ClaudeKit — Claude Code tools, guides, updates

[Update] Claude Fable 5 and Claude Mythos 5

Tue, 09 Jun 2026 00:00:00 GMT

Anthropic released Claude Fable 5 and Claude Mythos 5 on June 9, 2026. Fable 5 is a Mythos-class model made safe for general use — state-of-the-art on nearly all tested benchmarks, with the `claude-fable-5` model ID. Mythos 5 is identical with cybersecurity safeguards lifted, available in limited release through Project Glasswing. Both support a 1M token context window and up to 128k output tokens by default, priced at $10/$50 per MTok. When a safety classifier declines a request, the Messages API returns stop_reason: "refusal" as an HTTP 200, and the fallbacks parameter (beta) or SDK middleware retries on another Claude model.

[Update] Claude Code 2.1.169

Mon, 08 Jun 2026 00:00:00 GMT

The new `--safe-mode` flag (and `CLAUDE_CODE_SAFE_MODE` env) starts Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting, and `/cd` moves a session to a new working directory without breaking the prompt cache. `disableBundledSkills` (and `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS`) hides bundled skills, workflows, and built-in slash commands from the model. Fixes for enterprise managed MCP policies (`allowedMcpServers`/`deniedMcpServers`) not being enforced on reconnect or IDE-typed configs, Up/Down arrows jumping past wrapped rows of a long input, a 30-50ms per-turn UI stall on macOS with claude.ai credentials, and `claude -p` being slow on Windows (regression in 2.1.161) also land.

[Update] Claude Code 2.1.166

Sat, 06 Jun 2026 00:00:00 GMT

The new `fallbackModel` setting takes up to three fallback models tried in order when the primary is overloaded or unavailable, and `--fallback-model` now also applies to interactive sessions. Deny rules accept glob patterns in the tool-name position (`"*"` denies all tools), and messages relayed via `SendMessage` from other Claude sessions no longer carry user authority. `MAX_THINKING_TOKENS=0`, `--thinking disabled`, and the per-model thinking toggle now disable thinking on default-thinking models via the Claude API, and Claude Code retries a turn once on the fallback model when the API returns an unexpected non-retryable error. Plus fixes for remote sessions stuck during worker registration, JetBrains 2026.1+ terminal flicker, Shift+non-ASCII characters dropped under the Kitty keyboard protocol, and managed settings whose single invalid entry silently disabled enforcement of the rest.

[Update] Claude Code 2.1.163

Thu, 04 Jun 2026 00:00:00 GMT

Claude Code 2.1.163 lands enterprise version pinning, plugin listing, and several agent-loop ergonomics. `requiredMinimumVersion` and `requiredMaximumVersion` managed settings refuse to start outside an approved range, `/plugin list` lists installed plugins with `--enabled`/`--disabled` filters, and Stop and SubagentStop hooks can return `hookSpecificOutput.additionalContext` to keep the turn going. stdio MCP servers now receive `CLAUDE_CODE_SESSION_ID` on `--resume`. The release also fixes `claude -p` hanging on backgrounded commands, a `$TMPDIR` override regression from 2.1.154, org-managed permission rules missing parts of startup, and a broad sweep of background-session, Windows, and terminal-UI bugs.

[Update] Claude Code 2.1.162

Wed, 03 Jun 2026 00:00:00 GMT

`claude agents --json` now includes `waitingFor` showing what a waiting session is blocked on, and `--tools` finally provides the dedicated Grep/Glob tools on native builds when you list them. Slash command autocomplete clicks now fill the prompt instead of running immediately, and Remote Control moves from a startup message to a persistent footer pill. Plus a round of fixes for silent startup hangs on read-only config dirs, WebFetch permission rules being skipped for preapproved domains, and Windows permission rules never matching backslash paths.

[Update] Claude Code 2.1.160

Tue, 02 Jun 2026 00:00:00 GMT

Claude Code 2.1.160 lands a security tightening and a workflow-trigger rename. The release adds confirmation prompts before writes to shell startup files (`.zshenv`, `.zlogin`, `.bash_login`) and build-tool config files that grant code execution (`.npmrc`, `bunfig.toml`, and similar), and renames the dynamic-workflow trigger keyword from `workflow` to `ultracode`. Edit no longer requires a separate Read after a single-file `grep`/`egrep`/`fgrep`, and the release lands a broad sweep of `claude agents`, background-session, Windows/WSL clipboard, voice-mode, and auto-mode classifier fixes.

