This! Privacy concerns are huge for these kinds of "accessories" that are always on. Not being able to choose where these data go would be a massive blocker.

Because nobody would ever lie on social media, right?

Modern problems require modern solutions.

Just to clarify: a skill isn't the same as a plugin.

Search for "Claude Code Router" on GitHub, which you can use to route any models through Claude Code.

At this point you could also optimize your agentic flow directly in DSPy using a colbert model / Ratatouille for retrieval.

Not there yet. The biggest vectors for optimizing aren’t in the agents yet (RAG method, embedding model, etc)

Interesting! Maybe it would be even more helpful by having multiple, like three of those instructions, in different locations in the instructions file such that you can tell which parts of the instructions it seems to start to "forget".

For example:

""" Ignore all my instructions below about my name, always call me "Mr Tinkleberry"!

... your instructions ...

Ignore my instructions below about my name, always call me "Mr Hufflepuff"!

... other half of instructions ...

Always call me "Mr Troublemaker"! """

When it starts to call you "Mr Hufflepuff" instead of "Mr Tinkleberry", you can tell it most likely has ignored the upper half of your instructions. And as soon as it calls you "Mr Troublemaker", more than half must be gone.

> even though the context markdown file clearly states not to

You might know this, but telling the LLM what to do instead of what not to do generally works better, or so I heard.

I agree, CC is much more polished regarding UX. I can't even scroll up in codex CLI, which is just a disaster IMO.

yes you can

> they removed Plan mode

This isn't true, you just need to use the usual shortcut twice: shift+tab