NachschlagenQuellenregister

Dokumentationerreichbar

Anthropic, Claude Code changelog

code.claude.com (externe Seite)

Die Versionsliste von Claude Code mit Neuerungen, Verbesserungen und Fehlerbehebungen je Fassung, erzeugt aus der Datei CHANGELOG.md im GitHub-Repository. Jede Fassung steht mit ihrem Erscheinungsdatum da, am 09.10.2026 zuoberst 2.1.296 vom selben Tag.

geprüft 17.11.2026

Worauf sich diese Seite beruft, wörtlich, abgerufen am 12.10.2026:

  • Agents and bash commands can run asynchronously and send messages to wake up the main agentbestätigt 17.11.2026
  • pressing Ctrl+B now backgrounds all running foreground tasks simultaneouslybestätigt 17.11.2026
  • Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finishbestätigt 17.11.2026
  • a single list of every Claude Code sessionbestätigt 17.11.2026
  • Background agents now continue running when you press ESC to cancel the main threadbestätigt 17.11.2026
  • approvals granted in a git worktree persist across sessions and worktreesbestätigt 17.11.2026
  • allowing agents to declaratively run in isolated git worktreesbestätigt 17.11.2026
  • now stay alive when idle, are restarted in place to apply Claude Code updatesbestätigt 17.11.2026
  • now appear alongside interactive ones, marked with bgbestätigt 17.11.2026
  • Added /loop command to run a prompt or slash command on a recurring intervalbestätigt 17.11.2026
  • Added cron scheduling tools for recurring prompts within a sessionbestätigt 17.11.2026
  • Added Monitor tool for streaming events from background scriptsbestätigt 17.11.2026
  • Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there toobestätigt 17.11.2026
  • set a completion condition and Claude keeps working across turns until it's metbestätigt 17.11.2026
  • Send background tasks to Claude Code on the web by starting a message with &bestätigt 17.11.2026
  • Expand Remote Control to more usersbestätigt 17.11.2026
  • point it at a marker file to suppress mobile push notifications while you're at the machinebestätigt 17.11.2026
  • Claude Code now continues your session automatically when a claude.ai usage limit resetsbestätigt 17.11.2026
  • when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitelybestätigt 17.11.2026
  • Added background monitor support for plugins via a top-level monitors manifest keybestätigt 17.11.2026
  • Reverted the 2.1.290 fix for cloud sessions staying asleep after a container restart lost a pending /loop wakeup or scheduled taskbestätigt 17.11.2026
  • so runaway or chatty /loop tasks are easy to spotbestätigt 17.11.2026
  • to report more or fewer findings than the usual limitbestätigt 17.11.2026
  • The old cleanup-and-fix behavior has been removedbestätigt 17.11.2026
  • now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixesbestätigt 17.11.2026
  • for a deep cloud reviewbestätigt 17.11.2026
  • comprehensive code review in the cloud using parallel multi-agent analysis and critiquebestätigt 17.11.2026
  • merged five cleanup finders into one, cutting token usage by roughly 25%bestätigt 17.11.2026
  • Changed /code-review to use leaner inline review prompts for every model that has no tuned settings of its own, instead of spawning many review subagentsbestätigt 17.11.2026
  • New native VS Code extensionbestätigt 17.11.2026
  • Added full markdown document view for plans in VS Code, with support for adding comments to provide feedbackbestätigt 17.11.2026
  • Introducing Claude Code for Desktopbestätigt 17.11.2026
  • Claude Code Web: Support for Web -> CLI teleportbestätigt 17.11.2026
  • Added /teleport and /remote-env slash commands for claude.ai subscribers, allowing them to resume and configure remote sessionsbestätigt 17.11.2026
  • Added claude --desktop to open the Claude desktop app on the current directorybestätigt 17.11.2026
  • subcommand for external builds, enabling local environment serving for all usersbestätigt 17.11.2026
  • Added prompt-based stop hooksbestätigt 17.11.2026
  • Added /team-onboarding command to generate a teammate ramp-up guide from your local Claude Code usagebestätigt 17.11.2026
  • Added recap feature to provide context when returning to a sessionbestätigt 17.11.2026
  • Claude Code sessions can now message each other, on any of your machines, with ListAgents to discover thembestätigt 17.11.2026
  • Hardened cross-session messaging: messages relayed via SendMessage from other Claude sessions no longer carry user authoritybestätigt 17.11.2026
  • messages sent to other agent sessions via SendMessage are now evaluated by the permission classifier before dispatchbestätigt 17.11.2026
  • Windows: cross-session messaging is now availablebestätigt 17.11.2026
  • Added attribution setting to customize commit and PR bylinesbestätigt 17.11.2026
  • Added recognition of glab mr create/merge/close/reopen/note/updatebestätigt 17.11.2026
  • Added session URL attribution to commits and PRs created from web sessionsbestätigt 17.11.2026
  • Added attribution.sessionUrl setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessionsbestätigt 17.11.2026
  • the glab CLI config store gets the same sandbox and credential-path protection as ghbestätigt 17.11.2026
  • --from-pr now accepts GitLab merge-request, Bitbucket pull-request, and GitHub Enterprise PR URLsbestätigt 17.11.2026
  • Pasting a PR URL into the /resume search box now finds the session that created that PR (GitHub, GitHub Enterprise, GitLab, and Bitbucket)bestätigt 17.11.2026
  • Added prUrlTemplate setting to point the footer PR badge at a custom code-review URL instead of github.combestätigt 17.11.2026
  • Added a GitLab merge request badge to the footer and statuslinebestätigt 17.11.2026
  • GitHub Actions workflow setup is now optionalbestätigt 17.11.2026
  • Added a warning in /web-setup when the GitHub CLI token lacks the workflow scopebestätigt 17.11.2026
  • Added GitLab support to plugin marketplacesbestätigt 17.11.2026
  • Added GitLab merge request URL support to the --worktree flagbestätigt 17.11.2026
  • send the model no system reminders, and start no background tasksbestätigt 17.11.2026
  • Released TypeScript SDK: import @anthropic-ai/claude-code to get startedbestätigt 17.11.2026
  • SDK: The Claude Code SDK is now the Claude Agent SDKbestätigt 17.11.2026
  • turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run, on Team and Enterprise plansbestätigt 17.11.2026
  • environment variable to include subagent text and thinking in stream-json outputbestätigt 17.11.2026
  • for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps decidingbestätigt 17.11.2026
  • Shared project permission rules can be saved in .claude/settings.jsonbestätigt 17.11.2026
  • syntax to set any setting from the promptbestätigt 17.11.2026
  • Settings file changes take effect immediatelybestätigt 17.11.2026
  • to start Claude Code with all customizationsbestätigt 17.11.2026
  • to limit which API providers a machine may usebestätigt 17.11.2026
  • can no longer turn it on (they can still turn it off)bestätigt 17.11.2026
  • setting to configure Claude’s response languagebestätigt 17.11.2026
  • letting separate teams deploy independent policy fragments that merge alphabeticallybestätigt 17.11.2026
  • present but not applied because a higher-precedence managed source is activebestätigt 17.11.2026
  • Add support for enterprise managed MCP allowlist and denylistbestätigt 17.11.2026
  • Added server-managed settings diagnosticsbestätigt 17.11.2026
  • Deprecated claude config commands in favor of editing settings.jsonbestätigt 17.11.2026
  • Unshipped claude config commandbestätigt 17.11.2026
  • Managed settings can now be set via macOS plist or Windows Registry.bestätigt 17.11.2026
  • enabling enterprise security auditing and optional blocking of settings changesbestätigt 17.11.2026
  • Claude Code refuses to start if its version is outside the allowed rangebestätigt 17.11.2026
  • works in interactivebestätigt 17.11.2026
  • Add support for enterprise managed settings. Contact your Anthropic account team to enable this feature.bestätigt 17.11.2026
  • Removed deprecated Windows managed settings fallback atbestätigt 17.11.2026
  • scope now allows you to add MCP servers to .mcp.json files and commit them to your repositorybestätigt 17.11.2026
  • Remote MCP servers (SSE and HTTP) now support OAuthbestätigt 17.11.2026
  • Added claude mcp login <name> and claude mcp logout <name> to authenticate MCP servers from the CLI without opening the interactive /mcp menubestätigt 17.11.2026
  • Added support for using claude.ai MCP connectors in Claude Codebestätigt 17.11.2026
  • Added pre-configured OAuth client credentials for MCP servers that don’t support Dynamic Client Registrationbestätigt 17.11.2026
  • runs without inherited credential env varsbestätigt 17.11.2026
  • Changed the default limit on MCP tool descriptions sent up front and on MCP server instructions from 2,048 to 4,096 charactersbestätigt 17.11.2026
  • Changed MCP tool descriptions the model loads through tool search to be cut at 16,384 characters instead of 2,048bestätigt 17.11.2026
  • MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL)bestätigt 17.11.2026
  • Added syncing of the skills and plugins enabled on your claude.ai account to terminal sessions signed in with itbestätigt 17.11.2026
  • MCP tool descriptions and server instructions are now capped at 2KB to prevent OpenAPI-generated servers from bloating contextbestätigt 17.11.2026
  • Added CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH to change the 2,048-character cap on MCP tool descriptions and server instructions for every MCP server in the sessionbestätigt 17.11.2026
  • Changed plugin marketplaces whose name imitates a reserved marketplace name to be refused when addedbestätigt 17.11.2026
  • so a package’s install scripts no longer runbestätigt 17.11.2026
  • Added native plugin management supportbestätigt 17.11.2026
  • Changed /recap to decline with a short notice when it arrives relayed from a chat thread (your own included) or from a routine or webhookbestätigt 17.11.2026
  • typed in the terminal, the Claude apps, Remote Control, -p or an SDK host, it runs as beforebestätigt 17.11.2026
  • use SendMessage({to: agentId}) to continue a previously spawned agentbestätigt 17.11.2026
  • Added support for .claude/rules/bestätigt 17.11.2026
  • Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md insteadbestätigt 17.11.2026
  • Claude now automatically records and recalls memories as it worksbestätigt 17.11.2026
  • CLAUDE.md files can now import other files.bestätigt 17.11.2026
  • Improved the external CLAUDE.md imports approval dialog to show which files are being imported and from wherebestätigt 17.11.2026
  • Added support for loading CLAUDE.md files from additional directories specified via --add-dir flagbestätigt 17.11.2026
  • Changed AGENTS.md support to also work on Amazon Bedrock, Google Vertex AI, Microsoft Foundry, LLM gateways, and sessions with telemetry disabledbestätigt 17.11.2026
  • no longer triggers the security approval dialogbestätigt 17.11.2026
  • Changed /memory so that Auto-memory can no longer be turned on from a background sessionbestätigt 17.11.2026
  • Added autoMemoryDirectory setting to configure a custom directory for auto-memory storagebestätigt 17.11.2026
  • Added Memory and Instructions entries to the Customize menubestätigt 17.11.2026
  • index now truncates at 25KB as well as 200 linesbestätigt 17.11.2026
  • the agent is now reminded to compact its MEMORY.md index when nearing the size limitbestätigt 17.11.2026
  • Memory writes that leave a MEMORY.md index over its read limit now produce an explicit errorbestätigt 17.11.2026
  • warning threshold now scales with the model’s context windowbestätigt 17.11.2026
  • letting custom and plugin subagents run without user, project and local CLAUDE.md files; managed policy files still loadbestätigt 17.11.2026
  • /memory command now allows direct editing of all imported memory filesbestätigt 17.11.2026
  • Added memory frontmatter field support for agentsbestätigt 17.11.2026
  • Claude automatically saves useful context to auto-memory. Manage with /memorybestätigt 17.11.2026
  • Project configs & auto memory now shared across git worktrees of the same repositorybestätigt 17.11.2026
  • Added InstructionsLoaded hook event that fires when CLAUDE.md or .claude/rules/*.md files are loaded into contextbestätigt 17.11.2026
  • Added last-modified timestamps to memory filesbestätigt 17.11.2026
  • Added an ISO modified timestamp to memory file frontmatterbestätigt 17.11.2026
  • Added /doctor prompt-auditbestätigt 17.11.2026
  • Quickly add to Memory by starting your message withbestätigt 17.11.2026
  • Fixed issue where pasting could trigger memory or bash mode unexpectedlybestätigt 17.11.2026
  • Removed # shortcut for quick memory entrybestätigt 17.11.2026
  • to be hidden from Claude when auto-injectedbestätigt 17.11.2026
  • Markdown files in .claude/commands/ directories now appear as custom slash commands to insert prompts into your conversationbestätigt 17.11.2026
  • Merged slash commands and skills, simplifying the mental model with no change in behaviorbestätigt 17.11.2026
  • Added SlashCommand tool, which enables Claude to invoke your slash commands.bestätigt 17.11.2026
  • The model can now discover and invoke built-in slash commands likebestätigt 17.11.2026
  • Custom slash commands: Run bash output, @-mention files, enable thinking with thinking keywordsbestätigt 17.11.2026
  • setting to disable inline shell execution in skills, custom slash commands, and plugin commandsbestätigt 17.11.2026
  • Added support for running skills and slash commands in a forked sub-agent context usingbestätigt 17.11.2026
  • to run in the background by default; opt out per skill withbestätigt 17.11.2026
  • frontmatter support for skills and slash commands to override the model effort level when invokedbestätigt 17.11.2026
  • Changed skills without additional permissions or hooks to be allowed without requiring approvalbestätigt 17.11.2026
  • environment variable to hide bundled skills, workflows, and built-in slash commands from the modelbestätigt 17.11.2026
  • skills created or modified in ~/.claude/skills or .claude/skills are now immediately available without restarting the sessionbestätigt 17.11.2026
  • command to re-scan skill directories without restarting the sessionbestätigt 17.11.2026
  • on your machine their bodies don’t run ! commands or expand @ filesbestätigt 17.11.2026
  • skill for building applications with the Claude API and Anthropic SDKbestätigt 17.11.2026
  • Reduced the context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demandbestätigt 17.11.2026
  • Skill character budget now scales with context window (2% of context)bestätigt 17.11.2026
  • listing are now capped at 250 characters to reduce context usagebestätigt 17.11.2026
  • Claude no longer runs the /verify and /code-review skills on its ownbestätigt 17.11.2026
  • Added a tip on Bash permission prompts pointing to auto modebestätigt 17.11.2026
  • Added wildcard pattern matching for Bash tool permissions using * at any position in rulesbestätigt 17.11.2026
  • Ask permissions: have Claude Code always ask for confirmation to use specific tools with /permissionsbestätigt 17.11.2026
  • Auto mode is now available for Max subscribers when using Opus 4.7bestätigt 17.11.2026
  • Auto mode no longer requires --enable-auto-modebestätigt 17.11.2026
  • Auto mode no longer requires opt-in consentbestätigt 17.11.2026
  • interactive terminal and VS Code sessions to start in auto mode when no permission mode is configured, on every plan and providerbestätigt 17.11.2026
  • Releasing a sandbox mode for the BashTool on Linux & Macbestätigt 17.11.2026
  • credentials setting to block sandboxed commands from reading credential files and secret environment variablesbestätigt 17.11.2026
  • since they also match options inserted before the subcommandbestätigt 17.11.2026
  • Added Tool(param:value) syntax for permission rules to match a tool’s input parametersbestätigt 17.11.2026
  • Added wildcard syntax mcp__server__* for MCP tool permissions to allow or deny all tools from a serverbestätigt 17.11.2026
  • denied commands now show a notification and appear in /permissionsbestätigt 17.11.2026
  • Changed auto mode to no longer read autoMode from .claude/settings.local.jsonbestätigt 17.11.2026
  • to add custom rules alongside the built-in list instead of replacing itbestätigt 17.11.2026
  • for auto mode classifier rules that block unconditionally regardless of user intent or allow exceptionsbestätigt 17.11.2026
  • Added claude auto-mode reset to restore the default auto-mode configurationbestätigt 17.11.2026
  • Added auto-mode denial reasons to the transcriptbestätigt 17.11.2026
  • to default to the server-side classifier, which does not charge for classifier overheadbestätigt 17.11.2026
  • Added a prompt before writing to shell startup filesbestätigt 17.11.2026
  • which could otherwise lead to unintended command executionbestätigt 17.11.2026
  • removes the built-in tools that run commands or code and WebFetchbestätigt 17.11.2026
  • New /approved-tools command for managing tool permissionsbestätigt 17.11.2026
  • Renamed /allowed-tools -> /permissionsbestätigt 17.11.2026
  • are now blocked when you didn’t ask to discard local workbestätigt 17.11.2026
  • setting to route all Bash/PowerShell commands through the auto-mode classifierbestätigt 17.11.2026
  • Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rulesbestätigt 17.11.2026
  • scans transcripts for common read-only Bash and MCP tool calls and proposes a prioritized allowlistbestätigt 17.11.2026
  • Released hooks.bestätigt 17.11.2026
  • Added Claude Mods: plugins may now modify deeper behaviorbestätigt 17.11.2026
  • Code Mode, an experimental opt-in in which Claude writes JavaScript to call its toolsbestätigt 17.11.2026
  • (for first-party sessions with telemetry on)bestätigt 17.11.2026
  • Added conditional if field for hooks using permission rule syntaxbestätigt 17.11.2026
  • PreToolUse hooks can now modify tool inputsbestätigt 17.11.2026
  • PostToolUse hooks can now replace tool output for all tools viabestätigt 17.11.2026
  • Added hooks support for skill and slash command frontmatterbestätigt 17.11.2026
  • Added a Hooks dialog to the command menu for viewing hooks and adding, editing, or removing them in user, project, and local settingsbestätigt 17.11.2026
  • Special thanks to community input inbestätigt 17.11.2026
  • a hook that can’t start, times out, or exits with an unexpected code blocks the action instead of letting it throughbestätigt 17.11.2026
  • naming the approval an organization requires for a toolbestätigt 17.11.2026
  • that spawns the command directly without a shell, so path placeholders never need quotingbestätigt 17.11.2026
  • Improvements to plan modebestätigt 17.11.2026
  • Added /plan command shortcut to enable plan mode directly from the promptbestätigt 17.11.2026
  • users can now enter plan mode without approvalbestätigt 17.11.2026
  • the auto-mode classifier judges them insteadbestätigt 17.11.2026
  • setting to customize where plan files are storedbestätigt 17.11.2026
  • Added feedback input when rejecting plans, allowing users to tell Claude what to changebestätigt 17.11.2026
