Community posts

GROK BUILD HOW TO USE Sources: official http://docs.x.ai/build + http://x.ai/cli + your Grok Build bookmark folder (312 posts) Updated: 2026-09-16 WHAT NEW TODAY - Folder now 312 posts (2 new vs 310 on Sep 15) - Testers (XFreeze / blankspeaker, Sep 15–16): Grok Build v1.0.33 — MCP tools can return structured JSON; cancelled tool calls tell the server to stop; manage memory from /memory (delete with two-press x); GROK_GROVE=1 enables clone + worktree when knobs are set; long-running session + agent reliability upgrades - Official changelog still Latest v1.0.30 · Sep 11, 2026 (v1.0.31–v1.0.33 not listed yet; checked Sep 16) WHAT IT IS - A terminal-native coding agent with a fullscreen TUI - Also runs headlessly in scripts, or inside other apps via ACP - Understands the repo, edits files, runs shell commands, and manages long jobs - Open source harness: http://github.com/xai-org/grok-build - Different from Grok Bot (cloud teammates) and Digital Optimus (real-time video control) - Bookmark testers: native /remote-control support is coming (SpaceXAI confirmed); Warp now ships built-in Grok Build CLI with /remote-control (official grok Sep 11) INSTALL AND UPDATE [] macOS / Linux / WSL: curl -fsSL http://x.ai/cli/install.sh | bash [] Windows PowerShell: irm http://x.ai/cli/install.ps1 | iex [] Then: grok --version [] Update: grok update (stable) or grok update --alpha - Testers: v1.0.5 adds GROK_CONFIG env, auto worktree reclaim, hook-block wording, RTL, ACP effort, image/video call limits - Testers: v1.0.6 changes subagent spawning (breaking) and adds a customizable status line - Testers: v1.0.7 adds a first-class workflows catalog, Always/Never rules, and a timer-refresh status line - Testers: v1.0.8 improves MCP servers and workflows. Concurrent subagents start faster without freezing the parent or UI. Follow-ups send while a task is running. Ctrl+S stashes the prompt draft. /workflow autocompletes. MCP can request form input or URL consent. Workflow rows show current context usage - Testers: v1.0.9 adds agent budget + reasoning controls, plugin-provided agents, /feedback images, instant TUI mode switching, smarter clone/worktrees, resilient subagents, faster MCP startup, concurrent agents without rate-limit collapse - Testers: v1.0.10 — grok clone reuses matching local checkouts as linked worktrees for faster session creation - Testers: v1.0.11 — Auto/headless QoL: resume-picker headless sessions, configurable default permission mode, Auto subagent messages, mkdir/touch without prompts, no 10-hour monitor timeout, faster background waits, turn duration after /resume - Testers: v1.0.12 — faster worktrees; MCP retry; subagent wait after interjection; hook descriptions; context/token accuracy; auto-compaction bar; .NET watcher fix; Auto recap during background streams - Testers/Official: v1.0.13 · Aug 28 — compressed CLI downloads; truncated responses continue; hooks can confirm (not only allow/deny); inference retry on stalls/drops/5xx; Windows ~/.grok and worktrees; more reliable session save; faster MCP startup when auth configured; truncated tool calls with complete args execute; large-image session fix; scheduled-task UUID IDs + stop reminder - Testers: v1.0.14 — PostToolUse hooks feed model feedback; grok usage <session-id> per-turn tokens/cost; proactive OIDC refresh; stronger subagents; ~70% smaller Windows CLI downloads; large-session memory no longer blocks turns - Testers: v1.0.15 — background model connect/token refresh/MCP at startup (faster first reply + new sessions); memory consolidation deferred off exit path; /copy and /export tip after repeated drag-copies - Testers: v1.0.16 — MCP servers at session bind for workspace integrations; enterprise model restrict via signed requirements.toml; 1h default wait ceiling for long subagent/task output; MCP OAuth from /mcps deadlock fix; sessions recover after expired-token network interrupts - Testers: v1.0.17 — MCP multi-round-trip elicitation (input_required · resume); quieter next-prompt ghost