Source Intelligence
Follow Discord

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.

← All of v2.1.222 Home All releases ←olderv2.1.221 v2.1.223newer→
Claude Code v2.1.222

Skill refusal message tells the model not to work around it

You'll notice
Useful3 Signal0
Skills

Skills you mark as user-only now tell Claude not to reimplement them by hand.

disable-model-invocation
What

When the model tries to invoke a skill marked as user-only, the returned error now appends an explicit instruction against achieving the same thing another way.

Details
  • Applies to skills with disable-model-invocation set.
  • The added sentence closes the loophole of the model reading the skill and re-implementing its steps by hand.
Evidence

Do not replicate this skill's workflow by other means

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.222 →