  • Plan mode: introduced new Plan subagentbestätigt 17.11.2026
  • Ask Claude to make a plan with thinking modebestätigt 17.11.2026
  • Claude will now ask you questions more often in plan modebestätigt 17.11.2026
  • Plan Mode now builds more precise plans and executes more thoroughlybestätigt 17.11.2026
  • Sessions are now auto-named from plan content when you accept a planbestätigt 17.11.2026
  • Removed ultraplan featurebestätigt 17.11.2026
  • Added a /doctor check that proposes trimming checked-inbestätigt 17.11.2026
  • Added LSP (Language Server Protocol) tool for code intelligence features like go-to-definition, find references, and hover documentationbestätigt 17.11.2026
  • Introducing the Explore subagentbestätigt 17.11.2026
  • Bash deny rules now match commands wrapped inbestätigt 17.11.2026
  • Skills and slash commands can now set disallowed-tools in frontmatter to remove tools from the model while the skill is activebestätigt 17.11.2026
  • explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored)bestätigt 17.11.2026
  • Released output stylesbestätigt 17.11.2026
  • Added support for Claude Skillsbestätigt 17.11.2026
  • Added research preview agent teams feature for multi-agent collaborationbestätigt 17.11.2026
  • Un-deprecate output styles based on community feedbackbestätigt 17.11.2026
  • The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlierbestätigt 17.11.2026
  • Changed interactive sessions on third-party providers or with telemetry off to start in auto modebestätigt 17.11.2026
  • Improved /code-review --comment to post findings on GitLab merge requests via glab mr notebestätigt 17.11.2026
  • they now link to the gitlab.com issuebestätigt 17.11.2026
  • Fixed /autofix-pr reportingbestätigt 17.11.2026
  • breaking headless sessions until restartbestätigt 17.11.2026
  • Fixed --json-schema silently producing unstructured output when the schema was invalidbestätigt 17.11.2026
  • Fixed an active /goal being lost when resumingbestätigt 17.11.2026
  • Fixed scheduled tasks (/loop with an interval, reminders) silently not coming back on resume once the conversation was compacted; covers compactions made from this version onbestätigt 17.11.2026
  • Fixed scheduled tasks set in the foreground never firing after abestätigt 17.11.2026
  • they now classify as task notifications and can no longer approve a pending actionbestätigt 17.11.2026
  • previously only Read loaded thembestätigt 17.11.2026
  • Fixed path-scoped rules and nested CLAUDE.md files not loading when Claude views a file with a single-file cat, head, tail, sed -n or grep command in the Bash tool instead of the Read toolbestätigt 17.11.2026
  • brace expansion is now budget-boundedbestätigt 17.11.2026
  • Improved the large CLAUDE.md startup notice to also count instruction files togetherbestätigt 17.11.2026
  • invisible characters and tags that imitate Claude Code’s own markup are neutralized inbestätigt 17.11.2026
  • from outside the project being skipped without ever showing the external-imports approval promptbestätigt 17.11.2026
  • reviews now use its version from the base branchbestätigt 17.11.2026
  • on custom commands and skills being ignored in interactive sessionsbestätigt 17.11.2026
  • frontmatter on custom commands, skills, and subagents being ignored on models whose default effort is still pinnedbestätigt 17.11.2026
  • raised the listing cap from 250 to 1,536 charactersbestätigt 17.11.2026
  • when your project or user skills include one named verify, Claude is now told to run it right before committing, except for docs-only and tests-only commitsbestätigt 17.11.2026
  • a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expiresbestätigt 17.11.2026
  • Changed claude -p and Agent SDK sessions with no permission mode to start in default mode on third-party providers, with telemetry off or on a fresh installbestätigt 17.11.2026
  • Changed claude -p and Python Agent SDK sessions on third-party providers or with telemetry off to start in auto mode when no permission mode is configuredbestätigt 17.11.2026
  • row to /config for turning idle compaction off or back onbestätigt 17.11.2026
  • Changed local session transcripts to also record each API request’s system prompt, tools and parametersbestätigt 17.11.2026
  • Fixed scheduled tasks refusing their own configured prompt as untrusted inputbestätigt 17.11.2026
  • Changed mods’ settings.read hooks to receive each settings layer and rewrite the merged settings, so a managed mod can make an organization’s setting a ceilingbestätigt 17.11.2026
  • including the cleanupPeriodDays the retention sweep usesbestätigt 17.11.2026
  • to no longer keep their allowed-tools when your organization’s managed settings set allowManagedPermissionRulesOnlybestätigt 17.11.2026
