X-Master — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 sjtu-sai-agents · Agent Tool · ★ 322

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

🔒 Is X-Master safe to install? View the security audit →

About X-Master

X-Master: Can We Lead on Humanity’s Last Exam? 📑 ArXiv Paper 🔥 News [2025/08/22] Initial codes of X-Master is now available on GitHub! [2025/07/26] Play with our SciMaster, a general-purpose scientific AI agent product! This is the official implementation of X-Master, a general-purpose tool-augmented reasoning agent. Key Features 🧠 Interact with Environments during Reasoning: X-Master emulates human researchers by fluidly pivoting between internal reasoning and external tool use. 💻 Code as Interaction Language: X-Master communicates its intentions and interacts with environments—including Python libraries, custom tools, and even self-generated code—by formulating precise Python code snippets. 🔬 Scattered-and-Stacked Workflow: X-Masters enhances problem-solving performance by strategically increasing both the breadth of exploration and the depth of reasoning. Results on HLE Below is the X-Masters accuracy (%) on the text-only subset of Humanity’s Last Exam (HLE), broken down by category. Some response examples for each HLE categor

Quick Facts

Stars322
Forks23
LanguagePython
CategoryAgent Tool
Quality Score62.7547163311752/100
Open Issues11
Last Updated2025-10-18
Created2025-07-06
Platformspython
Est. Tokens~60k

Compatible Skills

These tools work well together with X-Master for enhanced workflows:

  • AIlice — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (60%)
  • ai-manus — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (58%)
  • NexAU — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (57%)
  • EnvScaler — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)
  • raptor — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)

X-Master alternative? Top 6 similar tools

Looking for a X-Master alternative? If you're comparing X-Master 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.

  • awesome-android-agent-skills by new-silvermoon · ⭐ 917

    A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr

  • claude-code-skill-factory by alirezarezvani · ⭐ 869

    Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude

  • agent-skills by hashicorp · ⭐ 860

    A collection of Agent skills and Claude Code plugins for HashiCorp products.

  • claude-plugins by Kamalnrf · ⭐ 563

    Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo

  • tutor-skills by RoundTable02 · ⭐ 400

    A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults

  • repren by jlevy · ⭐ 374

    Power rename/refactor tool for CLI and agent use

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is X-Master?

X-Master is Official implementation of X-Master, a general-purpose tool-augmented reasoning agent.. It is categorized as a Agent Tool with 322 GitHub stars.

What programming language is X-Master written in?

X-Master is primarily written in Python.

How do I install or use X-Master?

You can find installation instructions and usage details in the X-Master GitHub repository at github.com/sjtu-sai-agents/X-Master. The project has 322 stars and 23 forks, indicating an active community.

What are the best alternatives to X-Master?

The top alternatives to X-Master on Agent Skills Hub include awesome-android-agent-skills, claude-code-skill-factory, agent-skills. 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 Agent Tool tools