No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by theDanButuc · Agent Tool · ★ 51
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Claude-Usage-Monitor safe to install? View the security audit →
ClaudeUsageMonitor · v2.2.1 A native macOS menu-bar app that tracks your Claude.ai usage in real time — no API key needed. Changelog v2.2.1 Hourly update check — app now checks for new versions every hour in the background, not just at launch In-app download — when an update is available, click "Update Now" to download the DMG directly in the app; a progress bar is shown during download; click "Open & Install" when ready — Finder opens the DMG for a 1-step drag-install v2.2.0 Claude Design usage bar — new weekly progress bar for Claude Design usage, shown automatically when your plan has Claude Design allocation; tracks the bucket from the API v2.1.0 Daily routine runs — new progress bar tracking Claude Code Routine run budget per day (Pro: 5/day, Max: 15/day, Team/Enterprise: 25/day); shown automatically when your plan includes Routines Routine run notifications — alerts when 1 run remains and when all runs are exhausted for the day Data fetched from a dedicated API endpoint (), plan limits are read directly from the API — no hardcoding v2.0.0 Direct API — migrated from DOM scraping + JS injection (WKWebView) to direct URLSession calls against Claude's internal REST API; faster,...
| Stars | 51 |
| Forks | 7 |
| Language | Swift |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 74.9793610952882/100 |
| Open Issues | 4 |
| Last Updated | 2026-07-21 |
| Created | 2026-03-22 |
| Platforms | claude-code |
| Est. Tokens | ~17k |
These tools work well together with Claude-Usage-Monitor for enhanced workflows:
Looking for a Claude-Usage-Monitor alternative? If you're comparing Claude-Usage-Monitor with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
A keyboard-first menubar app to monitor and jump between AI coding sessions — minimum setup required.
Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Nativ
Keep Your Mac Awayke With the Lid Closed
Clipboard Manager for macOS
Cover your Mac screen with a hotkey while AI agents keep running. Dog/cat mascot, native Settings, Touch ID un
Explore other popular agent tool tools:
Claude-Usage-Monitor is A native macOS menu bar app that shows your Claude.ai usage at a glance — colour-coded icon, live counter, reset timer. No API key needed.. It is categorized as a Agent Tool with 51 GitHub stars.
Claude-Usage-Monitor is primarily written in Swift. It covers topics such as ai-tools, anthropic, claude.
You can find installation instructions and usage details in the Claude-Usage-Monitor GitHub repository at github.com/theDanButuc/Claude-Usage-Monitor. The project has 51 stars and 7 forks, indicating an active community.
Claude-Usage-Monitor is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Claude-Usage-Monitor on Agent Skills Hub include CodeIsland, cctop, Council. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: