Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.248entry #641

Claude Code v2.1.248 ·

New patterns for spotting prompt-shaped text in transcripts

Transcript sanitising gained patterns for spotting injected fake instructions and turn boundaries.

Under the hood In Development
JSON All of v2.1.248
Under the hoodTier: how much it should matter to you
3Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Prompt InjectionArea: what it touches
In DevelopmentKind: in v2.1.248,
In DevelopmentSection of the release
What

The transcript sanitiser gains literals for detecting injected instructions: a pattern matching phrases like "use 10k tokens" or "spend 5m tokens", a set of impersonation prefixes, and a list of speaker-like words used to find fake turn boundaries.

Details
  • The patterns are present in the build; where they are applied is not visible from the strings alone, so whether anything currently runs them is undetermined.
Evidence

\b(?:use|spend)\s+(\d+(?:\.\d+)?)\s(k|m|b)\stokens?\b

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

See this entry in the whole of v2.1.248 →

Feedback