AddedTool(param:value) syntax for permission rules to match a tool's input parameters (with `*` wildcard), e.g. `Agent(model:opus)` to block Opus subagents
~changed 5
Agent teams: removed the `TeamCreate` and `TeamDelete` tools. With `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` set, every session now has one implicit team — spawn teammates directly with the Agent tool's `name` parameter, no setup step needed. The `team_name` parameter on the Agent tool is still accepted but ignored.
Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as `<dir>:<name>` so both stay available
Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing `.claude/workflows/`
Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word
/bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title
↑improved 4
Improvedauto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review
Improved/doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names
Improved the skill listing truncation warning to show how many skill descriptions are affected
ImprovedRemote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy
✓fixed 14
Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process
Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login
Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs
Fixedseveral subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch
Fixedclaude agents workers failing with `401 Invalid bearer token` when the daemon was started from a shell with a custom API gateway via `ANTHROPIC_BASE_URL` and `ANTHROPIC_AUTH_TOKEN`
Fixed compaction not honoring `--fallback-model`: compaction now falls back to the configured fallback model chain on overload or model-availability errors
Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration
Fixed background sessions created with `/bg` or `←←` after a turn finished showing "Working" forever in the agents list
Fixed Linux sandbox failing to start when `.claude/skills` or `.claude/hooks` is a symlink
FixedCLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning
FixedMCP server-level specs (`mcp__server`, `mcp__server__*`, `mcp__*`) in subagent `disallowedTools` being silently ignored
Fixedvim mode undo: `u` now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step
Fixed statusline links with custom URI schemes (e.g. `vscode://`) not opening when clicked in `claude agents`
VSCodeFixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task
