Claude Code

Benjamin Cherny said Anthropic trains Claude against prompt injection and that Claude Code’s model, probe, and auto-mode layers can reach 0% attack success in next week’s defaults. The claim comes from an Anthropic engineer rather than an independent benchmark.

Boris Cherny said Anthropic has landed large P99 RSS improvements for Claude Code while still collecting CPU and memory reports across CLI and Desktop. The issue remains an active performance investigation requiring machine, OS, version, and task details rather than a fully verified fix.

Anthropic’s Boris Cherny said Claude Code users are not banned for using other model harnesses through proxies. He pointed to a classifier issue, unblocked one escalated account, and said false positives are being reduced.

Meng To released the Kage landing page repo and reusable Three.js skills after building the 3D scrolling site with Claude Code, Opus 5, and image tools. He cites a 922 KB build and mobile fixes.

Anthropic says Claude Code Pro, Max, and Team users will default to Auto Mode on Aug. 14. Its tool-call classifier reportedly caught 89% of dangerous commands, versus 14% for manual approval, after prompt-injection testing.

Graft scans a repo into linked markdown and plugs into Claude Code hooks so the agent can reuse codebase context. Its 162-run benchmark claims 46% fewer tool calls, up to 4x fewer tokens, and 60% less time.

Peter Yang published a 25-minute tutorial and written workflow that moves from problem definition and Claude Design prototypes to reusable design-md files and Claude Code implementation. The process adds Mobbin research and HTML specs so agents can reuse design context instead of rebuilding UI direction each prompt.

Creators shared playable game prototypes built with coding agents, including Codex rebuilding Octane in Blender, a Red Alert clone, a Three.js arena shooter, and a Claude Code tank game. Other demos used single-file browser-game scaffolds.

Shared workflows used Codex, Claude Code, and Fable for release testing, inbox triage, product-plan review, and adversarial code review. OpenClaw’s QA prompt split testing across 12 subagents.

Anthropic launched Claude Opus 5 for Claude Code and the API with high-effort defaults, fast mode, migration tooling, mid-conversation tool changes, and routing fallback. The model scored 43.3% on Frontier-Bench v0.1.

Levelsio pointed to customers and founders replacing paid apps with private AI-built versions. The debate centers on whether AI raises quality baselines while weakening pricing power for simple software.

Peter Yang shared Thariq’s explanation that Anthropic cut Claude Code’s system prompt by 80% as newer models need fewer examples and more room to reason. The same discussion covered /loop, /goal, workflows, and long-running agents.

ClaudeDevs said Pro, Max, Team, and seat-based Enterprise users keep 50% higher Claude Code weekly limits through August 19. Users had warned the promo’s end would sharply cut effective usage.

Levelsio shared a repeatable OpenCode setup using a paid Kimi Code API key and BUILD mode after OpenRouter limits and Claude Code safety blocks. Other users reported Kimi Code quotas interrupting small game builds.

Demos from Gokay and Meng To used video, object-view, and image references to generate HTML, Three.js, or Blender scenes. The builds paired Sol or Claude Code with tools including Reve, HyperFrames, and Blender MCP.

ClaudeDevs says Artifacts now support public links, multiplayer editing in Claude Code, and creation through Claude Tag. A workflow post shows Claude Tag dashboards edited by collaborators or local Claude Code sessions.

Levelsio exported diet logs from Claude chat into Claude Code on a VPS, then built Caltrack with Telegram, SSH entry, database memory, and Grok vision food scanning. The case turned failed chat memory into a persistent app.

Levelsio used Claude Code on a VPS to SSH into a cloud Mac Mini, build an iOS app headlessly, and stream serve-sim into a browser. Follow-up posts documented the tunnel and serve-sim setup, making the workflow reproducible for remote iOS testing.

Posts report Fable 5 remains included in Claude only through July 7 before moving to $10/$50 per million-token credits. Watch usage closely: tests show roughly 2x Opus consumption in subagent and one-shot app workflows.

Creator threads and Anthropic interviews documented Claude Code setups that run on VPS instances, stay reachable from phones, and keep working overnight. The setup matters because coding, deployment, and review can happen inside one persistent environment instead of a local machine session.

Levelsio says Claude Code has blocked requests involving country codes, country names, and dropdown selectors for about a year under its content filtering policy. Common form and localization tasks can fail even when the prompt is routine product or web work.

Anthropic documentation and user threads show Claude Tag can watch Slack channels ambiently and auto-reply to Datadog or Sentry-style alerts without explicit tags. That matters for production teams because bug triage, legal review, and ops handoffs can run inside shared channels.

Anthropic opened Claude Tag in Slack beta for Team and Enterprise plans, giving channels a persistent Claude with memory, tools, and self-scheduled follow-ups. The setup lets teams test whether an always-on assistant can handle ongoing workflow work, not just one-off replies.

A creator walkthrough mapped HyperFrames into a five-step process: gather assets, write a storyboard, mine the launch repo, review static frames, then build and polish the final clip. Keep edits in HTML until the last pass, then use Studio for copy, spacing, color, and motion tweaks.

ClaudeDevs said it raised 5-hour and weekly usage caps for the weekend across every plan. The change lands as users report token burn, overage charges, and heavier Claude Code sessions driven by long agent runs and goal-checked workflows.

Claude Code can now turn a working session into a shareable HTML Artifact that keeps updating while the agent continues, starting on Team and Enterprise. Use it to share prototypes, diagrams, dashboards, and internal sites without stopping the session.

Anthropic shipped two-way syncing between Claude Code and Claude Design, letting teams pull a design system into a repo or push built UI back into the canvas. The release connects component libraries to live code; teams should use it to reduce handoff drift between design and implementation.

