Claude Code Articles
51 articles across AI Catchup's news, guides, tutorials, and comparisons.
All Claude Code articles
Context Engineering for Claude 5: The New Rules for CLAUDE.md, Skills, and Tools
Context engineering for Claude 5 models means deleting more than you add. Anthropic says it removed over 80% of Claude Code's system prompt for models like Opus 5 and Fable 5 with no measurable loss on its coding evaluations. Replace rules with judgement, examples with well-designed tools, and always-loaded instructions with skills, references, and auto memory.
Prompting Claude Opus 5.5: Delete 'Think Carefully', Name the Finish Line, Start at Medium
Prompt Claude Opus 5.5 by handing over the whole task with a clear finish line, deleting “think carefully” lines, and starting at medium effort. Thinking is always on, so effort is your depth control. Add a CLAUDE.md rule that names when to stop, and set effort explicitly instead of carrying Opus 5 settings over.
Scheduled Claude Agents: Pick the Right Surface, Then Stop Them Failing Silently
Run repository work on Claude Code routines and production automations on Claude Managed Agents scheduled deployments, which add minute-level cron and a dollar cap per run. Whichever surface you pick, apply Anthropic's six rules: bookmarks, unreadable-not-quiet, re-check before posting, confirm then record, read-only preferences, least privilege.
Claude Code Hooks: A Practical Guide With Six Recipes
Claude Code hooks run your own shell commands, HTTP endpoints, MCP tools, prompts, or agents at fixed points in a session. You define them in settings.json, narrow them with matchers, and block actions with exit code 2 or JSON. Exit 0 is not approval, and a hook allow never loosens your deny rules.
How to Build a Claude Code Mod: Files, Hooks, State, and Testing
A Claude Code mod is a plugin whose JavaScript or TypeScript hooks run inside your session. Ask Claude to write one, or create plugin.json, hooks/hooks.json, and a module that exports register. Load it with --plugin-dir, keep state in $.state, then check it with claude plugin validate and claude plugin test.
Claude Code Subagents vs Agent Teams vs Dynamic Workflows: Which Parallel Approach to Use
Claude Code runs parallel work five ways. Use subagents for side tasks inside one session, agent view to dispatch background sessions, agent teams when workers must talk to each other, dynamic workflows for dozens to hundreds of cross-checked agents, and Projects for cloud work spanning days.
Anthropic Releases Claude Haiku 5.5, Its Fastest Model and First Haiku With Effort Levels
Anthropic released Claude Haiku 5.5 on October 7, 2026, its fastest model to date and the first Haiku with effort levels. It scores 72.4% on OSWorld 2.1 against Haiku 4.5's 15.7%, and costs $0.10 per million input and $0.50 per million output tokens for prompts up to 100,000 tokens, 90% less than Haiku 4.5.
Claude Code Mods Let Developers Customize the CLI and Desktop App
Anthropic introduced Claude Code mods as a plugin-based way to customize how Claude Code behaves and looks. Small JavaScript or TypeScript modules can add interface elements, change tool calls, or replace built-in features. Mods run with Claude Code's access to your machine, so review their source before installing.
Claude Code Can Build Evaluations and Improve Apps Against Held-Out Tests
Anthropic's Claude API skill gives Claude Code two evaluation workflows: `/claude-api build-eval` creates an evaluation in a codebase, and `/claude-api hillclimb` proposes one change at a time against it. The hillclimb holds out test cases, reverts changes that do not improve the test set, and reports uncertainty against the baseline.
Claude Sonnet 5.5 Launches With Lower Task Costs and Cursor Support
Anthropic introduced Claude Sonnet 5.5 on September 28 with model ID `claude-sonnet-5-5`. It keeps Sonnet 5's $2 input and $10 output price per million tokens; Anthropic reports output generation more than 30% faster and up to 30% lower cost per task. Cursor lists the model in Settings > Models. Cache reads dropped to $0.10 per million tokens on October 7.