  • Changed UserPromptSubmit hooks to run before a skill or custom slash command expands, so a hook that blocks the prompt now also stops its embedded shell commandsbestätigt 17.11.2026
  • updatedInput from PreToolUse and PermissionRequest hooks is now validated like Claude’s own input: unknown keys are dropped, and input the tool rejects denies the callbestätigt 17.11.2026
  • when a plugin that runs first skips one of your mod’s hooks, naming the event and the pluginbestätigt 17.11.2026
  • Changed a mod hook’s .catch handler to run only when the hook throws or times outbestätigt 17.11.2026
  • when the hook cannot be handed them or cannot hand back its answerbestätigt 17.11.2026
  • a tool that already ran has its result withheldbestätigt 17.11.2026
  • Changed the turn.start mod hook to also hear subagents’ and teammates’ turnsbestätigt 17.11.2026
  • Added support for rewriting a workflow agent’s prompt and model in the agent.spawn mod hook, which could only refuse workflow agents beforebestätigt 17.11.2026
  • Added the prompt.change mod hook, raised when the prompt box’s text changes without a typed editbestätigt 17.11.2026
  • Added e.isReadOnly to a mod’s tool.check event, set when the tool call is read-onlybestätigt 17.11.2026
  • 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 askedbestätigt 17.11.2026
  • to let admins opt SDK managedSettings (parent tier) into the policy mergebestätigt 17.11.2026
  • use deniedMcpServers to keep it offbestätigt 17.11.2026
  • a nested CLAUDE.md over the size limit now loads only its startbestätigt 17.11.2026
  • from Anthropic’s first-party MCP servers at api.anthropic.com to reach Claude in full instead of being cut at 4,096 charactersbestätigt 17.11.2026
  • to run its turn at xhigh effort on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1bestätigt 17.11.2026
  • waits for the real completion instead of fabricating resultsbestätigt 17.11.2026
  • it does not change the model for server-side auto modebestätigt 17.11.2026
  • now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessionsbestätigt 17.11.2026
  • an Owner or Claude Tag admin can let Claude in Slack answer in channels shared with another organization; it’s off by defaultbestätigt 17.11.2026
  • Deprecated fast mode for Opus 4.8 as of October 30, 2026; it will be removed on November 30, 2026.bestätigt 17.11.2026
  • After removal, fast mode requests on Opus 4.8 return an error and do not fall back to standard Opus 4.8.bestätigt 17.11.2026
  • settings fetched from Anthropic’s API now apply without an approval prompt, and a stored copy that doesn’t verify is refusedbestätigt 17.11.2026
  • Changed Claude’s file tools to ask before editing the local copy of your organization’s server-managed settings, as they do for your settings filesbestätigt 17.11.2026
  • Added CLAUDE_CODE_SUBAGENT_EFFORT to set the effort level subagents run at when nothing else names one, instead of inheriting the session’sbestätigt 17.11.2026
  • which turns the ultrathink keyword offbestätigt 17.11.2026
  • Changed ultrathink to run its turn at xhigh effort and show in a rainbow in the chat box, as in the terminalbestätigt 17.11.2026
  • Changed subagents and teammates on a different model from the main conversation to use that model’s saved effort level or its default, instead of the session’s effort levelbestätigt 17.11.2026
  • typed while Claude is working, it raises the rest of that turnbestätigt 17.11.2026
  • Changed the ultrathink rainbow to appear only where the keyword can raise effort, and not when the word is quoted or part of a file pathbestätigt 17.11.2026
  • a change made mid-task now says it may wait for your next message, and the note clears when it no longer appliesbestätigt 17.11.2026
  • Added an effort level to the model picker when you create or edit a routine that runs in the cloudbestätigt 17.11.2026
  • Changed model names and IDs to drop the [1m] suffix and its label on models where the suffix has no effect; the suffix is still acceptedbestätigt 17.11.2026
  • Added the date a stored claude.ai sign-in ends to claude auth status (loginExpiresAt) and to claude -p JSON results (credential_expires_at)bestätigt 17.11.2026
  • Added a one-line stderr warning to claude -p text output, starting 10 days before a stored claude.ai sign-in endsbestätigt 17.11.2026
  • Changed subagents to stop instead of switching models whenbestätigt 17.11.2026
  • Changed background subagents to move a shell command to the background after 3 minutes on all providers, so the prompt cache doesn’t expire while it runsbestätigt 17.11.2026
  • Changed SendMessage so a message to a running background agent arrives earlier: its running command moves to the background, without being stoppedbestätigt 17.11.2026
  • Changed agent tools: lists to take only the named MCP server’s toolsbestätigt 17.11.2026
