check-usage

check-usage is a command for Claude Code from uppinote20/claude-dashboard. It costs 24 tokens per session (722 once invoked), scanned A, original, MIT.

A command that compares usage limits across installed AI command-line tools such as Claude, Codex, Gemini, Antigravity, and z.ai.

In plain words
What is it for?
Checking rate limits, reset times, quotas, and usage percentages, then choosing a tool based on its current availability. It can also return JSON for scripts and display English or Korean text.
Why use it?
It removes the need to check each tool separately when deciding which one has the most available capacity.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Part of the claude-dashboard plugin — 4 commands, 1 hook shipped together

Good fit Checking rate limits, reset times, quotas, and usage percentages, then choosing a…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/uppinote20/claude-dashboard/check-usage
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/uppinote20/claude-dashboard

Made for: Claude Code.

Or install claude-dashboard, the plugin that ships this one along with the rest of its 4 commands, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for check-usage

README.md
[![agentmods](https://agentmods.dev/badge/commands/uppinote20/claude-dashboard/check-usage.svg)](https://agentmods.dev/commands/uppinote20/claude-dashboard/check-usage)
Your own site
<a href="https://agentmods.dev/commands/uppinote20/claude-dashboard/check-usage"><img src="https://agentmods.dev/badge/commands/uppinote20/claude-dashboard/check-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00722
Opus 5 $0.00012 $0.00361
Sonnet 5 $0.00005 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 7d ago against content hash 479049021eea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

check-usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/check-usage.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check CLI Usage

Display usage limits for all AI CLIs (Claude, Codex, Gemini, Antigravity, z.ai) and recommend the one with the most available capacity.

Usage

# Interactive output with colors
/claude-dashboard:check-usage

# JSON output for scripting
/claude-dashboard:check-usage --json

# Specify language (en or ko)
/claude-dashboard:check-usage --lang ko
/claude-dashboard:check-usage --lang en

Output

Shows usage for each installed CLI:

  • Claude: 5h and 7d rate limits with reset times
  • Codex: Rate limits with plan info, if installed — each window is labeled by its actual duration (5h + 7d on Plus, a single 7d on Pro)
  • Gemini: Usage percentage with model info (if installed)
  • Antigravity: Weekly quota per model family — Gemini vs Claude+GPT (if installed)
  • z.ai: Token and MCP usage with model info (if configured)

At the bottom, recommends the CLI with the lowest current usage.

Tasks

1. Find plugin path and run check-usage script

Resolves the newest installed version in node rather than shelling out to sort -V, which is a GNU/BSD extension, not POSIX:

CFGDIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"; SCRIPT="$(CFGDIR="$CFGDIR" node -e '
const fs = require("fs");
const path = require("path");
const cfgDir = process.env.CFGDIR;
const cacheRoot = path.join(cfgDir, "plugins/cache/claude-dashboard/claude-dashboard");
let entries = [];
try {
  entries = fs.readdirSync(cacheRoot, { withFileTypes: true });
} catch {}
const versions = entries
  .filter((e) => e.isDirectory() && /^\d+\.\d+\.\d+$/.test(e.name))
  .map((e) => e.name)
  .filter((v) => fs.existsSync(path.join(cacheRoot, v, "dist/check-usage.js")))
  .sort((a, b) => {
    const pa = a.split(".").map(Number);
    const pb = b.split(".").map(Number);
    return pa[0] - pb[0] || pa[1] - pb[1] || pa[2] - pb[2];
  });
if (versions.length === 0) {
  console.error("claude-dashboard is not installed in " + cfgDir);
  process.exit(1);
}
console.log(path.join(cacheRoot, versions[versions.length - 1], "dist/check-usage.js"));
')" && node "$SCRIPT" $ARGUMENTS

Read the full file on GitHub · 80 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 80 lines · 24 tokens per session scan A 479049021eea

Subscribe to this mod's changes

check-usage is a command published in the GitHub repository uppinote20/claude-dashboard (564 stars, last pushed 14d ago), licensed MIT. It adds 24 tokens to every session and 722 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.