Claude Opus 5.5: Fable 5.1-Level Scores at $4 and $20, With Benchmarks, Effort Costs, and Migration Guide
Claude Opus 5.5, released September 22, 2026, beats Claude Fable 5.1 on every benchmark Anthropic published and costs $4 and $20 per million tokens, 60% less than Fable 5.1. It scores 66.4% on Terminal-Bench 4.0 against 57.9% for GPT-6 Astra. Thinking is always on, the default effort is medium, and four API changes can break Opus 5 code.
Claude Code Adds Configurable AGENTS.md Support
Claude Code 2.1.277 adds AGENTS.md support through a built-in mod. By default Claude Code reads AGENTS.md when a project has no CLAUDE.md or CLAUDE.local.md, and /config changes the behavior. Since 2.1.281 it also works on Amazon Bedrock, Google Vertex AI, Microsoft Foundry, LLM gateways, and with telemetry disabled.
Claude Code Projects Turn One Conversation Into Parallel Cloud Sessions
Anthropic's redesigned Projects beta gives Claude Code one coordinating conversation that delegates work to parallel threads. Threads are usually cloud sessions, which Anthropic's docs now list as available, no longer in research preview, on Pro, Max, and Team and for eligible Enterprise seats. A project can also run a thread on your own machine through Remote Control.
Claude Code Can Now Create Design, Slide, and Doc Artifacts
Claude Design, Claude Slides, and Claude Docs work inside Claude Code, so developers can point Claude at files and RFCs, ask for a design review deck or UI mockup, edit it, and share it from desktop or terminal. As of October 8, 2026 the three templates are out of beta and on every plan.
Claude Code Adds Plugin Evals for Regression Testing and No-Plugin Baselines
Claude Code now includes `claude plugin eval`, a testing workflow for plugin and skill authors. The command can create cases and graders, run a plugin in isolated non-interactive sessions, compare results with a no-plugin baseline, generate an HTML report, and support CI gates for plugin changes. Evals require Claude Code v2.1.269 or later and consume model usage.
Claude Code Desktop Adds Pop-Out Panes for Diff and Terminal Work
ClaudeDevs says Claude Code Desktop can now pop out any pane into its own window. You can move a diff or terminal to another screen while Claude keeps working, dock it back later, and run sessions side by side or stacked.
Claude Computer Use Runs in the Background in Cowork and Claude Code
Anthropic added computer use to Claude Cowork and Claude Code in the Claude Desktop app. Claude can click, type, open apps, and use dev tools while you keep working on macOS, with Windows support also documented. The beta is limited to Pro and Max plans and still requires the desktop app to be open and the computer awake.
Claude's ant CLI Can Now Manage Agent Resources as Code
Anthropic added `ant apply` to the Claude CLI, letting teams declare Managed Agent environments, agents, skills, memory stores, and deployments in a repository and reconcile them with the Claude API.
Anthropic Open-Sources a Commerce Agents Blueprint for Claude
Anthropic's open-source Claude Commerce Agents blueprint, released September 2, 2026, ships a shopping agent and a merchant agent that run on the Messages API, the Agent SDK, or Managed Agents, four runnable verticals, a Claude Code plugin, and an engineering deep-dive. It is Apache-2.0, unmaintained by design, and no demo places an order or charges a card.
Claude Code Desktop Can Now Resume Sessions Started in the Terminal
Claude Code can now move a terminal-started session into the Claude Code desktop app. Anthropic says users can type /resume, choose a CLI session, and continue with the full conversation and context intact.
Anthropic Opens a Claude Team Plan for Scientists With Free Standard Seats
Anthropic opened a Claude Team plan for scientists on August 27, 2026. Verified principal investigators at eligible academic and nonprofit institutions can apply for free Standard seats or Premium seats at $15 per user per month for 12 months, with Claude Science, Claude Code, Cowork, shared projects, and administration included.
Claude Code Remote Control Can Start Sessions From Your Phone
As of September 2026, a machine running claude remote-control appears as a device card at the top of the Code tab in the Claude app: tap it, pick a directory, and a session starts on that machine. Anthropic's Week 34 digest also took Remote Control out of research preview. Code and files stay local.
