debroid — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 PatilShreyas · Codex Skill · ★ 255

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

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

About debroid

Debroid 🤖⚡ The Headless Android Debugger for AI Agents Debroid (DEBug + AnDROID) is a headless CLI that speaks the Java Debug Wire protocol (JDWP) so AI agents — Claude Code, Grok Build, Codex, OpenCode, Cursor, Antigravity, or anything with a terminal — can debug a live Android app the way a human would in Android Studio: set breakpoints, catch exceptions, step through code, inspect and mutate variables, and watch fields — all without a GUI, and all through strict, machine-parseable JSON. ❓ Why it exists Traditional Android development environments are highly visual. While AI coding assistants can write code, they are effectively "blind" when it comes to runtime debugging because they cannot click through the Android Studio UI to inspect memory or pause execution. Debroid closes this gap. It acts as a translation layer between the raw te

agentic-aiandroidantigravityclaude-codeclicodexdebuggerdebuggingdebugging-tooldeveloper-tools

Quick Facts

Stars255
Forks13
LanguageKotlin
CategoryCodex Skill
LicenseApache-2.0
Quality Score66.1620302721581/100
Open Issues7
Last Updated2026-09-06
Created2026-08-02
Platformsclaude-code, cli, codex
Est. Tokens~18k

Compatible Skills

These tools work well together with debroid for enhanced workflows:

  • adbfriend — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • KMPilot — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)

debroid alternative? Top 6 similar tools

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

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • ccpocket by K9i-0 · ⭐ 1.1k

    Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge

  • agent-sessions by jazzyalex · ⭐ 869

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

  • agent-skills-cli by Karanjot786 · ⭐ 175

    Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitH

  • sub-agents-mcp by shinpr · ⭐ 98

    Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Kotlin Agent Tools

Frequently Asked Questions

What is debroid?

debroid is Autonomous, headless Android debugger designed for AI coding agents. Inspect runtime memory, set breakpoints, and debug live apps.. It is categorized as a Codex Skill with 255 GitHub stars.

What programming language is debroid written in?

debroid is primarily written in Kotlin. It covers topics such as agentic-ai, android, antigravity.

How do I install or use debroid?

You can find installation instructions and usage details in the debroid GitHub repository at github.com/PatilShreyas/debroid. The project has 255 stars and 13 forks, indicating an active community.

What license does debroid use?

debroid 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 debroid?

The top alternatives to debroid on Agent Skills Hub include compose-skill, hcom, ccpocket. 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