code-mate-codex
Lets your agent analyze and implement code. It's useful for getting coding results or comparing with other tools.
What it does
This tool helps you analyze and implement code. It runs a program called Codex to perform tasks on your programming project.
When to use it
- ✓When you want the AI to analyze your code.
- ✓When you ask the AI to make changes to the code.
- ✓When you want a second opinion from another AI on your code.
Example of what to ask your AI
“Analyze this code and tell me if there are any errors.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool sets up the environment for the Codex program, sends your instructions, and waits for the result. It shows the final result or informs you if something went wrong.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add CherryHQ/cherry-studio --skill code-mate-codexOr download just the file:
curl -L https://raw.githubusercontent.com/CherryHQ/cherry-studio/main/resources/code-cli-skills/code-mate-codex/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Codex CLI
Run
- Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
- Check availability with
command -v codex. If it is missing, stop and ask the user to install Codex CLI in Code Mate. - Run one task and exit:
codex exec "<prompt>" --json
Pass the prompt as one quoted argument. Parse stdout as JSONL, preserve event order, and use the final agent message as the result. Treat an error event or nonzero exit as failure. Never start interactive codex or codex login.
Authentication And Permissions
If Codex reports missing login or API configuration, stop and ask the user to finish Codex setup in Code Mate. Never request, read, print, or copy credentials.
Use --sandbox read-only unless the user explicitly requested workspace changes. For an approved edit, use only the narrowest suitable sandbox and working directory; never add --dangerously-bypass-approvals-and-sandbox. Add --skip-git-repo-check only when the user intentionally selected a non-Git directory.
Example: for a review request, append --sandbox read-only, ask Codex not to modify files, and summarize the final JSONL message plus any reported errors.
FAQ
What is Codex?
Codex is a program that helps programmers analyze and write code.
Do I need to install anything?
Yes, you need to install the Codex CLI in Code Mate to use this tool.
Can the tool change my files?
It only changes your files if you explicitly ask and it's configured to do so. Most of the time, it just analyzes the code without making changes.
Details
Original description by the author
Runs Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Codex or obtain a second coding-agent result.
repo: CherryHQ/cherry-studio
Popularity
- GitHub stars
- 53k
- Ranking position
- #1804
- License
- AGPL-3.0
- Updated
- 10/16/2026
Comments
- …
More skills from this repository
code-mate-antigravity
Lets your agent analyze code and perform programming tasks. It's useful for reviewing or improving existing code.
CherryHQ/cherry-studio
code-mate-claude-code
Helps your agent analyze and implement code. It's useful for software development tasks and code reviews.
CherryHQ/cherry-studio
code-mate-deepseek-harness
Helps your agent analyze and implement code in repositories. It's useful for bounded development tasks and code analysis.
CherryHQ/cherry-studio
code-mate-gemini
Lets your agent analyze code and perform programming tasks. It's useful for delegating coding work or comparing results.
CherryHQ/cherry-studio
Similar skills
benchmark-optimization-loop
Has your agent improve something's speed in a measured way. It tests multiple versions and chooses the fastest one that still works correctly.
affaan-m/ECC
change-impact
Helps your agent analyze the impact of code changes before making them. It compares the planned vs. actual results afterward, covering paths, data, tests, and documentation. Useful for risky or system-wide changes.
affaan-m/ECC
click-path-audit
Lets your agent trace all user buttons and interactions to find bugs. It finds issues where functions seem to work alone but fail together. Useful when bugs persist even after debugging.
affaan-m/ECC