Claude Code Auto-Continues When Usage Limits Reset, On by Default
Claude Code waits in the open session and continues your task automatically when a claude.ai usage limit resets. It is on by default from version 2.1.234 in interactive sessions signed in with a claude.ai subscription. Turn it off in /config under 'Continue automatically at usage limit' or set autoContinueAtUsageLimit to false. It resumes work; it does not raise the limit.
Codex Can Import Workflows From Other AI Agents
OpenAI now lets the ChatGPT desktop app and Codex CLI import supported setup and recent work from other agents. The desktop app can import from Claude Code, Claude Cowork, and Cursor, while Codex CLI supports Claude Code and Cursor, with automatic updates and import history available in the desktop app.
Claude Code Made Auto Mode the Default on August 14, and Now on Every Plan
Auto mode is the built-in starting permission mode for interactive Claude Code terminal and VS Code sessions on every plan and provider with v2.1.283 or later. It became the default for Pro, Max, and Team on August 14, 2026. A classifier reviews each tool call, and pinned or managed defaults still win.
Claude Code Sessions Can Now Message Each Other
Claude Code lets independent sessions discover and message one another. As of September 2026, a session can start a conversation with a session on the same machine, on another of your machines, or on Claude Code on the web; same-machine messaging works on macOS, Linux, WSL 2, and native Windows and on every provider. Messaging is on with nothing to enable, and incoming messages can be accepted, held, or refused per session.
Claude Code artifacts can now call MCP connectors for live, viewer-specific data
Claude Code artifacts can call MCP connectors each time someone views them, so a published page shows current data rather than a session snapshot. Available on Pro, Max, Team, and Enterprise plans with Claude Code v2.1.209 or later. A connector-backed page can now go to a public link, but its live sections stay empty for signed-out or outside viewers.
Claude Code Desktop Adds an iOS Simulator Pane: Watch Claude Test Your App Live
Claude Code Desktop opens Apple's iOS Simulator in a pane beside your conversation when Claude builds or checks your app, taps through it, and reads the screen to verify its own changes. Public beta on macOS for Pro, Max, Team, and Enterprise plans; needs Claude Desktop v1.24012.0+ and Xcode, with Xcode 26.x or Xcode 27 recommended.
Claude Code Ships Screen Reader Mode: Plain-Text TUI for VoiceOver and NVDA
Claude Code now has an opt-in screen reader mode that replaces boxes, spinners, and in-place redraws with labeled linear text that VoiceOver and NVDA read in order. Turn it on with the --ax-screen-reader flag, the CLAUDE_AX_SCREEN_READER env var, or the axScreenReader setting (v2.1.181+). Menus become numbered lists, a terminal bell signals when Claude needs you, and separate settings cover magnifiers, reduced motion, and colorblind themes.
Claude Code Artifacts Expand to Pro and Max Plans (Private Until You Share)
Claude Code Artifacts, which launched for Team and Enterprise, reached Pro and Max plans in July 2026. On Pro and Max an artifact is private until you share it, and a public link is the way to share it; sharing with specific people or a whole organization is a Team and Enterprise feature.
Claude Desktop for Linux Beta: Ubuntu and Debian, With Caveats
Anthropic shipped a beta of the Claude desktop app for Linux on Ubuntu 22.04+ and Debian 12+ (x86_64 or arm64), with Chat, Cowork, and Claude Code on all paid plans. The app does not self-update; updates arrive through apt, and as of August 2026 a directly installed .deb registers the repo itself. Computer Use and Dictation are missing.
Claude Sonnet 5 Launch: Anthropic's Most Agentic Sonnet, Since Replaced by Sonnet 5.5
Anthropic launched Claude Sonnet 5 on June 30, 2026 as its most agentic Sonnet yet, and made its $2 input and $10 output per million token pricing permanent. Claude Sonnet 5.5 replaced it on September 28; Anthropic now lists Sonnet 5 as a legacy model, still available on the API as claude-sonnet-5.
