gitagent-protocol — 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 open-gitagent · Codex Skill · ★ 2.8k

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

🔒 Is gitagent-protocol safe to install? View the security audit →

About gitagent-protocol

GitAgentProtocol (Open GAP) | your repository becomes your agent — the GitAgentProtocol (GAP) Manager CLI, published as . Previously published as . GitAgentProtocol (Open GAP) is a framework-agnostic, git-native standard for defining AI agents. Clone a repo, get an agent. is its reference CLI. Why Every AI framework has its own structure. There's no universal, portable way to define an agent that works across Claude Code, OpenAI, LangChain, CrewAI, and AutoGen. gitagent fixes that. Git-native — Version control, branching, diffing, and collaboration built in Framework-agnostic — Export to any framework with adapters Compliance-ready

agentagent-frameworkagent-skillsagentsassistantclaude-codegitagentopen-standardopenclawskills

Quick Facts

Stars2,776
Forks334
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score68.3893173008418/100
Open Issues12
Last Updated2026-05-13
Created2026-02-24
Platformsclaude-code, node
Est. Tokens~1675k

Compatible Skills

These tools work well together with gitagent-protocol for enhanced workflows:

  • skills — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • voltagent — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • skills — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • skills — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (56%)
  • agent-skills — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

gitagent-protocol alternative? Top 6 similar tools

Looking for a gitagent-protocol alternative? If you're comparing gitagent-protocol 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.

  • symbiotic-ai by lout33 · ⭐ 733

    A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

  • hive by aden-hive · ⭐ 11.0k

    Multi-Agent Harness for Production AI

  • Upsonic by Upsonic · ⭐ 8.0k

    Build autonomous AI agents in Python.

  • refly by refly-ai · ⭐ 7.5k

    The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex

  • AI-Infra-Guard by Tencent · ⭐ 6.4k

    A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca

  • deepchat by ThinkInAIXYZ · ⭐ 6.3k

    🐬DeepChat - A smart assistant that connects powerful AI to your personal world

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is gitagent-protocol?

gitagent-protocol is A framework-agnostic, git-native standard for defining AI agents. It is categorized as a Codex Skill with 2.8k GitHub stars.

What programming language is gitagent-protocol written in?

gitagent-protocol is primarily written in TypeScript. It covers topics such as agent, agent-framework, agent-skills.

How do I install or use gitagent-protocol?

You can find installation instructions and usage details in the gitagent-protocol GitHub repository at github.com/open-gitagent/gitagent-protocol. The project has 2.8k stars and 334 forks, indicating an active community.

What license does gitagent-protocol use?

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

What are the best alternatives to gitagent-protocol?

The top alternatives to gitagent-protocol on Agent Skills Hub include symbiotic-ai, hive, Upsonic. 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