v2.1.178 Claude Code Release Notes

Jun 15, 2026

Claude's Analysisby Sonnet 4.6

Tool(param:value) rules now gate on tool inputs — Agent(model:opus) blocks Opus subagents. Breaking: workflow keyword now needs explicit phrases. 13 auth and agent fixes.

Changes

Total Changes (vs Average)

2.2×

Version Type

Patch

Release Focus

Bug Fixes

Days Since Prior Release

Release # This Month

#16 of 19

Bug Fix Ratio

58%

Post-Release Edits

Change Category

Ecosystem Impact

Plugins / Skills has appeared in 3 of the last 10 releases, and MCP in 4. This release's nested .claude/ directory resolution, MCP permission fixes, and marketplace repair continue a sustained buildout of Claude's extensibility layer.

Key Themes

1Parameter-level permission rules|4Subagent reliability and visibility|4Auth token and credential stability|1Breaking: workflow keyword now more specific|4Nested skills and plugin directory improvements

May Help If You've Noticed

Your Claude session crashes on startup in a terminal where you previously ran Claude

Added1 change

•Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents

Improved4 changes

•Improved auto 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
•Improved Remote 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

Fixed14 changes

•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
•Fixed several 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
•Fixed claude 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
•Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning
•Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored
•Fixed vim 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
•[VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task

Changed1 change

•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

Other4 changes

•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/
•/bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title

Improved4 changes

•Improved auto 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

•Improved Remote 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

Fixed14 changes

•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

•Fixed several 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

•Fixed claude 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

•Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning

•Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored

•Fixed vim 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

•[VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task

Other4 changes

•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/

•/bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title

v2.1.178 Claude Code Release Notes

Changes in Claude Code v2.1.178

Added1 change

Improved4 changes

Fixed14 changes

Changed1 change

Other4 changes

v2.1.178 Claude Code Release Notes

Changes in Claude Code v2.1.178

Added1 change

Improved4 changes

Fixed14 changes

Changed1 change

Other4 changes