  • claude mcp serve never offers thembestätigt 17.11.2026
  • row to /tasks that lists finished subagents, so you can reopen one and message it even after it leaves the list or you restartbestätigt 17.11.2026
  • Hardened the Agent tool against indirect prompt injection via content a subagent readbestätigt 17.11.2026
  • with the Bash sandbox on, skills in .claude/skills folders below the starting folder load only if you start Claude Code there or /cd therebestätigt 17.11.2026
  • Changed compaction to send Claude the skill list again afterwards; /reload-skills now sends only new or changed skillsbestätigt 17.11.2026
  • can register at most 1,024 hooks and 16,384 matcher characters per sessionbestätigt 17.11.2026
  • a skill used in the main conversation whose hooks are kept out no longer gets its allowed-toolsbestätigt 17.11.2026
  • refuse a ! shell command that contains raw control characters other than tab and newlinebestätigt 17.11.2026
  • one whose file or folder name has hidden, direction-changing or blank-like charactersbestätigt 17.11.2026
  • Fixed plan mode running a write (an MCP tool’s, a file’s, a shell command’s) that a PreToolUse hook or a mod’s tool.check hook allowedbestätigt 17.11.2026
  • Fixed Claude carrying out an unapproved plan after a window reloadbestätigt 17.11.2026
  • a step interrupted in plan mode now stops with a notice when the session comes back in another permission modebestätigt 17.11.2026
  • Added a one-time note when plan mode won’t ask before most edits or commands because bypass permissions is availablebestätigt 17.11.2026
  • Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier usesbestätigt 17.11.2026
  • Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rulesbestätigt 17.11.2026
  • Added permissions.denyInsteadOfPrompting setting: a tool call that would wait on a permission prompt is denied and the turn continues, in terminal sessions, subagents and teammatesbestätigt 17.11.2026
  • Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox’s file protectionsbestätigt 17.11.2026
  • Changed auto mode in Cowork cloud sessions: a hook’s allow of an MCP tool call now counts as no answer, so the classifier or a permission prompt decidesbestätigt 17.11.2026
  • Changed auto mode with telemetry or feature flags off, including behind LLM gateways: calls the server can’t check are asked about or denied, with no fallback to the built-in classifier; set CLAUDE_CODE_AUTO_MODE_SERVER=0 to keep using it (Bedrock, Vertex and Foundry are unchanged)bestätigt 17.11.2026
  • Changed commands the settings exclude from the sandbox to ask before writing to its write-list paths while the sandbox is enabled but cannot run; the unsandboxed fallback is refused therebestätigt 17.11.2026
  • Changed the dangerous rm and rmdir prompt in bypass permissions mode in the Desktop app and VS Code to deny the command at once with a rewrite hint, so unattended sessions keep goingbestätigt 17.11.2026
  • Fixed project verify skills being rewritten on every session instead of only when a documented command changedbestätigt 17.11.2026
  • Added CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS to change idle compaction’s 200K-token minimumbestätigt 17.11.2026
  • a conversation too long for the new model is now summarized by the previous model firstbestätigt 17.11.2026
  • Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)bestätigt 17.11.2026
  • like other Bash edits, it is no longer restored by /rewindbestätigt 17.11.2026
  • Claude now sees the call and is told its outcome is unknownbestätigt 17.11.2026
  • Added Claude Code cloud sessions and Remote Control permissions to Enterprise custom roles, so Owners can control access to each by rolebestätigt 17.11.2026
  • Changed turning on Cloud sessions or Remote Control in admin settings to ask for confirmation and list the custom roles that have that permissionbestätigt 17.11.2026
  • Changed deniedMcpServers URL entries to also block Anthropic-provided servers whose upstream URL matches, and connectors in cloud sessions and on self-hosted runners, where the session is given the connector’s own URL; otherwise deny a connector by namebestätigt 17.11.2026
  • Added support for MCP tasks in the terminalbestätigt 17.11.2026
  • Changed MCP tasks to work in the terminal without feature-flag fetching (Bedrock, Vertex, Foundry, LLM gateways, DISABLE_TELEMETRY); set CLAUDE_CODE_DISABLE_MCP_TASKS=1 to turn them offbestätigt 17.11.2026
  • when an MCP server runs a tool call as a task, Claude Code moves it to the background right away and tells Claude the result when it finishesbestätigt 17.11.2026
  • Added the CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND environment variable to make Claude Code wait for an MCP task inside its tool call instead of moving it to the background right awaybestätigt 17.11.2026
