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 openqa-cn · Codex Skill · ★ 111
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codexqa safe to install? View the security audit →
codexqa Seven local-first Agent Skills for requirements, test design, test data, change impact, exception RCA, code-risk scan, and graph-evidence review. English | 简体中文 Quick Start · Sample report · How It Works · Blind Evaluation · Evidence & Limits · Getting Started · FAQ · Support Matrix <img src="docs/assets/previews/defect-report.png" alt="Defect-detection HTML report: three requirement mismatches" wi
| Stars | 111 |
| Forks | 2 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 69.2287764664459/100 |
| Open Issues | 4 |
| Last Updated | 2026-10-03 |
| Created | 2026-09-05 |
| Platforms | browser, claude-code, codex, python |
| Est. Tokens | ~17k |
Looking for a codexqa alternative? If you're comparing codexqa 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.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI
An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as sec
QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude C
AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query f
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
AI-powered code quality analysis using MCP to help AI assistants review code more effectively. Analyze git cha
Explore other popular codex skill tools:
codexqa is codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.. It is categorized as a Codex Skill with 111 GitHub stars.
codexqa is primarily written in Python. It covers topics such as agent-skills, agentskills, ai-code-review.
You can find installation instructions and usage details in the codexqa GitHub repository at github.com/openqa-cn/codexqa. The project has 111 stars and 2 forks, indicating an active community.
codexqa is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to codexqa on Agent Skills Hub include bug-hunter, Gito, qaskills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: