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 v2.1.224 Home All releases olderv2.1.223 v2.1.225newer

Memory writes are scanned for secrets before they land

Not switched on
Useful4 Signal4
Memory

Memory writes get scanned for secrets and refused, naming what matched and that the store is shared.

Secret scanning on memory writes is behind a gate that is false in this build.

Feature flag
tengu_haze_glass Off in both readings

The flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.

This account: off · anonymous baseline: off · compiled default in v2.1.224: on

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.224. It isn't a statement about your account. What a flag value here can and cannot tell you

What

Memory document content is scanned before it is written, and a match refuses the write with a message naming what matched and noting that the store is shared with everyone on the project. The tool's own instructions carry the same rule. Behind tengu_haze_glass, which is false in this build.

Evidence

Never write secrets or credentials into a memory \u2014 the store is shared with every collaborator on the project, and such writes are refused.

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

See this entry in the whole of v2.1.224 →