DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.
Someone-else's-artifact warning takes its verb and object as arguments
Under the hood
Useful1Signal3
Artifacts
The warning before touching someone else's artifact can now be worded to fit other artifact actions.
What's wrong with this entry?
Anonymous. No account, no email.
What
The warning shown before touching an artifact you do not own is now parameterised, defaulting to "write into" and "their database", so other artifact actions can reuse it with wording that fits what they do.
Evidence
This artifact belongs to someone else
Strings lifted out of the shipped bundle, so the claim above can be checked against them.