codex-reviewThree-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 ClawdBot CLI:
clawdbot install abczsl520/codex-reviewGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://img.shields.io/badge/ClawHub-codex--review-blueUses known external API (expected, informational)
api.openai.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Development teams use L1→L2 flow before deploying critical updates to production. The quick scan identifies obvious vulnerabilities, then deep audit examines complex logic chains and edge cases. This prevents security breaches in financial or healthcare applications.
Maintainers run L3 cross-validation when accepting major contributions from external developers. Dual independent audits compare findings, while adversarial testing simulates malicious inputs. This ensures code quality while maintaining community trust in popular Node.js libraries.
Engineering teams migrating old codebases use L2 deep audit to uncover hidden technical debt and security flaws. The bug-audit integration systematically examines outdated patterns and dependencies. This reduces risks during cloud migration or framework upgrades.
Early-stage startups with limited security expertise use L1 quick scan for rapid vulnerability assessment. The external API provides expert-level review without hiring specialists, while agent-only fallback ensures continuous operation. This helps bootstrap secure applications on tight budgets.
CI/CD pipelines automatically trigger L1 scans on pull requests, with L2 audits for production branches. Hotspot files enable incremental reviews between pipeline stages. This embeds quality assurance into deployment workflows without manual intervention.
Consulting firms offer tiered code review services using this skill's levels as service packages. L1 serves as affordable entry scan, L2 as comprehensive audit, and L3 as premium enterprise validation. Clients pay per project size and criticality.
Code hosting platforms integrate this skill as a premium code review feature. Basic users get L1 scans, while enterprise plans unlock L2/L3 workflows. The platform monetizes through tiered subscriptions and API call bundling.
Security vendors embed this skill into their application security suites. The three-tier approach complements SAST/DAST tools with AI-assisted review. Sales target compliance-driven industries with annual licensing models.
💬 Integration Tip
Configure environment variables for external API access to enable L1 Round 1 scanning, and install the bug-audit skill dependency for full L2/L3 functionality.
Scored Apr 19, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.