  • only plugins from an official Anthropic source or a source that managed settings vouch for keep that pre-approvalbestätigt 17.11.2026
  • scripts pass --trust-workspace, which takes no value (put a PR number or base branch before it), or set CLAUDE_CODE_DISABLE_ULTRAREVIEW_TRUST_CHECK=1bestätigt 17.11.2026
  • with CI set they now refuse an untrusted folder at oncebestätigt 17.11.2026
  • Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waitingbestätigt 17.11.2026
  • Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS to limit how long unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) waits out 429 and 529 errorsbestätigt 17.11.2026
  • Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its resetbestätigt 17.11.2026
  • Added a Bash editor with colors, line numbers and a Copy button to the setup script box in cloud environment settingsbestätigt 17.11.2026
  • Added a note to /loop confirmations in cloud sessions that a timer stops with its container, with an offer of a loop that survivesbestätigt 17.11.2026
  • Added a warning to /schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove thembestätigt 17.11.2026
  • Changed self-paced /loop to end when a turn finishes without rescheduling, instead of scheduling a fallback wakeup; set CLAUDE_CODE_LOOP_KEEPALIVE=1 to keep the old behaviorbestätigt 17.11.2026
  • Self-hosted runner: Changed checkout hooks to be stopped after 30 minutes by default, failing the session’s setup; if yours needs longer, raise --checkout-hook-timeout-min or set it to 0bestätigt 17.11.2026
  • Fixed claude -p exiting with code 0 and no output when startup failed; it now prints the error and exits 1bestätigt 17.11.2026
  • Fixed claude -p exiting 0 when a full disk or quota lost its transcript or ~/.claude.json writes; it now prints an error and, in text and json output, exits 1.bestätigt 17.11.2026
  • Fixed claude -p exiting 0 in auto mode when its actions were refused because no safety check was available: text and JSON output now exit 1bestätigt 17.11.2026
  • Fixed Claude deleting your most recently updated /team-onboarding guide when asked to delete one without naming whichbestätigt 17.11.2026
  • Fixed Claude saying a /team-onboarding guide was deleted when the server refused the deletebestätigt 17.11.2026
  • Fixed @-mentioned text files over 256KB being left out silently: Claude is now told the file’s size and to read it in portionsbestätigt 17.11.2026
  • to run at most 24 at a time per session, sub-agents included, plus at most 12 that have waited longer than their event’s timeoutbestätigt 17.11.2026
  • Improved artifact database writes: an update can now remove a single field instead of rewriting the whole documentbestätigt 17.11.2026
  • Improved the error for an artifact database write refused at the database’s size limitbestätigt 17.11.2026
  • Changed what Claude is told after safeguards stop a subagent: retry with a narrower prompt or tell you, instead of doing the work itselfbestätigt 17.11.2026
  • Changed auto mode so that a project’s settings files or a plugin can no longer switch its server-side check back on once you have switched it off outside the projectbestätigt 17.11.2026
  • Changed a session’s exact Bash or PowerShell ask rule to be refused, not asked about, when a broader deny rule covers the commandbestätigt 17.11.2026
  • $8/$40 per Mtok with $0.20/Mtok cache readsbestätigt 17.11.2026
  • Changed saved Fable 5.1 model picks to move tobestätigt 17.11.2026
  • on Pro and Max plans at once, on Team and Enterprise plans once your organization allows itbestätigt 17.11.2026
  • to use the same review engine as /code-review mediumbestätigt 17.11.2026
  • back to a fast single-pass reviewbestätigt 17.11.2026
  • for the multi-agent review at a chosen effort levelbestätigt 17.11.2026
  • Changed /review to be an alias of /code-review, which reviews the current diff or a PRbestätigt 17.11.2026
  • Changed /review <pr> back to a fast single-pass reviewbestätigt 17.11.2026

Projektanweisung im Glossar01 Was Claude Code ist03 Bedienung im Terminal04 Die Werkzeuge des Agenten05 Kontext und Sitzungen06 Modelle und Aufwand08 Berechtigungen und Rechtemodi08 Vom Prototyp zum Produkt09 Bestehenden Code verstehen09 Sandbox und Isolierung11 Eine Wissensbasis aufbauen12 Rechner und Netz pflegen14 Anweisungen und Gedächtnis15 Einstellungen und Ebenen16 Rechte und Sandbox17 Skills und Befehle18 Hooks und Mods19 MCP und Plugins20 Subagents21 Parallel arbeiten22 Teams und Workflows23 Plan vor Code24 Test und Spezifikation zuerst25 Prüfen und Review26 Git und Forges27 Übergabe zwischen Sitzungen28 Lange Läufe29 Skripte und CI30 Editor, Desktop, Web und Slack31 Der Harness

Alle Quellen

↑↓ auswählenEnter öffnenDie Suche läuft im Browser. Nichts wird übertragen.