' in a temporary tmux session — exactly what you'd expect for this task.

Instruction Scope

SKILL.md directs running the included shell script. The script launches the local 'claude' CLI, handles the trust prompt, sends '/usage', captures output, and cleans up. This stays within the stated scope. Note: invoking the local 'claude' binary will cause that binary to perform network activity and use any auth it has — that's expected for querying subscription status but is an external dependency to trust.

Install Mechanism

No install spec; instruction-only plus a small shell script. Nothing is downloaded or extracted from remote URLs, and no third-party packages are installed by the skill itself.

Credentials

The skill declares no environment variables or credentials. The script does not read unrelated files or env vars. It relies on the existing local 'claude' authentication (as it must) but does not attempt to exfiltrate tokens or access other services.

Persistence & Privilege

always is false and the skill does not persist changes to agent config or other skills. It creates only a temporary directory and tmux session and cleans them up on exit.

Assessment

This script appears to do exactly what it says: run your local 'claude' CLI in a temporary tmux session and parse the /usage output. Before running, verify you trust the 'claude' binary you have installed (it will use whatever local auth tokens exist and may perform network calls). You can review the short script (it's included) — it creates a temp directory, runs claude, captures output, and deletes the temp files. If you're cautious, run 'claude' manually to confirm behavior and authentication, or run the script in an isolated environment (VM/container) first. It will not send your system files or credentials anywhere on its own.

Claude Quota Checker

How much Claude do you have LEFT?

Most tools tell you how much you spent. This one tells you how much you have remaining — the question that actually matters when you're working and worried about hitting limits.

Checks your Claude Max/Pro subscription quota by automating the /usage command via tmux. No API keys needed, no Admin keys, no complex setup.

How It Works

1. Creates a temporary tmux session with a scratch git repo
2. Launches Claude Code CLI
3. Handles the "trust this folder" prompt automatically
4. Sends /usage command
5. Captures and parses the output
6. Cleans up tmux session

Usage

bash ./scripts/check-usage.sh

Note: Run from the skill directory, or use the full path based on where you installed this skill. The script auto-detects its own location.

Output

• Plan type: Pro or Max (e.g., "Opus 4.6 — Claude Max")
• Session usage: current session % used
• Weekly usage: all models % and Sonnet-only %
• Reset time: when the weekly quota resets

Error Handling

Problem	Symptom	Fix
tmux not installed	command not found: tmux	brew install tmux
Claude CLI not in PATH	Session hangs	Install Claude Code CLI, ensure claude is in PATH
Auth expired	"Please log in" in output	Run claude manually and re-authenticate
Git not installed	Script fails at git init	brew install git

If the script hangs for >15 seconds, it likely means Claude CLI couldn't start. Kill with: tmux kill-session -t cu-*

Requirements

• macOS or Linux
• tmux installed
• claude CLI in PATH
• Active Claude Code authentication (Pro or Max subscription)
• git installed (for scratch repo)

Performance

~8-10 seconds (bottleneck: Claude Code CLI startup time).

Limitations

• Only checks subscription usage (Pro/Max), not API billing
• Requires a running terminal environment (won't work in sandboxed containers)
• Output parsing depends on Claude Code CLI's /usage format — may break if Anthropic changes the output layout