agent-watch-approve: 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒

by ghy196830-del · Codex Skill · ★ 124

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

Featured in: Claude Code Hooks, Subagents & Statusline

How to install agent-watch-approve

git clone https://github.com/ghy196830-del/agent-watch-approve.git

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 62/100

Flagged: sudo usage. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

ai-agentapple-watchclaude-codeclaude-code-hookscodexdevtoolshooksnotificationsntfypushcut

Quick Facts

Stars124
Forks11
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score62/100
Open Issues1
Last Updated2026-06-16
Created2026-06-06
Platformsclaude-code, codex, python
Est. Tokens~17k

About agent-watch-approve

⌚ agent-watch-approve AI 在干活,你在摸鱼;危险操作抬腕一点,任务跑完手表喊你。 让 Claude Code 和 Codex 的危险操作推送到你的 Apple Watch / iPhone 上审批, 任务完成自动通知 —— 全程不用回终端。 安卓 / Wear OS / 鸿蒙(兼容模式)同样支持:一个开关切到 ntfy 载体,连 Pushcut 都不用装(见「不止苹果」一节)。 English 📺 看它干活 危险操作 → 手表一震 → ✅ 点一下放行,agent 继续干活 ▶️ 完整介绍视频(30 秒) —— 点开即播(备用:仓库内文件) 功能速览 |:--

Compatible Skills

These tools work well together with agent-watch-approve for enhanced workflows:

  • apple-books-mcp — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
  • claude-ctrl — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)

agent-watch-approve alternative? Top 6 similar tools

Looking for a agent-watch-approve alternative? If you're comparing agent-watch-approve 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.

  • sage by usetig · ⭐ 106

    An LLM council that reviews your coding agent's every move

  • claude-code-hooks by karanb192 · ⭐ 587

    🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.

  • cc-best by xiaobei930 · ⭐ 50

    🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 44 commands · 19 skill

  • pilot by alekspetrov · ⭐ 189

    AI that ships your tickets - autonomous dev pipeline with Claude Code

  • browser-debugger-cli by szymdzum · ⭐ 185

    Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C

  • yume by aofp · ⭐ 154

    Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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