codex-review
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/abczsl520/codex-reviewWhat This Skill Does
Codex Review provides a professional-grade, three-tier code quality defense mechanism for your software projects. Designed for OpenClaw agents, it intelligently manages the depth of your code analysis based on the complexity of your request. At Level 1 (L1), it performs a swift scan using an optional external AI model combined with an agent-led pass to catch low-hanging fruit. Level 2 (L2) triggers a rigorous audit, utilizing the dedicated 'bug-audit' skill for deep-level security and performance inspection. Level 3 (L3) offers the highest level of scrutiny, orchestrating cross-validation between dual independent audits and adversarial testing scenarios to uncover edge-case vulnerabilities.
Installation
To integrate Codex Review into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/abczsl520/codex-review
Use Cases
Codex Review is ideal for CI/CD pipeline integration, pre-release sanity checks, and security-critical refactoring. It is perfect for developers who need to ensure that their codebase meets high standards of quality and security without manual overhead. By categorizing tasks into tiers, it ensures you only spend as much time as necessary on analysis.
Example Prompts
- "review the current directory and provide a summary of potential bugs."
- "Please run a deep audit on this module to ensure it meets our security guidelines."
- "Perform a pre-deploy check on the main branch before we push to production."
Tips & Limitations
- Security First: The skill operates in a read-only mode by default, ensuring that your source code is never modified or deleted by the agent.
- Optional Optimization: While the skill works independently, setting up an OpenAI-compatible API key significantly enhances the speed and depth of L1/L3 reports.
- Exclusion Lists: The skill automatically ignores noise files like 'node_modules', '.git', and build artifacts to maintain focus on your proprietary logic.
- Data Privacy: No data is sent to external APIs beyond the specific file snippets under review; no telemetry or analytics are collected.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-abczsl520-codex-review": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read, external-api
Related Skills
doctorbot-ci-validator
Stop failing in production. Validate your GitHub Actions, GitLab CI & Keep workflows offline with surgical precision. Born from Keep bounty research, perfected for agents.
q-kdb-code-review
AI-powered code review for Q/kdb+ — catch bugs in the most terse language in finance
astrai-code-review
AI-powered code review with intelligent model routing — saves 40%+ vs always using the most expensive model
afrexai-observability-engine
Complete observability & reliability engineering system. Use when designing monitoring, implementing structured logging, setting up distributed tracing, building alerting systems, creating SLO/SLI frameworks, running incident response, conducting post-mortems, or auditing system reliability. Covers all three pillars (logs/metrics/traces), alert design, dashboard architecture, on-call operations, chaos engineering, and cost optimization.
opentangl
Not a code generator — an entire dev team. You write the vision, it ships the code. Autonomous builds, PRs, reviews, and merges across multiple repos. Point it at any JS/TS project and a product vision. It plans features, writes code, verifies builds, creates PRs, reviews diffs, and merges — autonomously. Manages multiple repos as one product. Use when you want to ship code without writing it. AI code generation, autonomous development, workflow automation, multi-repo orchestration, TypeScript, JavaScript, GitHub, OpenAI, Anthropic, Claude, GPT, LLM, devtools, CI/CD, pull requests, code review.