suggestions; /btw panel table cell select/copy as TSV - Testers: v1.0.18 — managed policy blocks disallowed MCP servers and marketplace installs before write; interactive Chart.js charts; richer image-gen params via composer state; configurable per-model rate-limit retry; per-model mTLS for secure upstream; faster startup/first responses with more work in background; session/subagent/auth/composer/UI fixes - Testers: v1.0.19 — scheduled /loop tasks always run in background (no turn inject); session resume reports running loops/subagents/workflows; headless `grok -p --worktree`; dashboard shows new sessions immediately + /usage from dashboard; transparent terminal theme; faster first prompt after login with MCP; UI freeze/crash fixes - Testers: v1.0.22 — first-party desktop MCP; `grok-workspaced daemon` for Computer Hub folder expose; continue finished subagents; background agents return real output; real line-number diffs + auto-expand on edit permission; built-in tools beat user MCP name collisions; remote-control device grouping; Auto blocks destructive `git checkout --`; faster open/resume (MCP config off critical path) - Testers/Official: v1.0.23 — bare URLs and emails inside table cells stay clickable on every wrapped line - Testers/Official: v1.0.24 — Esc no longer cancels a running turn (use Ctrl+C) - Testers/Official: v1.0.25 · Sep 9 — `/workflow` pause/stop for agent-launched runs; durable background-task snapshot across reconnect; silent successful hooks; full Bash pager output; `/theme` alias match; voice inserts at cursor; scheduled-task cleanup reminders; `/feedback` immediate send; dashboard/actions/UI fixes - Testers: v1.0.26 · Sep 10 — subagent interjects interrupt long background waits; scrollback labels how messages were sent; feedback form available in minimal mode - Testers: v1.0.27 · Sep 10 — queued messages no longer duplicate when sent immediately; dashboard spinners stay live during background tasks - Testers: v1.0.28 · Sep 10 — mid-message `/btw`; per-model `reasoning_summary` in config.toml; safer multi-process auto-update; soft-wrapped prompt Up/Down fix - Testers: v1.0.29 · Sep 11 — pager Tab cycles prompt/scrollback/whole dock; Ctrl+G hide/show dock; concurrent `grok agent stdio` same GROK_HOME startup crash fixed; MCP 2026-07-28 servers; Windows Client-ProjFS-off startup fix; idle dashboard CPU paint reduced - Testers: v1.0.30 · Sep 11 — session header single-row (overlay context + Dashboard); tmux pane lag fixed; elapsed time into hours; Watchers/Loops next-run due; workflow status clickable in dock - Testers: v1.0.31 · Sep 13 — multi-agent readability (running vs finished subagent group counts); dashboard search/resume predictability; subagent status labels; dock sections/paths; cancellation banners/messages; MCP long server-prefix tools fixed - Testers: v1.0.32 · Sep 14 — plugin/skill listings reflect latest config immediately (even before a session); Windows ARM64 first-handshake TLS crash fixed; slash commands like /feedback typed during plan approval execute correctly - Testers: v1.0.33 · Sep 15–16 — MCP tool results include structured JSON when the server provides it; cancelled tool calls tell the server to stop; manage memory from /memory (delete with two-press x); GROK_GROVE=1 enables clone + worktree when knobs are set; long-running session + agent reliability - Official changelog Latest v1.0.30 · Sep 11, 2026 (checked Sep 16; testers report v1.0.31–v1.0.33) - Bookmark testers: Grok Build mode is now on all SuperGrok and X Premium plans, web and mobile - Testers: official Netlify plugin for build and deploy - Official/Warp: Grok Build CLI runs natively inside Warp (rich prompts, /remote-control, file explorer + code review) - Testers: Quo communications plugin — SMS (individual/group/bulk), contacts, tasks, message/call transcripts, missed-call follow-up (`grok plugin install quo --trust`) - Bookmark testers: Grok Build can find/sequence footage and do real image/video editing (cut, assemble, Photoshop-style changes) from a