Claude Code

Anthropic added /goal to Claude Code for completion-checked runs, alongside /loop, /schedule, stop hooks, auto mode guidance, and an Opus 4.7 fast mode preview. Use /goal when a session needs to keep working until a defined condition is met; fast mode is opt-in now and becomes the default on Thursday.

Anthropic opened Agent View as a research preview, giving Claude Code one control pane for parallel sessions, skills dispatch, and quick replies. The change makes multi-session supervision a native workflow instead of a terminal-tab workaround.

Creators documented running Claude Code on always-on VPS setups with SSH, mosh/tmux, and /resume so sessions survive laptop sleep. It cuts battery drain and lost progress, but image paste and remote file handoffs still feel clunky.

New Hermes Agent and Claude Code playbooks mapped memory, skills, soul, crons, and nightly GitHub sync into repeatable personal-OS setups. The guides push agent workflows into daily content and admin tasks while surfacing security and stale-memory failure modes.

Creators reported Claude Code sessions hanging for minutes with no status feedback, and an Anthropic engineer said responsiveness improvements and self-serve debug logs are on the way. Users also say Claude Desktop now shows context-window usage, giving long sessions a clearer limit indicator.

A viral creator workflow swaps markdown for Claude-generated HTML files, then publishes them as live links for review and iteration. Users say the format is easier to scan and share for one-pagers, slides, and handoff docs, though the practice is entirely community-led.

Anthropic says this week's Claude Code release fixes long-running session bugs across 1M-context prompts, caching, auth fallbacks, MCP retries, and terminal rendering. The update targets the stability problems that surface in longer agent runs and heavier IDE workflows.

At Code with Claude San Francisco, builders showed Claude Code running 21-agent app pipelines across Figma, Jira, Confluence, and TestFlight. Users should watch for reliability strain as posts and conference recaps tie recent slowdowns to Anthropic's reported 80x growth.

Anthropic said a SpaceX partnership will add compute capacity, and it doubled Claude Code 5-hour limits for paid plans. It also removed peak-hour reductions for Pro and Max and raised Opus API limits; the change should reduce throttling for heavy users.

Anthropic introduced dreaming as a research preview in Claude Managed Agents alongside multiagent orchestration, rubric-based self-improvement, and webhook updates. Sub-agents now share a container and filesystem, so teams can coordinate longer-running work and manage memory across sessions.

Creators showed Google’s DESIGN.md file and custom skills as a way to encode typography, color, spacing, and component rules for AI-built UI. The workflow helps move from prototype to app with backend stubs and clearer Claude Code handoffs.

Rezonant showed a browser extension that records screen walkthroughs and narration, then turns them into structured briefs, tickets, and agent-ready tasks using live product context. It plugs into GitHub, Figma, Linear, Jira, Notion, Granola, and Confluence, so teams can skip a standalone spec doc.

Builder demos show Claude Code being run as a structured team of specialist agents, including a 21-agent setup that Aakash Gupta says shipped from idea to App Store submission in 72 minutes. The workflow shifts the bottleneck from typing code to specs, review, and product judgment, making Claude Code look more like a product-build system than a code assistant.

Hermes Agent playbooks now show the agent writing its own skill file and running a 7-agent SEO loop claimed to get posts indexed in under 14 days. That makes Hermes look more like a reusable operating layer, with Claude Code as the execution handoff.

Posts and demos described Claude Code controlling Blender through an MCP connector to create, edit, and debug 3D scenes from chat prompts. The demos matter because they show text prompting reaching direct scene manipulation inside a mainstream 3D tool.

Hacker News users documented Claude Design workflows that move from UI exploration into Claude Code handoff and even AGENTS.md-backed backend scaffolds. The reports matter because the preview is being used as a design-to-code front end, while exposed prompt material shows rough edges remain.

Claude Code added phone push notifications for long-running tasks and published 50-plus stability fixes across recent CLI releases, including up to 67% faster /resume on large sessions. The update matters because mobile alerts, auth fixes and lower-memory startup remove several workflow interruptions from daily coding use.