[Update] Claude Code 2.1.161

Tue, 02 Jun 2026 00:00:00 GMT

`OTEL_RESOURCE_ATTRIBUTES` values are now included as labels on metric datapoints so usage can be sliced by custom dimensions like team or repo, and a failed Bash in a parallel tool batch no longer cancels its siblings. Fullscreen Linux clipboard now uses `wl-copy`/`xclip`/`xsel` and copies to both the clipboard and PRIMARY selection. Plus fixes for `claude mcp` printing secrets to the terminal and the `forceLoginOrgUUID`/`forceLoginMethod` managed-settings regression (2.1.146) that blocked Bedrock, Vertex, Foundry, and Mantle sessions.

[Tool] Herdr

Tue, 02 Jun 2026 00:00:00 GMT

A terminal-native agent multiplexer in a single Rust binary. Herdr combines tmux-style session persistence and pane splits with agent awareness — a sidebar that shows whether each pane's agent is idle, working, blocked, or done — for Claude Code and other CLI agents. The direct Claude Code integration (`herdr integration install claude`) adds full state detection, semantic state forwarding over a local socket API, and agent-session restoration after a server restart.

[Update] Claude Code 2.1.157

Fri, 29 May 2026 00:00:00 GMT

Claude Code 2.1.157 auto-loads plugins from `.claude/skills` directories with no marketplace required, adds `claude plugin init ` to scaffold a new plugin in place, and ships autocomplete for `/plugin` arguments. `claude agents` dispatched sessions now honor the `agent` field in `settings.json`, `EnterWorktree` can switch between Claude-managed worktrees mid-session, and worktrees are left unlocked when the agent finishes. The release also fixes a broad set of bugs across background sessions, `--resume`, worktrees, the `/model` picker, terminal rendering, WSL image paste, and the VS Code / Cursor / Windsurf integrated terminals.

[Update] Claude Code 2.1.153

Thu, 28 May 2026 00:00:00 GMT

`/model` now saves your selection as the new-session default (matching the IDE); `s` in the picker switches the current session only — reversing the 2.1.144 `d` behavior and requiring a keybinding rename. Security fixes close a regression where a custom API gateway could receive the user's Anthropic OAuth credential, and subagent frontmatter MCP servers now respect `--strict-mcp-config` and enterprise managed policies. Other fixes cover `skipLfs` for `github`/`git` marketplace sources, `COLUMNS`/`LINES` env vars in status line, macOS Privacy & Security persistence, background sessions, and the Windows installer.

[Update] Claude Code 2.1.154

Thu, 28 May 2026 00:00:00 GMT

Claude Code 2.1.154 brings Opus 4.8 (now defaulting to high effort, with `/effort xhigh` for your hardest tasks) and dynamic workflows (`/workflows`) to Claude Code. Fast mode on Opus 4.8 ships at 2x the standard rate for 2.5x the speed, and the lean system prompt becomes the default for most models. It also adds `! ` background shell sessions in `claude agents`, plugin `defaultEnabled: false`, a cleanup-only `/simplify`, and a broad sweep of background-session, security, and terminal-UI bug fixes.

[Update] Claude Opus 4.8

Thu, 28 May 2026 00:00:00 GMT

Claude Opus 4.8 builds on Claude Opus 4.7 with improvements across benchmarks and is a more effective collaborator, available today for the same price. It targets long-horizon agentic coding with better long-context handling and compaction recovery, more reliable effort calibration, and better tool triggering. The model ID is claude-opus-4-8; it supports the 1M token context window by default on the Claude API, Amazon Bedrock, and Vertex AI, with 128k max output tokens.

[Update] Dynamic workflows in Claude Code

Thu, 28 May 2026 00:00:00 GMT

Claude breaks a problem into subtasks and fans them out across tens to hundreds of subagents running in parallel, dynamically writing orchestration scripts that run in a single session and checking its work before anything reaches you. It targets broad work like codebase-wide bug hunts and security audits and large migrations spanning thousands of files, verifying each result before folding it into the final answer. Available as a research preview on Max, Team, and Enterprise plans.

