Source Intelligence

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 v2.1.232 Home All releases olderv2.1.231 v2.1.233newer
Claude Code v2.1.232

Skill names are hashed in telemetry only when they are your own

Under the hood
Useful1 Signal2
Telemetry

Only your own skills get hashed names in telemetry; built-in and MCP skills report real names.

What

The hashed skill name attached to skill telemetry is now emitted only for user-authored skills; MCP, built-in, bundled and official skills already report their real names, so the hash is redundant for them.

Details
  • The hash is included only when the sanitized skill source resolves to "custom".
  • Three fields were added to the telemetry redaction allowlist: skill_name_hashes, parent_skill_name_hash and item_name_hash, used by the plugin name-collision event and by aggregate skill reporting.
Evidence

parent_skill_name_hash

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 v2.1.232 →