Standardize OpenAI model invocations for code analysis and review via scripts/codex.
npx skills add https://github.com/kent013/aicue --skill app-codex-vscode
Please help me install this Agent Skill. Skill: app-codex-vscode Source: https://github.com/kent013/aicue/tree/main/.claude/skills/app-codex-vscode Command: npx skills add https://github.com/kent013/aicue --skill app-codex-vscode
This Skill simplifies the invocation of OpenAI models for code-based tasks, providing a standardized and secure interface for code analysis, review, and technical design.
scripts/codex executable, with configurable options for different models and reasoning depths.codex exec command with the necessary parameters, ensuring secure and controlled access to the AI model.To perform a code analysis on the 'code_sample.txt' using the 'gpt-5.3-codex' model with medium reasoning effort, run:
scripts/codex exec --ephemeral --sandbox read-only -m gpt-5.3-codex \
-c 'model_reasoning_effort="medium"' \
-o analysis_output.txt - < code_sample.txt
High-intent search queries and answers about installing and using this skill.
Standardize OpenAI model calls for code review by using a centralized executable, allowing you to configure specific models and reasoning depths for technical design tasks securely.
Yes, you can configure reasoning effort for code analysis by passing specific parameters to the model invocation, allowing you to adjust the depth of reasoning applied to your code review.
Perform secure code analysis by executing the model invocation command with read-only sandboxing and ephemeral execution, passing your local file as input to generate an analysis output file.
The best way to execute code-based tasks in a controlled environment is using secure execution and sandboxing, which provides controlled access to the AI model during code analysis.
Yes, you need the openai dependency to run code analysis and model invocation scripts, as it provides the necessary framework for standardizing and executing the AI model calls.
yoanbernabeuConfigure GrepAI to use OpenAI embeddings for semantic code search.
mkusakaProcess a unified diff and return up to eight high-priority findings per hunk.
hiromailyClassify modified files and apply targeted fixes to PR review comments.
tomlupoInvoke external LLM models to review code, architecture, and design plans.