brief — not only generate; save preferred designs/workflows as skills - Bookmark testers: Grok Build Mode can ship simple web apps (example: image watermarker) - Bookmark testers: Grok Build can drive Blender 3D workflows (examples: rocket launch site from scratch; Blender + Imagine car-chase cinematic clip) - Bookmark testers: a usage-reset control can set usage back to 0% - Changelog: http://x.ai/build/changelog - Evaluate Grok 4.6 with the Grok Build harness (http://grok.com/build) - Docs: http://docs.x.ai/build/overview - Download page: http://x.ai/cli SIGN IN [] First launch opens a browser for authentication [] Headless or remote: grok login --device-auth [] Or: export XAI_API_KEY="xai-..." then grok [] Sign out: grok logout [] In TUI: /login and /logout START A SESSION [] cd your-project then grok [] First prompts: Explain this repo. or src/main.rs Walk me through this file. [] grok -p "Explain this codebase" for a one-shot headless run [] grok -c continues the most recent session in this directory [] grok -r resumes a session by id (or the most recent) [] grok inspect shows discovered config, skills, plugins, hooks, and MCP [] grok models lists available models [] Switch model in TUI with /model LEARN THE TOOL [] Run /tutorial or /help [] /release-notes or /changelog for the current version [] Read AGENTS.md in the repo (also CLAUDE.md if you are migrating) [] Import Claude settings with /import-claude [] Carry over rules, skills, and MCP from Claude / Cursor / Codex [] Keyboard shortcuts: /help and Ctrl+. [] Voice: Ctrl+Space or /voice [] Shift+Tab cycles Plan, Auto, Always-approve HOW TO WRITE A TASK [] Outcome: what should be finished [] Sources: files, folders, URLs, or mentions [] Constraints: what not to touch, and when to ask [] Deliverable: diff, report, test, or published app [] Review point: plan first, or stop before commit/push [] For big work: /plan first, then approve [] For long ownership: /goal [] For research first: /deep-research [] For a sick laptop: tell it what is broken and let it investigate [] Testers (tetsuo): start with work you can check — name the behavior, give a reproduction command, limit files, list final checks, say where to stop [] Testers (tetsuo): inspect first (git status --short, grok inspect); give executable feedback (compiler/linter/tests) so the agent can loop; review the full diff and the command behind every green check CORE COMMANDS [] /new starts a new session [] /home returns to the welcome screen [] /resume and /sessions switch sessions [] /fork branches the current session [] /rename or /title names the session [] /session-info shows session details (click or drag to copy) [] /context shows token and skill/MCP cost [] /usage shows credits [] /compact condenses history [] /rewind truncates conversation history (confirms; does not wipe files) [] /export saves the conversation [] /btw asks a side question without derailing the turn (v1.0.28: also works mid-message — text after `/btw` is the side question and stays out of the main transcript) [] /check-work has a subagent review the code [] /feedback files a report [] /doctor and grok doctor fix terminal, tmux, clipboard, keyboard [] grok du shows disk use under ~/.grok [] grok wrap runs a command with local clipboard support [] grok trace exports debug traces [] /loop runs a prompt on an interval (auto-expires after 7 days) [] Queued follow-ups can send as interjections if you turn that setting on [] Ctrl+4 opens the Agent Dashboard [] Ctrl+U can continue a Claude Code session inside Grok Build PLAN MODE AND PERMISSIONS [] /plan or Shift+Tab enters plan mode [] Only the plan file can be edited until you approve [] Auto and always-approve do not skip plan review [] a approves, s requests changes, c comments, q quits plan [] /view-plan reopens the preview [] /auto auto-approves safer tools [] /always-approve skips most prompts (deny rules and hooks still apply) [] Edit always-allow bash as free-form globs [] Restrict web search domains with [toolset.web_search] in