Claude Code Adds Artifacts: Live, Shareable Pages for PR Walkthroughs and Dashboards
Artifacts in Claude Code turn an in-progress session into a live web page that updates as the session works. Launched in June 2026 as a beta for Team and Enterprise with org-only sharing, they are now on Pro, Max, Team, and Enterprise, and an artifact can be shared to a public link anyone can open.
Claude Design's `/design-sync` Makes Claude Design and Claude Code a Two-Way Workflow
As of September 2026, `/design-sync` is a Claude Code command that converts your repo's design system and uploads it to Claude Design, so designs start from your real components. `/design` in Claude Code creates, edits, and syncs designs, and a finished design hands off to Claude Code through the Export menu. It needs a claude.ai account.
Claude Code adds dynamic workflows (research preview) for large parallel agent runs
Dynamic workflows in Claude Code let Claude write orchestration scripts, fan out work across tens to hundreds of parallel subagents, verify results, and resume long-running jobs.
Claude Opus 4.8 Fast Mode: 2.5x Faster Output Tokens; Opus 5.5 Is Now the Default
Anthropic launched fast mode for Claude Opus 4.8 on May 28, 2026: the same model at 2.5x the output speed, three times cheaper than before. Opus 5.5 is now the fast mode default in Claude Code v2.1.280 and later, at $8/$40 per MTok; Opus 4.8 still supports it at $10/$50, billed to usage credits on subscription plans.
Claude Code ships a security-guidance plugin for in-session vulnerability checks
Anthropic shipped an official security-guidance plugin for Claude Code. It runs automatic vulnerability checks while Claude edits files, at the end of each turn, and when Claude runs commits or pushes through its Bash tool.
Claude Agent SDK Monthly Credit on Paid Plans: Paused in June, Now Covered by Max and Team API Credits
The Claude Agent SDK monthly credit never started: Anthropic paused it on June 15, 2026. Since October 7, 2026, Max and Team plans instead include monthly API credits that cover the Agent SDK, `claude -p`, the Claude API, and Managed Agents. Pro and Enterprise get no credit; plan sign-in usage still draws from subscription limits.
Claude Code 2.1.142: `claude agents` Gains Session Flags, Fast Mode Defaults to Opus 4.7, MCP Tool Timeout Honored
Claude Code 2.1.142 (May 14, 2026) added eight dispatch flags to `claude agents`, moved fast mode's default from Opus 4.6 to Opus 4.7, and made `MCP_TOOL_TIMEOUT` lift the 60-second cap on remote MCP servers. The flags and timeout fix stand; fast mode now defaults to Opus 5.5 (v2.1.280 and later) at $8/$40 per MTok.
Claude Code +50% Weekly Limits Promo Ended September 13, 2026; Limits Are Now 25% Higher Permanently
Anthropic's +50% Claude Code weekly-limits promotion ended September 13, 2026 at 11:59 PM PT. On September 14 Anthropic rewrote its support article: starting September 14, 2026, weekly limits in Claude Code are 25% higher than they were before the promotion for Pro, Max, Team, and seat-based Enterprise plans. Five-hour limits are unchanged.
Claude Code 2.1.133: `worktree.baseRef` Default Returns to `origin/<default>`, MCP OAuth Proxy Honored Across the Whole Flow
Anthropic shipped Claude Code 2.1.133 on May 7, 2026. The headline is a worktree-base behavior change: a new `worktree.baseRef` setting (`fresh` | `head`) defaults to `fresh`, which moves `EnterWorktree`'s base back to `origin/<default>` after three days of branching from local `HEAD` (since 2.1.128 on May 4). The release also routes `HTTP(S)_PROXY` / `NO_PROXY` / mTLS through the entire MCP OAuth flow (discovery, dynamic client registration, token exchange, refresh), exposes effort level to hooks via `$CLAUDE_EFFORT`, adds Linux sandbox path overrides, and fixes a refresh-token race that was 401-ing parallel sessions.
