What variant of Codex are you using?
App, CLI, Web, IDE Extension
What feature would you like to see?
Add support for specifying paths and files for codex agents to ignore, using e.g. a .codexignore or .aiignore file, or in the config.toml.
Intended use is to prevent files that contain:
- sensitive data
- data that might bias AI responses but which are helpful to be versioned (e.g. to show progress or store results for skill development, iterating on prompts, etc.)
Current workarounds are incomplete and unreliable:
- Ask agent to respect it in AGENTS.md, but this is easily ignored.
- Use a
PreToolUse hook with a custom script to attempt to reliably read the tool use and the file path, but (a) there are various ways to not correctly catch reads since Codex reads via shell tools and not a built in Read tool, and (b) agents may try to work around the script.
This has been a user frustration for a while now:
I am writing this since #205 was closed as "completed", by what looks like a mistaken agent advising to check if it was now supported (it is not):
Thank you for the feedback! Please try the latest version of Codex CLI to see if this feature is supported. If not, we encourage you to contribute to the codex-rs/ implementation. More details on our project update can be found #1174.
Additional information
No response
What variant of Codex are you using?
App, CLI, Web, IDE Extension
What feature would you like to see?
Add support for specifying paths and files for codex agents to ignore, using e.g. a
.codexignoreor.aiignorefile, or in theconfig.toml.Intended use is to prevent files that contain:
Current workarounds are incomplete and unreliable:
PreToolUsehook with a custom script to attempt to reliably read the tool use and the file path, but (a) there are various ways to not correctly catch reads since Codex reads via shell tools and not a built inReadtool, and (b) agents may try to work around the script.This has been a user frustration for a while now:
I am writing this since #205 was closed as "completed", by what looks like a mistaken agent advising to check if it was now supported (it is not):
Additional information
No response