npx @buildinternet/releases get claude-code-releasesprompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should blockprompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop earlyclaude-haiku-5-5), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K)agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apartisDeferred to $.tool.register for mods: false lists the tool's schema in the prompt from the start instead of behind tool search← moved the session to the background; if a queued message can't move, ← now stays put and says so/model effort ←/→ wrapping past the highest or lowest level, which could accidentally save Low as a model's default effort/tui disconnecting Claude in Chrome in a session started with --chrome, and ignoring --no-chromeSendMessage in sessions, including resumed ones, where a host, a permission rule or a --tools list removed that tool--agent sessions being told a built-in tool was disabled for the whole session when only their own tool list left it out/clearclaude logs, stop, kill, rm and claude daemon status, stop, uninstall sometimes signing you out when your login had expired or was about toworker being shown as "Agent" when it starts, and the agent detail dialog's title losing the agent type once the agent finishesArtifact("(unprintable path)") while a publish call was still streaming in/ultrareview upload on Linux wrongly refusing some repositories, such as one inside another checkout, over a settings file that "could not be parsed" while a sandboxed command was running/ultrareview upload's refusal over split-index files advising a git command that could leave git unable to read its indexclaude remote-controlclassic.* events being skipped while the plugin hooks worker restarts, which left settings hooks to answer without themclaude plugin test failing for mods that call $.session.append; tests can read the appended rows back with the new mock.sessionclaude plugin eval refusing every Bash-granting run on Macs with Docker Desktop (links under ~/.docker/bin); the refusal now names which part of a credential store held the linkdesktop policy sets Claude Desktop's built-in browser keys, such as builtinBrowserEnabledclaude agents offering bypass permissions that background sessions then ignored when consent was saved only in .claude/settings.local.json or a --settings file; it now asks for consent first, and a session that ignores bypass shows a short notice that stays← backgrounding a session after 10 seconds while the prompt held unsent text (it now cancels the move) or a question was waiting for your answer← had just been pressed to move the session to the background/feedback returning to the drafts list after Ctrl+O or Ctrl+Z while a report was sending, leaving the send impossible to cancelclaude purge stopping silently (exit 0, or a hang in a terminal) when a file or folder could not be deleted; it now deletes the rest, lists what it could not delete, and exits 1>> and << on a line of only spaces leaving the cursor past the end of the line, where a following x deleted nothingV then d) the cursor lands on the first non-blank, and . after it acts on the cursor's line/loop wakeup or scheduled task; Claude is no longer told, and the session stays asleepclaude_code.at_mention logging to emit at most 100 agent and 100 MCP-resource events each time a prompt is read--marketplace <source> to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from iteffort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask forCLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS environment variable to set a longer base delay for the backoff when retrying an overloaded (529) requestprompt.autocomplete, an event a mod hooks to add its own rows to the prompt box's autocomplete list$.model.complete for mods: prompt and system take blocks of text, and cache: true on a block caches the request up to itagent.spawn mod hook, with their run and index, so a mod can refuse thempermissionMode: auto entering auto mode when auto mode is unavailable (disabled by settings, circuit breaker, or a model that doesn't support it)/ultrareview uploads under ~/.claude/seed-adminrm -rf on the 8.3 short name or another alternate Windows spelling of the home folder or a drive not being treated as removing itallowed-tools rule coming back in a later turn when you leave auto mode or plan mode partway through that turnNO_PROXY being ignored for Claude Code's own API requests (sign-in, policy, feedback, artifacts) when HTTPS_PROXY is setclaude plugin commands such as marketplace add and install running before an organization's managed settings had loaded on a first runclaude -p and Agent SDK runs stopping a background command 5 seconds after the final result, and one-shot claude -p runs dropping a scheduled wakeup; both are now waited forclaude --resume session picker or with /resume/resume, /branch or /clear never firing, and saved tasks ignoring later creates and deletes after two writes to the tasks file milliseconds apart/loop silently stopping when the session's process restarted (for example after a crash), because its pending wakeup was lostpages was a list such as "6,9,15"; it now returns an error saying to read each page or range separately/bug, /share and /feedback <text> starting over after Ctrl+O or Ctrl+Z while a report was being sent, and closing as cancelled after it had been sent/remote-env replacing your saved default environment when you pressed Enter right away: the list now opens on your default, and no row has a check mark when no default is in effectf/t/F/T/;/, jumping to, or deleting up to, a match on another line of the prompt/add-dir path box letting Shift+Enter or a paste add a line break, and treating fast-typed "tab", "up" or "down" as those keys! leaving the row selected/cd or a permission change, and added a transcript line when a nested one isn't loaded/name letting Claude invoke a skill that is reserved for the user$.state calls through one const taking minutes to load or validateclaude plugin validate listing a matcher or state value for a hooks module that the engine reads from elsewhereclaude plugin validate listing a $.state value read through a top-level var that was declared again or reassigned; such a module is now refused$ method restarting the hook origin, which could run a guard hook with a .catch above it again without endconfig.set, state.set, env.set or agent.spawn hook that denies after calling next(e) being answered as a refusal: the hook is now reported as failed, by name/theme, the /config Theme menu and the first-run theme step saving a theme before a plugin's config.set hook was askedtool.check hook answering allow running a tool that requires your answer (a question, a plan approval) without showing its dialognext(e) and then failed while the turn was interrupted letting the call through; the call is now rejected$ name that a user-installed mod had added; the mod is now unloaded insteadtool.call hooks seeing some tool calls before misnamed parameters were repaired; a hook now sees the arguments the tool will run with.catch being skipped silently for calls another mod's hook makes beneath the guard's own $ call; its .catch is now askedclaude -p and SDK sessions: the first turn no longer waits for HTTP and SSE MCP servers to answer resources/list<system-reminder> tags written in a hook's output are escaped before they reach Claudefile_path for path, and Write, WebFetch and Read ignore a few stray parameters instead of failing the callFOO=bar python3 app.py runs unpromptedMCP_PROTOCOL_NEGOTIATION=legacy opts outclaude plugin test: a failed expect inside a hook the test registered, or a stub answer the engine refuses, now fails the test instead of passing silentlyname longer than that is ignored@Claude !status in a channel to say when Claude has stopped reading its untagged messages, why, and that an @-mention starts it reading again!fork to a card showing where it came from, the request, and who asked, with a link to the original thread