[Tool] LLM Wiki

Thu, 28 May 2026 00:00:00 GMT

A cross-platform desktop application implementing Andrej Karpathy's llm-wiki.md pattern. Instead of traditional RAG that retrieves and answers from scratch every time, the LLM incrementally builds and maintains a persistent wiki from your sources. A built-in local HTTP API and a companion agent skill let Claude Code query your wiki — "what does my LLM Wiki say about X."

[Update] Claude Code 2.1.152

Wed, 27 May 2026 00:00:00 GMT

`/code-review --fix` now applies review findings to the working tree, and `/simplify` is folded into it. New: `disallowed-tools` in skill and slash-command frontmatter, `/reload-skills`, `SessionStart` `reloadSkills` and `sessionTitle`, and a `MessageDisplay` hook event. An unfound primary model now switches the session to `--fallback-model` instead of failing every request, and Auto mode no longer requires opt-in. Other fixes cover Vim NORMAL-mode `/` reverse history, `/usage` including large session files, plugin MCP dedup, remote MCP under egress proxy, markdown tables, and the post-response timer waiting for backgrounded agents.

[Update] Claude Code 2.1.149

Fri, 22 May 2026 00:00:00 GMT

`/usage` now breaks limit consumption down by skills, subagents, plugins, and per-MCP-server cost. The `/diff` detail view is keyboard-scrollable, markdown output renders GFM task lists as checkboxes, and enterprise gets the new `allowAllClaudeAiMcps` managed setting. Four permission-model gaps are closed, along with `find` exhausting the macOS file/vnode table and a wide bug-fix sweep across the transcript view, `/feedback`, `/insights`, `/config`, and the status bar.

[Tool] CC Workflow Studio

Fri, 22 May 2026 00:00:00 GMT

Design workflows on a canvas in VS Code and export them as Markdown your AI agent already understands — skills, commands, and agents for Claude Code, Cursor, Copilot, and more. An MCP server runs in the background so you can refine workflows in natural language with 'Edit with AI'.

[Update] Claude Code 2.1.147

Thu, 21 May 2026 00:00:00 GMT

Added the `Workflow` tool for deterministic multi-agent orchestration, off by default and enabled with `CLAUDE_CODE_WORKFLOWS=1`. Pinned background sessions in `claude agents` now stay alive when idle and are restarted in place to apply updates. Renamed `/simplify` to `/code-review` — it now reports correctness bugs at a chosen effort level with `--comment` for inline PR comments. REPL and Workflow tool sandboxes are hardened, the auto-updater reports error category and OS code on failure, and a managed-settings bypass was closed where `forceLoginOrgUUID` and `forceLoginMethod` weren't enforced against third-party-provider and API-key sessions.

[Update] Claude Code 2.1.144

Tue, 19 May 2026 00:00:00 GMT

Added `/resume` support for background sessions (marked `bg` in the picker). `/model` now changes the current session only — press `d` in the model picker for the new-session default. Renamed "extra usage" to "usage credits" (`/extra-usage` → `/usage-credits`, old name still works). 50+ bug fixes including startup hanging up to 75s on unreachable `api.anthropic.com`, garbled terminal output after window resize, `/model` changes not applying after startup, MCP `tools/list` pagination returning only the first page, and a regression where the Skill tool failed in headless mode.

[Update] Claude Code 2.1.145

Tue, 19 May 2026 00:00:00 GMT

Added `claude agents --json` to list live sessions as JSON for scripting. `claude_code.tool` OTEL spans now include `agent_id` and `parent_agent_id` so background subagent traces nest correctly. Status line JSON now includes GitHub repo and PR information, and `/plugin` Discover/Browse screens show commands, agents, skills, hooks, and MCP/LSP servers before installation. Fixed a permission-prompt bypass where bare variable assignments to non-allowlisted environment variables in Bash were auto-approved, along with MCP slash-command validation, spinner freezing after terminal resize, and the Read tool now returning a truncated PARTIAL view instead of a hard error on oversized reads.