Anthropic's Claude Code Post-Mortem: Three Engineering Missteps Behind the Spring 2026 Quality Decline
Anthropic published a post-mortem on April 23, 2026 explaining the Claude Code quality regression that ran from early March through mid-April: a March 4 default-effort downgrade from high to medium, a March 26 caching change that wiped reasoning history every turn, and an April 16 verbosity prompt that capped responses at 25 words between tool calls. All three were resolved by April 20, the API was unaffected, and Anthropic reset usage limits for all subscribers.
Claude Code Subagent Patterns: 10 Reusable Agent Definitions
A Claude Code subagent is a delegated worker with its own context window, defined as a markdown file with YAML frontmatter in .claude/agents/. Subagents can edit files when you grant Edit or Write, nest three layers deep by default, and run 20 at a time. These 10 definitions cover the highest-value delegations.
Claude Opus 4.7 Best Practices: How to Actually Get the Most Out of the Upgrade
Claude Opus 4.7 follows instructions more literally than 4.6, runs longer agentic tasks more reliably, and ships a new xhigh effort level. Anthropic's launch-day guidance is to specify the task up front, batch your interactions, use auto mode, and default to xhigh; this guide adds the verification, recap, and scoping habits that make those gains show up in your sessions.
Codex CLI vs Claude Code vs Cursor: 2026 Architecture Deep-Dive (Sandboxing, Context, Plugins, Scheduling)
Codex CLI, Claude Code and Cursor now all confine local shell commands in an OS-enforced sandbox and all run hook scripts, so the real split is defaults and composition. Codex sandboxes by default, Claude Code's sandbox is opt-in, and Cursor sandboxes under Auto-review. Choose by default posture, Windows support and how unattended work runs.
Claude Opus 4.7 Launch: Stronger Coding, xhigh Effort, and a New Cyber Safeguards Tier
Anthropic launched Claude Opus 4.7 on April 16, 2026, with gains over Opus 4.6 in advanced software engineering at the same $5/$25 pricing, a new xhigh effort level, /ultrareview, higher-resolution vision and the first cyber safeguards. It is now a legacy model, succeeded by Opus 4.8, Opus 5 and Opus 5.5.
Master Claude Code's 1M Context Window: Rewind, Compact, Clear, and Subagents
Claude Code's 1M token context window opens longer autonomous sessions but introduces 'context rot' -- degraded performance as the window fills. Master four turn-end tools: /rewind to drop bad branches, /compact to summarize and continue, /clear to start fresh with a distilled brief, and subagents to wall off noisy work in their own context.
Inside Claude Code's Rebuilt Desktop: Parallel Agents, Drag-Drop Panes, Side Chat
Anthropic rebuilt the Claude Code desktop app on April 14, 2026 around parallel agent workflows: a multi-session sidebar, drag-and-drop panes, an in-app file editor, integrated terminal, side chat, three view modes, and SSH on macOS. Four months on the app also creates routines and local scheduled tasks, browses external sites, and controls your computer.
Claude Code Routines: Schedule, API, and GitHub-Trigger Your AI Agents
Claude Code Routines is Anthropic's new way to run saved Claude Code configurations automatically -- by schedule, API call, or GitHub event. Routines run on Anthropic's cloud infrastructure with a prompt, repo, and MCP connectors. Available in research preview on Pro, Max, Team, and Enterprise plans.
Scheduled AI Coding Agents in 2026: Claude Code Routines vs Cursor Automations vs Codex vs Warp vs Gemini CLI
Claude Code Routines and Cursor Automations both ship schedules, API calls and native source-control events, and Cursor's trigger set is widest. ChatGPT scheduled tasks add Gmail, Slack and GitHub pull-request triggers but no API or webhook. Warp orchestrates other vendors' agents. Gemini CLI has no scheduler and lost its free individual tier on June 18, 2026.
Cursor vs Claude Code in 2026: Which AI Coding Tool Is Better?
Neither tool is terminal-only or editor-only any more: Cursor ships a CLI and Claude Code ships a desktop app, IDE extensions and a browser surface. Choose Cursor for inline tab autocomplete and cross-lab model choice, though OpenAI plans to end Cursor's direct model access on a proposed November 12; choose Claude Code for one agent across surfaces.