codexUse Codex safely for repo-aware coding with explicit approvals, sandbox choices, MCP boundaries, and PR-ready verification workflows.
Install via ClawdBot CLI:
clawdbot install ivangdavila/codexRequires:
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawic.com/skills/codexUses known external API (expected, informational)
api.openai.comAudited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
A software development team needs to safely refactor a legacy codebase using Codex. The skill ensures bounded edits by first inspecting the repo's structure, test surface, and git status, then using explicit approval modes and sandbox choices to prevent unintended side effects, making changes review-ready for PR workflows.
A DevOps engineer uses Codex with approved MCP servers to automate cloud infrastructure tasks. The skill enforces trust boundaries by reviewing MCP server scopes and side effects, requiring explicit user approval for remote operations, and storing recovery patterns in memory files to handle stuck sessions or failed commands safely.
An open-source contributor leverages Codex with local OSS providers for coding tasks without cloud dependencies. The skill guides explicit mode selection, such as using --oss flags, and maintains durable context in ~/codex/ to track approved repos and sandbox postures, ensuring predictable execution in low-trust environments.
A development team employs Codex in review mode to generate and verify code changes before handoff. The skill enforces preflight checks on repo state and permissions, uses codex review workflows for bounded execution, and stores verification evidence in memory files to facilitate clear, scoped handoffs with minimal risk.
Offer a subscription-based service providing enhanced Codex integrations with repo-aware safety features, approval workflows, and MCP guardrails. Revenue comes from monthly or annual fees for teams needing predictable, secure coding automation in enterprise environments.
Provide consulting services to help organizations adopt Codex safely, including setup, custom memory configurations, and training on operating modes like exec and review. Revenue is generated through project-based fees and ongoing support contracts tailored to client needs.
Sell enterprise licenses for a premium version of the skill with advanced features like incident recovery playbooks, cloud task management, and compliance reporting. Revenue streams include one-time license purchases and annual maintenance fees for updates and support.
💬 Integration Tip
Ensure the codex binary is installed and authenticated, and pre-configure ~/codex/ memory files with repo profiles and safety defaults to streamline operational workflows and reduce setup overhead.
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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.