[Update] Claude Managed Agents — Self-hosted sandboxes and MCP tunnels

Tue, 19 May 2026 00:00:00 GMT

Claude Managed Agents now supports self-hosted sandboxes (public beta) and MCP tunnels (research preview). The agent orchestration loop stays on Anthropic infrastructure while tool execution runs in customer infrastructure or with managed sandbox providers — Cloudflare, Daytona, Modal, Vercel — and agents reach private-network MCP servers through a lightweight gateway with a single outbound connection, no inbound firewall rules required.

[Guide] Claude Code `/goal` — running auto-continuation safely

Sat, 16 May 2026 00:00:00 GMT

Claude Code `/goal` — running auto-continuation safely — Claude Code practical guide (6 min)

[Update] Claude Code 2.1.143

Fri, 15 May 2026 00:00:00 GMT

Added plugin dependency enforcement (`claude plugin disable`/`enable` understand dependency chains), projected context cost in the `/plugin` marketplace browse pane, a `worktree.bgIsolation: "none"` setting for repos where worktrees are impractical, `-ExecutionPolicy Bypass` for the PowerShell tool, model and effort preservation across background-session wakeups, and auto mode in the Shift+Tab cycle. Bug fixes cover a corrupt `.credentials.json` hanging startup, stop hooks looping forever, macOS background sessions failing under Full Disk Access folders, and `git worktree remove` no longer falling back to `rm -rf`.

[Update] Claude Code 2.1.142

Thu, 14 May 2026 00:00:00 GMT

Added new `claude agents` flags — `--add-dir`, `--settings`, `--mcp-config`, `--plugin-dir`, `--permission-mode`, `--model`, `--effort`, and `--dangerously-skip-permissions` — to configure dispatched background sessions. Fast mode now uses Opus 4.7 by default (set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1` to pin to Opus 4.6). Plugins with a root-level `SKILL.md` and no `skills/` subdirectory are now surfaced as a skill, the `/plugin` details pane and `claude plugin details` show LSP servers a plugin provides, and `/web-setup` warns before replacing an existing GitHub App connection. Bug fixes span `MCP_TOOL_TIMEOUT` not raising the per-request fetch timeout for remote HTTP and SSE MCP servers, background sessions disappearing and daemon reconnect failing after macOS sleep/wake, the daemon not exiting cleanly after `brew upgrade`, plus a wide sweep of `claude agents`, plugin, session-title, and UI regressions.

[Update] Claude Code 2.1.141

Wed, 13 May 2026 00:00:00 GMT

Added `terminalSequence` to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal, `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` to clone GitHub plugin sources over HTTPS instead of SSH, `ANTHROPIC_WORKSPACE_ID` for workload identity federation, and `claude agents --cwd ` to scope sessions to a directory. `/feedback` can now include recent sessions (last 24 hours or 7 days), and the Rewind menu adds "Summarize up to here" to compress earlier context. Bug fixes span background side-queries sending an unavailable Haiku model ID on Bedrock/Vertex/Foundry/gateway, Remote Control MCP connectors failing with 401 during worker token rotation, `claude plugin install` failing on stale marketplace refs, MCP HTTP/SSE 403s being shown as `failed` instead of `needs auth`, and a wide sweep of auth, session, MCP, plugin, and UI regressions.

[Skill] Google Skills

Wed, 13 May 2026 00:00:00 GMT

Agent Skills for Google products and technologies — maintained by Google. The repo ships 13 skills: 7 foundational (Gemini API, AlloyDB, BigQuery, Cloud Run, Cloud SQL, Firebase, GKE basics), 3 recipes (Google Cloud onboarding, auth, network observability), and 3 Well-Architected Framework skills (security, reliability, cost optimization), so Claude Code pulls in Google Cloud guidance automatically when those topics come up.

[Update] Claude Code 2.1.140

Tue, 12 May 2026 00:00:00 GMT

Agent tool `subagent_type` matching now accepts case- and separator-insensitive values (e.g. "Code Reviewer" resolves to `code-reviewer`), and plugins now warn when a default component folder (e.g. `commands/`) is silently ignored because `plugin.json` sets the matching key. Bug fixes cover `/goal` silently hanging under `disableAllHooks` / `allowManagedHooksOnly`, a settings hot-reload regression on symlinked files, `claude --bg` connection drops at idle-exit, remote managed settings not retrying on 401, the managed `extraKnownMarketplaces` auto-update policy not being persisted, `Read` tool validation on whitespace-padded `offset` strings, and a Windows event-loop stall caused by missing executables.

