Skills with implicit invocation disabled while only allowing explicit invocation

[your-diary]

What variant of Codex are you using?

CLI

What feature would you like to see?

This issue is preceded by this question:

• Specify that a skill cannot be invoked implicitly #10573

---

Currently, there is no way to disable implicit invocation of skills while allowing explicit invocation via $<name>; we can only instruct codex in natural languages not to invoke skills implicitly, which may or may not be respected by codex.

Given that custom prompts, which is similar to skills but can only be invoked explicitly (via /prompts:<name>), is deprecated in favor of skills, there should be a way to define skills with implicit invocations disabled; otherwise skills cannot be a complete alternative to custom prompts.

Additional information

No response

[github-actions]

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

• Specify that a skill cannot be invoked implicitly #10573
• Non-discoverable (manual) skills #8713

Powered by Codex Action

[your-diary]

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

#10573

No, it's not.
This is a question issue asked by me in the past.

#8713

Similar but not the same. I believe my issue is valid because:

• My issue wants to solve and concentrates on the situation where custom prompts has been deprecated recently in favor of skills. Non-discoverable (manual) skills #8713 is a feature request unrelated to this deprecation.

• Non-discoverable (manual) skills #8713 proposes a new syntax for skill metadata and thus was redirected to an issue of Agent Skills spec repo. My issue doesn't specify how the feature should be implemented. For example, it may be implemented as a config key in ~/.codex/config.toml, which can evolve independent of the standard.

[etraut-openai]

Out of curiosity, are you seeing situations where a skill is invoked implicitly when you don't want it to be? Or is this more of a theoretical concern?

If you're seeing cases where it's being invoked implicitly when that's not desired, we'd be interested in hearing about that.

[your-diary]

@etraut-openai
It's a theoretical concern.

I have many custom prompts which perform destructive operations such as deleting AWS resources, so I want to be 100% (not 99%) sure they are invoked only when I explicitly request so.

A workaround I come up with (but haven't tried) is to bind-mount the skills directories only when I want to use them. This would work only when, for example, codex CLI is running inside a Docker container. (Actually I do wrap codex inside a docker container and implement many safeguards (e.g. bind-mounting an empty file onto an existing .env for extra safety).)

[EricGT]

For what it's worth, similar skill invocation/activation concerns are also noted at

https://github.com/agentskills/agentskills/issues

[wsmoak]

Some tools use disable-model-invocation: true in the frontmatter for this -- then the skill will not be auto-invoked, only if you specifically ask for it. I thought it was in the agent skills spec but apparently not.

Cursor defines it like this:

By default, skills are automatically applied when the agent determines they are relevant. Set disable-model-invocation: true to make a skill behave like a traditional slash command, where it is only included in context when you explicitly type /skill-name in chat.

[lattwood]

One potential use-case for this functionality are skills that the agent might not be able to invoke in all environments the repository is being modified in.

For instance, an infrastructure type repo could have a skill for planning/previewing the changes (ie Terraform Plan), but it requires SRE type credentials to be discoverable in the environment. This is not a skill you would want the model to automatically try to invoke if it's running somewhere like Codex Cloud, but it is a skill you would want to manually invoke from Codex CLI running on your laptop.