DocMason — 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 JetXu-LLM · Codex Skill · ★ 135

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

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

About DocMason

DocMason A repo-native agent app for deep research over private work files. The repo is the app. Codex is the runtime. Build a local, evidence-first knowledge base with provenance. Already paying for ChatGPT? Codex for macOS is included in your plan. Turn that unused capacity into a local Second Brain. Watch the ▶️ video demo to see how DocMason performs deep rese

agentscodexdeepresearchknowledge-baserepo-native-agent-app

Quick Facts

Stars135
Forks35
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score60.7951174017533/100
Open Issues7
Last Updated2026-09-03
Created2026-03-21
Platformscodex, python
Est. Tokens~16k

Compatible Skills

These tools work well together with DocMason for enhanced workflows:

  • obsidian-second-brain — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • LLM-Wiki — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)

DocMason alternative? Top 6 similar tools

Looking for a DocMason alternative? If you're comparing DocMason 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.

  • avatar by zou-group · ⭐ 241

    (NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

  • seline by tercumantanumut · ⭐ 143

    Seline is a local-first AI desktop application that brings together conversational AI, visual generation tools

  • Cerno-Agentic-Local-Deep-Research by Cerno-AI · ⭐ 84

    Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiab

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • mcp-link by automation-ai-labs · ⭐ 622

    Convert Any OpenAPI V3 API to MCP Server

  • codex-mcp-server by tuannvm · ⭐ 616

    MCP server wrapper for OpenAI Codex CLI that enables Claude Code to leverage Codex's AI capabilities directly.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is DocMason?

DocMason is DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime.. It is categorized as a Codex Skill with 135 GitHub stars.

What programming language is DocMason written in?

DocMason is primarily written in Python. It covers topics such as agents, codex, deepresearch.

How do I install or use DocMason?

You can find installation instructions and usage details in the DocMason GitHub repository at github.com/JetXu-LLM/DocMason. The project has 135 stars and 35 forks, indicating an active community.

What license does DocMason use?

DocMason 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 DocMason?

The top alternatives to DocMason on Agent Skills Hub include avatar, seline, Cerno-Agentic-Local-Deep-Research. 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