son-of-claude — 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 asarnaout · Claude Skill · ★ 97

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

🔒 Is son-of-claude safe to install? View the security audit →

About son-of-claude

son-of-claude A Claude Code tool that monitors your Microsoft Teams and responds to messages — no Graph API, no webhooks, no admin permissions. Just vibes. How it works Claude Code's flag lets it control your browser. Son of Claude runs in a loop — every couple of minutes, it opens Teams in Chrome, checks for unread messages, and responds on your behalf. It has access to your local repos, so it can give real answers about your code and projects. Its personality and tone come from . The rules — who to respond to, who to ignore, what it has access to — live in . Why browser automation instead of the Graph API? No Azure AD app registration, no OAuth, no webhooks, no admin permissions required. Claude Code with uses your existing browser session. Setup Download the 3 files: , , and (or if you are on Mac/Linux).

claudeclaude-code

Quick Facts

Stars97
Forks6
LanguageBatchfile
CategoryClaude Skill
LicenseMIT
Quality Score60.9343907167484/100
Last Updated2026-03-22
Created2026-03-20
Platformsclaude-code
Est. Tokens~2k

Compatible Skills

These tools work well together with son-of-claude for enhanced workflows:

  • Claude-Zeroclaw — semantic(0.33)+complementary+similar_pop+shared_platform (51%)
  • explore-claude-code — semantic(0.23)+complementary+similar_pop+shared_platform (48%)
  • linear-claude-skill — semantic(0.22)+complementary+similar_pop+shared_platform (48%)
  • agent-reachout — semantic(0.36)+complementary+similar_pop+shared_platform (47%)

son-of-claude alternative? Top 6 similar tools

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

  • mcp-claude-code by SDGLBL · ⭐ 304

    MCP implementation of Claude Code capabilities and more

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • claudex by Mng-dev-ai · ⭐ 224

    Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • claude-code-statusline by rz1989s · ⭐ 477

    Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos

  • mcp-server by e2b-dev · ⭐ 394

    Giving Claude ability to run code with E2B via MCP (Model Context Protocol)

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Batchfile Agent Tools

Frequently Asked Questions

What is son-of-claude?

son-of-claude is Let Claude Code answer your Microsoft Teams messages while you do literally anything else. It is categorized as a Claude Skill with 97 GitHub stars.

What programming language is son-of-claude written in?

son-of-claude is primarily written in Batchfile. It covers topics such as claude, claude-code.

How do I install or use son-of-claude?

You can find installation instructions and usage details in the son-of-claude GitHub repository at github.com/asarnaout/son-of-claude. The project has 97 stars and 6 forks, indicating an active community.

What license does son-of-claude use?

son-of-claude is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to son-of-claude?

The top alternatives to son-of-claude on Agent Skills Hub include mcp-claude-code, deepcontext-mcp, claudex. 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 Claude Skill tools