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 Task tool's system prompt now documents that agents can be resumed using the resume parameter, that agent outputs should generally be trusted, and includes guidance on distinguishing research vs. code-writing tasks.
Evidence
New prompt text (search for "Agents can be resumed using the \resume\ parameter")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.