Anthropic support docs now say Claude Pro users in Claude Code need extra usage to access Opus, with Sonnet 4.5 as the default. Separate user posts report mismatched receipts and an unverified $200 overage case, making spend harder to predict.

BeatBandit opened an MCP integration that lets Cursor and Claude Code call its story engine for scripts, revisions, storyboard images, and videos. The release moves story development tasks from a separate web app into agentic IDE workflows.

Users described Claude Design as a front end for layout exploration, then exported zipped projects into Claude Code or HyperFrames for implementation and rendering. The workflow reduces spec writing and prototype setup, but still depends on downstream code, FFmpeg and a tuned design system.

Anthropic refreshed Claude Code on web and mobile with a sessions sidebar, routines view, faster responses, and claude --teleport handoff to the CLI. Use it to start work on web or mobile and continue in a terminal with branch state intact.

Anthropic published a post-mortem on Claude Code regressions, said the problems lived in the harness rather than the models or API, and reset subscriber usage limits after fixes. The update matters for long agent sessions because recent complaints centered on reliability, wasted effort, and broken trust.

Claude Code introduced /ultrareview in research preview, sending parallel bug-hunting agents to scan critical changes and return findings in the CLI or Desktop. That matters because Pro and Max users get three free runs through May 5, and analysis threads frame it as a lower-noise answer to conventional AI review false positives.

Fresh HN discussion and creator posts say Opus 4.7's tokenizer change, xhigh defaults, and adaptive thinking can make sessions costlier or harder to steer. Users also report normal workflows triggering safety refusals or burning large chunks of monthly limits in a single project.

Users posted WOZCODE, a Claude Code plugin that swaps in smarter file and search tools, and reported 54% lower cost, 68% fewer turns, and faster completion on the same Opus 4.7 task. The benchmark is community-run, but it includes install steps and repeatable commands.

Anthropic released Claude Opus 4.7 with adaptive thinking, xhigh effort, and new Claude Code controls including auto mode, recaps, and ultrareview. The update also changes token use, adds a tokenizer update, and fixes rate limits for longer coding and creative sessions.

Anthropic put Claude Code routines into research preview and rolled out a rebuilt desktop app the same day. The update moves Claude Code toward event-triggered agents and parallel task review, so teams can test workflow automation.

Posts from PM candidates say Google is using a live Cursor build instead of a standalone technical screen. Figma, Codex, and Claude Code users are also shipping prototypes and PRs inside coding tools.

Anthropic began charging pay-as-you-go for third-party harnesses like OpenClaw instead of covering usage with Claude subscriptions. Users should review wrappers and migration paths, including Claude Code CLI, OpenAI auth, Hugging Face guides and local tools.

Community plugins now add multi-agent orchestration and self-hosted repo tours to Claude Code, including five execution modes, 32 agents, and generated code maps. Install them to package repeatable coding and onboarding workflows as skills instead of custom setup.

An open-source Claude Code template now clones websites from a single /clone-website command using Chrome MCP, design-token capture, and parallel git worktrees. It packages front-end recreation into a repeatable flow, but current proof comes from repo demos rather than broad field use.

Composio open-sourced Agent Orchestrator, which spawns parallel coding agents with separate worktrees, PRs, CI feedback loops, and a local dashboard. It matters for vibe coders building creative tools, because it cuts the branch and review babysitting that slows prototyping.

A tutorial thread showed how to route Claude Code through Ollama, choose a local coding model, and point Claude at a local base URL for private work. Use it if you want agent-style coding on your own machine without cloud API spend.

LangChain open-sourced Deep Agents v0.4.11, an MIT agent harness with planning, files, shell access, sub-agents, and auto-summarization. Study it if you want a readable template for building Claude Code-style tools on your own model stack.

AgentCash claims agents can buy access to 250-plus premium APIs from inside Claude Code, OpenClaw, and Codex without separate keys or subscriptions. Verify provider coverage and costs before relying on it for research-heavy workflows.