[Guide] Build Your Own MCP Server

Tue, 12 May 2026 00:00:00 GMT

Build Your Own MCP Server — Claude Code advanced guide (25 min)

[Tool] Firecrawl

Tue, 12 May 2026 00:00:00 GMT

🔥 The API to search, scrape, and interact with the web for AI. Three integrated capabilities — Search, Scrape, Interact — exposed through one API. Open source under AGPL-3.0 and self-hostable via docker-compose, the engine also powers the firecrawl.dev cloud SaaS run by the same team.

[MCP] Firecrawl MCP

Tue, 12 May 2026 00:00:00 GMT

🔥 Official Firecrawl MCP Server — Adds powerful web scraping and search to Cursor, Claude and any other LLM clients. Exposes 12+ tools spanning single-page scrape, batch processing, site crawl, search, structured extraction, autonomous research agent, and interactive page automation, returning clean LLM-ready markdown.

[MCP] Perplexity MCP

Tue, 12 May 2026 00:00:00 GMT

The official MCP server implementation for the Perplexity API Platform. Provides AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API.

[Update] Claude Code 2.1.139

Mon, 11 May 2026 00:00:00 GMT

Adds the agent view (Research Preview) for tracking every Claude Code session in one place, and a `/goal` command that keeps Claude working across turns until a completion condition is met. Hooks gain an exec form (`args: string[]`) and a `PostToolUse` `continueOnBlock` option, MCP stdio servers now receive `CLAUDE_PROJECT_DIR`, and `/mcp` Reconnect picks up `.mcp.json` edits without a restart. Note: Remote Control, `/schedule`, claude.ai MCP connectors, and notification preferences are now disabled whenever `ANTHROPIC_API_KEY` / `apiKeyHelper` / `ANTHROPIC_AUTH_TOKEN` is set, even alongside a Claude.ai login.

[Update] Agent view in Claude Code

Mon, 11 May 2026 00:00:00 GMT

Agent view is a centralized interface inside the Claude Code CLI for managing multiple concurrent agent sessions. Now in Research Preview, it lets developers see which agents need input, are actively working, or have completed tasks — and scale up background work via peek, `/bg`, and `claude --bg`.

[Update] Claude Platform on AWS is now generally available

Mon, 11 May 2026 00:00:00 GMT

The Claude Platform on AWS — Anthropic-operated, accessed via AWS IAM with CloudTrail audit logging and a single AWS invoice — is generally available. AWS customers get day-one access to all native Claude API features, including Claude Managed Agents (beta), Advisor strategy (beta), Files API (beta), Skills (beta), and the MCP connector (beta), with Claude Opus 4.7, Sonnet 4.6, and Haiku 4.5 available at launch.

[Guide] Hidden Claude Code commands you actually want to use

Sat, 09 May 2026 00:00:00 GMT

Hidden Claude Code commands you actually want to use — Claude Code practical guide (7 min)

[Plugin] Codex Plugin for Claude Code

Sat, 09 May 2026 00:00:00 GMT

Use Codex from Claude Code to review code or delegate tasks. An OpenAI-published plugin that exposes standard reviews, adversarial reviews, and task delegation as slash commands, plus a Codex subagent and background-job tracking.

[Skill] Find Skills

Sat, 09 May 2026 00:00:00 GMT

A meta-skill that activates when users ask "how do I do X" or "is there a skill that can…", then searches the open agent skills ecosystem and walks the user through installation.

[Skill] Graphify

Sat, 09 May 2026 00:00:00 GMT

Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

[Update] Claude Code 2.1.136

Fri, 08 May 2026 00:00:00 GMT

Session quality survey is re-enabled for OTEL enterprises via `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL`, and `settings.autoMode.hard_deny` lets classifier rules block actions unconditionally. WSL2 image paste now falls back to PowerShell when xclip/wl-paste are unavailable. Plus a wide round of fixes — MCP servers disappearing after `/clear`, login loops from concurrent OAuth token writes, and plan mode failing to block writes when an `Edit(...)` allow rule matched.

