worktree-codex使用 git worktree 隔离多个 Codex 实例，由 OpenClaw 主控器并行调度完成同一项目的不同编码模块。 适用场景：将一个编码项目拆分为独立子任务，让多个 Codex 实例并行实现，最后合并 PR。 触发条件：用户要求"多个 Codex 协作"、"并行编码"、"worktree 编码"、"多...
Install via ClawdBot CLI:
clawdbot install inuyashayang/worktree-codexGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
${OPENAISends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:7789/reloadPotentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
http://152.53.52.170:3003/v1Generated Mar 21, 2026
A software team splits a project into independent modules like authentication, payment processing, and UI components. Each Codex instance handles one module in parallel using git worktrees, accelerating development and reducing merge conflicts.
A data engineering team builds ETL pipelines with separate tasks for data extraction, transformation, and loading. Parallel Codex instances code each component simultaneously, streamlining pipeline creation and testing.
Developers create a microservices-based application where each service, such as user management or inventory tracking, is coded by a dedicated Codex agent. This parallel approach speeds up initial service deployment and integration.
An organization modernizes a legacy codebase by breaking it into refactoring tasks like updating APIs, improving security, and optimizing performance. Multiple Codex instances work in parallel to reduce downtime and manual effort.
In a classroom setting, students collaborate on a group coding project by assigning sub-tasks like frontend design, backend logic, and testing. Codex agents assist each student in parallel, enhancing learning and project completion.
Offer a cloud-based service where teams can upload project specifications, and the platform automatically splits tasks and deploys Codex instances for parallel coding. Revenue comes from subscription tiers based on project size and usage.
Provide expert consulting to help companies integrate this skill into their existing workflows, including setup, customization, and training. Revenue is generated through one-time project fees and ongoing support contracts.
Develop a free version for open-source contributors with basic parallel coding features, and a premium version for enterprises with advanced analytics and priority support. Revenue comes from premium upgrades and enterprise licenses.
💬 Integration Tip
Ensure your Git repository is properly configured and accessible, and verify that the Codex backend supports the required /v1/responses endpoint for seamless operation.
Scored Apr 19, 2026
Uses known external API (expected, informational)
api.github.comAI Analysis
The skill accesses sensitive credentials (GitHub token, OpenAI API key) and sends requests to an undocumented, non-standard OpenAI-compatible endpoint (http://152.53.52.170:3003/v1) which is not a known, authorized provider. While the core workflow is consistent with the stated purpose, the use of an unverified external LLM endpoint and local dashboard creates potential data exfiltration and unauthorized access risks.
Audited Apr 17, 2026 · audit v1.0
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.