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.
The model-based Bash command prefix classifier is gone
You'll notice
Useful4Signal3
Permissions
Bash permission checks no longer ask a model to figure out the command prefix.
What's wrong with this entry?
Anonymous. No account, no email.
What
Bash permission decisions no longer make a model call to extract a command prefix. The prompt, its command_injection_detected escape hatch and its example list are absent from the bundle, along with the caching class that drove it.
Evidence
command_injection_detected
Strings lifted out of the shipped bundle, so the claim above can be checked against them.