[Update] Claude Code 2.1.132

Thu, 07 May 2026 00:00:00 GMT

`CLAUDE_CODE_SESSION_ID` is now exposed to Bash subprocesses, and `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1` lets you opt out of the fullscreen renderer. Plus a wide round of stability fixes — graceful shutdown on external SIGINT, blank fullscreen after sleep/wake, 10GB+ RSS growth from stdio MCP servers, scroll regressions in Cursor/VS Code/JetBrains terminals, and Bedrock/Vertex 400s when `ENABLE_PROMPT_CACHING_1H` is set.

[Update] Claude Code 2.1.133

Thu, 07 May 2026 00:00:00 GMT

A new `worktree.baseRef` setting (`fresh` | `head`) lets you choose whether worktrees branch from `origin/` or local `HEAD`, and hooks and Bash commands can now read the active effort level via `$CLAUDE_EFFORT`. Plus fixes for a refresh-token race that dead-ended parallel sessions at 401, MCP OAuth ignoring `HTTP(S)_PROXY`/mTLS across discovery and token refresh, and subagents failing to discover project, user, or plugin skills.

[Update] Claude Code 2.1.129

Wed, 06 May 2026 00:00:00 GMT

`--plugin-url` loads a `.zip` plugin straight from a URL, and Homebrew/WinGet installs can self-upgrade in the background. Ctrl+R history is back to searching all projects by default, and Gateway `/v1/models` discovery is now opt-in via env var. Plus fixes for 1-hour prompt cache TTL silently downgrading, OAuth logouts after wake-from-sleep, and `/context` wasting ~1.6k tokens per call.

[Update] What's new in Claude Managed Agents — Dreaming, Outcomes, Multiagent, Webhooks

Wed, 06 May 2026 00:00:00 GMT

A month after the April 8 beta launch, Managed Agents added two new features and promoted three from research preview to public beta. Dreaming (research preview) curates memory between sessions for self-improvement, and outcomes, multiagent orchestration, memory, and webhooks all ship as public beta.

[Update] Claude Financial Services Agents — 10 templates, Moody's MCP, and 17 data connectors

Tue, 05 May 2026 00:00:00 GMT

Ten ready-to-run financial services agents — pitch builder, KYC screener, month-end closer, and more — ship as plugins in Claude Cowork and Claude Code, and as cookbooks for Claude Managed Agents. A Moody's MCP app brings proprietary credit ratings and data on 600M+ companies, and 17 data partners are integrated alongside.

[Update] Claude for Microsoft 365 — Excel, PowerPoint, and Word now GA, Outlook joins in beta

Tue, 05 May 2026 00:00:00 GMT

The Claude add-ins for Excel, PowerPoint, and Word are generally available on all paid plans, and Claude for Outlook joins in public beta. Once installed, context carries automatically between apps so a model built in Excel can become a PowerPoint deck or a Word memo without re-explaining inputs, assumptions, or calculation flow.

[Plugin] Caveman

Tue, 05 May 2026 00:00:00 GMT

why use many token when few token do trick — a Claude Code skill that cuts output tokens by ~65-75% by talking like caveman.

[Tool] RTK

Tue, 05 May 2026 00:00:00 GMT

A high-performance CLI proxy that compresses dev command output by 60-90% before it reaches the LLM context. Single Rust binary, 100+ supported commands — better reasoning, longer sessions, lower costs.

[Update] Claude Code 2.1.128

Mon, 04 May 2026 00:00:00 GMT

`--channels` now works with console (API key) authentication, and `/mcp` shows per-server tool counts and flags zero-tool servers. `OTEL_*` environment variables no longer leak into subprocesses, and `EnterWorktree` branches from local HEAD as documented. Plus fixes for falsely-blocked 1M-context sessions, parallel shell tool regressions, sub-agent cache misses, and more.

[Guide] Agent Teams

Mon, 04 May 2026 00:00:00 GMT

Agent Teams — Claude Code advanced guide (15 min)

[Update] Claude Code 2.1.126

Fri, 01 May 2026 00:00:00 GMT

Gateway-driven `/model` picker, `claude project purge` for full project state cleanup, OAuth code paste for WSL/SSH/container logins, broader `--dangerously-skip-permissions` scope, plus Windows PowerShell 7 detection, CJK rendering fix, and a long list of OAuth, stream-timeout, and Remote Control fixes.