godmode — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 thiientv · Codex Skill · ★ 92

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

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

About godmode

Godmode English | 简体中文 Your coding agent already knows how to code. Godmode teaches it how to engineer. Godmode is a composable catalog of engineering workflows and expert capabilities for AI coding agents. It helps agents design before editing, test before claiming, review independently, and verify with fresh evidence. The problem Coding agents are good at producing code. Without explicit engineering behavior, they can start too early, miss existing conventions, bolt tests on at the end, and call a plausible-looking result complete. Composition, not one giant prompt Godmode equips compatible agents to discover and compose the engineering behavior require

agent-evaluationagent-skillsai-agentsai-codingclaude-codecode-reviewcodexcoding-agentsdeveloper-toolsllm

Quick Facts

Stars92
Forks81
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score67.6582357446733/100
Last Updated2026-08-26
Created2026-08-13
Platformsclaude-code, codex, python
Est. Tokens~16k

Compatible Skills

These tools work well together with godmode for enhanced workflows:

  • claude-arsenal — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (62%)
  • penpot-mcp — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

godmode alternative? Top 6 similar tools

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

  • metis by Wholiver · ⭐ 177

    Metis is a coding agent that boosts AI/LLM coding performance by 50%

  • claude-skills by OneWave-AI · ⭐ 313

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • speckit-agent-skills by dceoy · ⭐ 140

    Agent skills for Spec Kit

  • LibreUIUX-Claude-Code by HermeticOrmus · ⭐ 108

    UI/UX system for Claude Code: 71 plugins, 93 agents, 74 skills. Design mastery, archetypal design, accessibili

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is godmode?

godmode is Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.. It is categorized as a Codex Skill with 92 GitHub stars.

What programming language is godmode written in?

godmode is primarily written in Python. It covers topics such as agent-evaluation, agent-skills, ai-agents.

How do I install or use godmode?

You can find installation instructions and usage details in the godmode GitHub repository at github.com/thiientv/godmode. The project has 92 stars and 81 forks, indicating an active community.

What license does godmode use?

godmode is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to godmode?

The top alternatives to godmode on Agent Skills Hub include metis, claude-skills, 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 Codex Skill tools