CATCH #2166
DETECTED OCT 19, 2026 22:19 UTC
THE CATCHscore 8/10
EXHIBIT 2166 · FLASH
Oct 19, 2026 22:19 UTC
github_releases+pages
anthropics/claude-code
Anthropic's Claude Code v2.1.304 release adds a guided auto-mode setup, new mod control features, and a managed agent security comparison tool, alongside numerous bug fixes.
READY TO POST:
anthropic's claude code just dropped v2.1.304, bringing a guided auto-mode setup that can learn from your project. seems like they're making auto-mode smarter and easier to use.
devs using claude code, check out the new `decider: "person"` for mod tool checks in v2.1.304 – gives more control over permissions. also, a security tool for managed agents looks interesting.
EVIDENCE — the receipts
[MERGED across 2 sources: github_releases, pages]
shared signal: claude-api, claude-code
--- github_releases :: anthropics/claude-code ---
anthropics/claude-code release: v2.1.304
name: v2.1.304
published: 2026-10-19T21:34:39Z
url: https://github.com/anthropics/claude-code/releases/tag/v2.1.304
## What's changed
- Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin
- Added `decider: "person"` to a mod's `tool.check` answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked
- Added `e.isReadOnly` to a mod's `tool.check` event, set when the tool call is read-only
- Added `/auto-mode-setup`: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions
- Added `/claude-api managed-agents-secure`, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything
- Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)
- Added a warning on Pro and Max plans when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit: resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it
- Fixed the organization policy not refreshing until the hourly check after approving an `ANTHROPIC_API_KEY` at startup or switching "Use custom API key" in `/config`
- Fixed sandboxed commands failing to start on Linux when a `sandbox.filesystem.denyRead` glob contains brackets that are not a character class, such as a `[user-id]` route folder
- Fixed `rm -r` of a mounted drive or a folder at its top level (`/Volumes`, `/media`, WSL's `/mnt/c`) not getting the safety prompt that `rm -rf /Applications` gets
- Fixed `CLAUDE_CODE_TRANSCRIPT_
caught by the 20-minute sweep ·
the live wire · all receipts