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

Claude Code v2.1.178 ·

Scratchpad Directory Always Enabled

Entry
JSON All of v2.1.178
EntryKind: in v2.1.178,
ImprovementsSection of the release
What

The Scratchpad Directory section is now always included in the system prompt when a scratchpad is available. It was previously gated by the tengu_scratch feature flag.

Details
  • Workers can read and write to the scratchpad without permission prompts
  • The section is only added when a scratchpad directory is actually configured and not already present in the system prompt
  • The # Scratchpad Directory marker is used to detect duplicate inclusion
Evidence

Removal of tengu_scratch flag check (search for "# Scratchpad Directory", "Twf"); old code checked pz5() which called Y$("tengu_scratch", !1))

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

Read from
Feature flag
tengu_scratch 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 v2.1.178: off

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 v2.1.178. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns off for tengu_scratch, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns nothing at all, having stopped carrying it for tengu_scratch, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

See this across every release →

See this entry in the whole of v2.1.178 →

Feedback