Prewire · case file · public copy of the record
FILE P396 PREWIRE receipts archive the live wire
CATCH #1096 DETECTED SEP 1, 2026 18:27 UTC
THE CATCHscore 9/10
EXHIBIT 1096 · FLASH
Sep 1, 2026 18:27 UTC github_releases+npm+pages https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md
Claude Code v2.1.257 introduces Claude Fable 5.1 as the new default Fable model with 1M context, new time and timezone settings, and various security and workflow improvements.

✓ VERIFIED — BEAT THE ANNOUNCEMENT BY 0.0H · AUTO-VERIFIED AGAINST ANTHROPIC NEWS

READY TO POST:

claude-code just dropped v2.1.257 with claude fable 5.1 as the new default! 1m context, $10/$50 per mtok. sounds like a big upgrade for fable users.

new claude-code update adds improved security rules, time format settings, and better control over subagent models. looks like a solid set of workflow fixes.

EVIDENCE — the receipts
[MERGED across 3 sources: github_releases, npm, pages]
shared signal: claude-code, claude-fable-5-1

--- npm :: @anthropic-ai/claude-code ---
@anthropic-ai/claude-code 2.1.252 -> 2.1.257: +5 strings, -6 strings, 2 flagged as interesting

[sentence] (2)
  + s description, which is what decides when the skill is used; for an improvement, restate or update the existing skill
  + s entire instructions and the name and description come from the fields above; other frontmatter keys are not kept. For an improvement this replaces the existing skill

--- github_releases :: anthropics/claude-code ---
anthropics/claude-code release: v2.1.257
name: v2.1.257
published: 2026-09-01T17:53:52Z
url: https://github.com/anthropics/claude-code/releases/tag/v2.1.257

## What's changed

- Added Claude Fable 5.1 (`claude-fable-5-1`), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads
- Added "Time format" (`timeFormat`) and `timeZone` settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps
- Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected
- Added `CLAUDE_CODE_SUBAGENT_MODEL_FORCE` to apply `CLAUDE_CODE_SUBAGENT_MODEL` (or the main model) to every subagent, ignoring per-spawn and agent-definition model overrides
- Added `s` in `/effort` to change effort for the current session only, matching `/model`
- Added a `/doctor` warning for stale sandbox mask files left by a killed session
- Added a one-time prompt in auto mode before the first file read outside the working directories, with the option to block such reads (`permissions.blockReadsOutsideWorkingDirectories`)
- Added support for a gateway-supplied `description` on discovered `/model` picker entries (`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY`); entries without one still read "From gateway"
- Fixe

caught by the 20-minute sweep · the live wire · all receipts

THE WIRE RECEIPTS ACCESS @VEDOLOS TERMS PRIVACY break the story before it breaks