New Claude Code and Codex tests showed open-ended /goal runs drifting or stopping too early, while planning-first and verifier loops forced rechecks before completion. The more reliable setup improves long build workflows, but it costs more turns and tokens.

Practitioner threads showed Claude Code /goal refactors running until an evaluator marked them done, with live testing and autoreview checkpoints in the loop. The pattern turns long repo cleanup into trackable agent runs, though today’s evidence is user-led rather than a fresh Anthropic release.

Community demos showed Claude Fable 5 generating playable games and simulations from short prompts, image refs, and goal-based instructions, from Pokémon and F-Zero to city sims and FPS clones. The demos make the model’s creative ceiling clearer, but builders still needed follow-up prompts for speed, style, or polish.

Anthropic opened Claude Fable 5 across Claude Code, Desktop, Cowork, and API, with always-on reasoning and Opus 4.8 fallback on some flagged requests. Early demand triggered model-picker friction and quota pressure, so Anthropic reset the 5-hour and weekly limits the same day.

Claude Code shipped nested subagent support capped at depth 5 and expanded /usage so builders can see which skills, MCPs, and plugins are consuming tokens. That gives long-running vibe-coding sessions a cleaner way to split work and diagnose expensive tool chains instead of stuffing everything into one thread.

Anthropic staff said Claude Code usage has shifted toward auto mode, routines, and phone-based coding one year after GA, and they pointed users to /usage for token breakdowns. The thread matters because it shows Anthropic’s intended daily-driver workflow as community comparisons with Codex intensify.

A creator showed Ideogram 4.0 using structured JSON and drawn bounding boxes in ComfyUI to lock composition and text placement, then extended it through Claude Code and ComfyCloud MCP for exact-pixel variations. The posts say the model needs 12 turbo steps and the Kijai prompt-builder node is still being updated, so users should expect an evolving workflow.

Anthropic changed Claude Code’s explicit dynamic-workflow trigger from "workflow" to "ultracode" after users reported accidental activations. The change narrows when the feature fires, and Opus 4.8 users can compare the new behavior against live speed.

Anthropic released the ant CLI so Claude Platform APIs, file uploads, and Managed Agents sessions can run from the terminal, then updated Claude Code so /fork starts a background agent with the same context and prompt cache. Teams can use it to script agent runs, inspect traces, and hand work between Claude Code and the platform.

Anthropic reset 5-hour and weekly usage caps for Pro and Max users after a request-handling bug spawned too many parallel tool calls. If you hit the issue, retry now and expect the Opus 4.8 request path to behave more normally.

Fresh Hacker News comments and user posts report 400 errors tied to modified thinking blocks, short cache TTLs, and behavior some testers call a regression from 4.7. The issue matters because the same model is also powering one-prompt sites and games, so quota burn and client breakage are showing up alongside stronger creative output.

Anthropic documented mid-conversation system messages and automatic cache preservation in Opus 4.8, while Claude Code and Cowork gained /effort controls. Try the new workflow controls if you rely on long sessions, since they may matter more operationally than the raw model bump.

Anthropic rolled out Claude Opus 4.8 across Claude Code, the API, and partner surfaces, plus a research-preview workflow mode that coordinates large subagent fleets. It keeps 4.7 pricing, but early tests suggest workflow runs can burn very large token budgets, so teams should watch usage closely.

Peter Yang published a /slides skill for Claude Code that turns rough outlines into animated HTML decks with 12 layouts, three templates, live charts, and screenshot-based self-fixes. It matters because presentation polish becomes a repeatable prompt-to-HTML pipeline that also runs in Codex.

Anthropic released a Security Guidance plugin for Claude Code through the plugin marketplace and said internal use cut security-related PR comments by 30-40%. Teams can also enforce repo or MDM-distributed claude-security-guidance.md rules, making Claude Code a first-pass policy check before review.

Creator tutorials across Aura, MotionSites, and SceneAI showed Claude Code moving from static one-prompt pages to animated sites with GPT Image 2 visuals, video backgrounds, and mouse-scrub hero effects. That makes prompt-built web design more presentation-ready and cuts handoff time from concept to coded front end.

Users highlighted Claude Code auto mode for running parallel sessions, and fresh demos showed landing pages and UI sections built in minutes. The same posts also reported failed profiling runs and effort resets, so teams should watch quota and session reliability.

levelsio said he now ships directly on production VPSes with Claude Code, backed by 3-2-1 backups and almost no dependencies. The thread ties a vanilla PHP, JS, and SQLite stack to two brief outages in a year, so lower complexity may keep AI-assisted bugs manageable.

Anthropic previewed a Claude Code update that shows token usage by Skills, Agents, MCPs, and Plugins in the CLI, with desktop support planned later. The command targets skills-heavy workflows where token costs are hard to attribute across multiple moving parts.

Practitioners documented Cowork and Claude Code setups that use shared CLAUDE.md files, progressive skill loading, and agent memory instead of blank-session prompting. That matters for vibe-coders because PM, design, and implementation workflows can compound across sessions, though some stronger performance claims came from third-party posts.

Anthropic made /fast default to Opus 4.7, added prompt cache diagnostics in Claude Console, published scale guidance for large codebases, and renamed extra usage to usage credits. The bundle gives teams clearer controls over latency, cache misses, and paid usage while running long Claude Code sessions.

Skilled launched a CLI and TUI that scans installed skills across Claude Code, Codex, Droid, OpenCode and Grok Build. It surfaces dead skills, single-project dependencies and usage by agent or project, so teams can clean up skill sprawl.

Anthropic's ClaudeDevs account said it reset everyone's 5-hour and weekly rate limits. The reset landed alongside paid-user complaints about slow sessions and visible switching pressure toward Codex, without a root-cause or permanent policy change attached.