Pulse — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 qunqin24 · Codex Skill · ★ 299

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Pulse safe to install? View the security audit →

About Pulse

Pulse A lightweight, elegant screen-edge monitor for your AI coding allowances. Real-time remaining quotas and rate limits for Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, Grok, and more. macOS 14 Sonoma or newer · Apple Silicon & Intel Universal · English · 简体中文 · 繁體中文 · 日本語 · 한국어 Pulse is an unobtrusive floating monitor that docks neatly al

antigravityappkitclaude-codecodexkimimacosmenu-baropencoderate-limitssparkle

Quick Facts

Stars299
Forks32
LanguageSwift
CategoryCodex Skill
LicenseApache-2.0
Quality Score60.7254162910125/100
Open Issues6
Last Updated2026-09-20
Created2026-08-30
Platformsclaude-code, codex
Est. Tokens~18k

Compatible Skills

These tools work well together with Pulse for enhanced workflows:

  • TokenEater — semantic(0.55)+complementary+rare_topics+same_lang+similar_pop+shared_platform (78%)
  • Claude-Usage-Monitor — semantic(0.38)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)

Pulse alternative? Top 6 similar tools

Looking for a Pulse alternative? If you're comparing Pulse with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • TokenEater by AThevon · ⭐ 495

    Native macOS app to monitor Claude AI usage limits and watch your coding sessions live

  • TokenBar by Nanako0129 · ⭐ 360

    AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tra

  • aizen by vivy-company · ⭐ 298

    Bring order to your projects, environments, and day-to-day work.

  • poirot by a7t-ai · ⭐ 213

    A native macOS companion for Claude Code that lets you browse sessions, explore diffs, and re-run commands.

  • Hopet by BinaryFroggy · ⭐ 62

    A macOS desktop AI pet that mirrors your Claude Code & Codex CLI session state in real time. 支持Claude Code和Cod

  • agent-sessions by jazzyalex · ⭐ 869

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is Pulse?

Pulse is A floating macOS monitor for how much Claude Code, Codex, Antigravity, OpenCode Go and Kimi Code you have left. It is categorized as a Codex Skill with 299 GitHub stars.

What programming language is Pulse written in?

Pulse is primarily written in Swift. It covers topics such as antigravity, appkit, claude-code.

How do I install or use Pulse?

You can find installation instructions and usage details in the Pulse GitHub repository at github.com/qunqin24/Pulse. The project has 299 stars and 32 forks, indicating an active community.

What license does Pulse use?

Pulse is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Pulse?

The top alternatives to Pulse on Agent Skills Hub include TokenEater, TokenBar, aizen. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools