Claude Code v2.1.223
Claude Code v2.1.223 was released on .
Summary
Claude Code 2.1.223 strengthens security with fixes to permission checks that prevent commands from hiding themselves using tabs or invisible characters, and adds support for GitHub organization wildcards in marketplace settings for easier access control. You'll also notice im...
Release Context
- This was the 178th Claude Code release of 2026 tracked by Havoptic.
- It shipped 1 day after Claude Code v2.1.222 (August 4, 2026).
- Claude Code: ships every 2.1 days — 20 releases in the last month.
Why it matters: Code execution now properly sandboxed from workflows.
Shipped around the same time
Within 3 days of this release, other AI coding tools also shipped:
- Gemini CLI v0.54.4 (August 7, 2026)
- Antigravity CLI v1.1.11 (August 7, 2026)
- OpenAI Codex CLI rust-v0.147.0 (August 7, 2026)
- Gemini CLI v0.54.0 (August 6, 2026)
- OpenAI Codex CLI rust-v0.146.1 (August 5, 2026)
Compare Claude Code: vs OpenAI Codex CLI · vs Cursor · vs Gemini CLI · vs Kiro CLI · vs GitHub Copilot CLI · vs Devin Desktop · vs Antigravity CLI
Release Notes
- Added owner wildcard entries ("owner/") to the strictKnownMarketplaces and blockedMarketplaces managed settings for allowing or blocking all marketplace repos under a GitHub org
- Added a warning when workflow agents, forked skills, slash commands, or resumed background agents' requested subagent model is restricted and the parent model runs instead
- Added a /teleport hint in cloud sessions showing how to continue locally with claude --teleport <session id>
- Fixed a Bash permission bypass where a crafted command could hide parts of itself from permission checks
- Fixed permission prompts so commands padded with tabs or invisible Unicode can no longer hide part of the command from the approval dialog
- Fixed workflow scripts being able to use dynamic import() to run code outside the workflow sandbox
- Fixed a permission gap where an agent definition's bypassPermissions mode ignored the org bypass-permissions disable policy
- Fixed resuming a session after a mid-session /cd coming back empty
- Fixed gateway model discovery hiding Claude models registered under provider-prefixed IDs such as vertexai/claude- or bedrock/anthropic.claude-
- Fixed modelOverrides keys that aren't Anthropic model IDs being treated as the session's canonical model ID; unknown keys are now ignored as documented
- Fixed managed settings: server-delivered settings no longer disable the env block of a machine-local managed-settings.json or MDM profile; admin env now merges per key
- Fixed sandboxed commands failing to start on Linux when sandbox.filesystem.denyWrite covers the working directory
- Fixed forked background agents getting stuck "already resuming" for the rest of the session when rebuilding the fork's parent prompt failed during resume
- Fixed a resumed session failing every turn, or leaving the interactive app on an unresponsive error screen, when its history held a malformed diagnostics attachment
- Fixed a rare hang when parsing unusual git push output
- Changed CLAUDECODEDISABLE1MCONTEXT to hold every Claude model with a native 1M window to 200K via auto-compaction, not just a fixed list; a startup warning now appears when auto-compaction isn't holding the session to 200K
- Changed auto-compact to keep sessions on unrecogni
Other Recent Claude Code Releases
- v2.1.232 (August 13, 2026)
- v2.1.231 (August 13, 2026)
- v2.1.229 (August 12, 2026)
- v2.1.228 (August 11, 2026)
- v2.1.227 (August 10, 2026)
All Claude Code releases · All AI coding tool releases on Havoptic