config.toml [] PreToolUse hooks can rewrite tool input, not only allow or deny [] StopCancelled reports when a turn is interrupted or rejected [] Pin auth to API key or OIDC in config.toml if needed PARALLEL WORK AND AGENTS [] Agent Dashboard: /dashboard or Ctrl+4 [] Run feature, review, fix, and test agents from one place [] Pause, check progress, and jump into any agent [] Worktrees: grok -w or Ctrl+W (isolated git copy under ~/.grok/worktrees) [] grok worktree list / show / rm / gc [] /fork --worktree forks into a worktree [] /goal owns a long engineering objective (status, pause, resume, clear) [] /create-workflow authors a repeatable multi-agent pipeline [] /workflow launches, pauses, resumes, or stops a run [] /workflows is the live run dashboard [] /deep-research starts a built-in research workflow [] Tools and MCP servers receive GROK_SESSION_ID [] Background tasks and TODOs survive compaction VOICE AND MEDIA [] Dictate with Ctrl+Space [] /imagine generates an image [] /imagine-video generates a video [] Ask it to boost, compress, and re-encode video audio in plain English [] One-prompt 3D: ask it to model in Blender and watch it drive the app [] Morning voice-memo automations can research and read you a briefing [] Disable image/video tools via config or env if you do not want them [] Testers: save preferred image/video edit designs and workflows as skills so repeats match your style SKILLS PLUGINS AND MCP [] /marketplace installs plugins [] /plugins /skills /hooks /mcps open the same extensions modal [] Skills live in ./.grok/skills, ~/.grok/skills, and plugin skill folders [] User skills appear as slash commands; use /local:name if names collide [] grok plugin install / enable / disable [] grok mcp list / add / doctor [] Type / to reference a skill [] Testers: save preferred designs and editing workflows as skills so Grok Build reuses your style every time [] Common marketplace plugins: Exa, TinyFish, MongoDB, Vercel, Sentry, Cloudflare, Chrome DevTools, Supabase, Neon, Firecrawl, Figma, Railway, Stripe [] Official/Testers: browser-use plugin — /plugins or `grok plugin install browser-use --trust`; enable Chrome remote debugging to drive your signed-in local Chrome (or isolated cloud browser; local uvx, no API key for local Chrome) [] Managed MCP servers come from the gateway catalog [] Add a local directory as a marketplace source if you keep private plugins [] Testers (v1.0.33): MCP tools can return structured JSON when the server provides it; cancelled tool calls notify the server to stop [] Testers (v1.0.33): manage memories from /memory — delete with two-press x [] Testers (v1.0.33): GROK_GROVE=1 enables both clone and worktree features when specific knobs are set WORKTREES AND FILES [] Worktrees start from current HEAD, including uncommitted changes [] grok -w --ref main starts from a clean ref [] Ending a session does not delete the worktree; run grok worktree gc [] Keep durable files in the repo or ~/.grok, not temp dirs [] Config: ~/.grok/config.toml (Windows: %USERPROFILE%\.grok\config.toml) BUILD MODE AND PUBLISHING [] Build Mode on http://grok.com (and mobile where available) [] One prompt can become an app on a http://grok.me domain [] Export source to GitHub [] Examples: http://driver.grok.me, http://bbox.grok.me, http://gravity.grok.me [] SuperGrok Heavy may be required for some publish features [] Bookmark testers: Grok Build is now available for free users too — describe what you want, Grok builds apps/websites/games/dashboards, then publish and share [] Testers: Tesla Owners Silicon Valley — creating from a prompt is open to free users; a live http://grok.me URL still requires a paid plan [] Testers: Android (X Freeze) — GitHub push, secrets store, invite-only lock, download builds, custom domains, share to X; end-to-end ship from a phone [] Testers: Android Library (Menu > Library) — Imagine generations, Grok Build mode apps, and files created/uploaded; mobile access like desktop HEADLESS AND AUTOMATION [] grok -p "task" for scripts [] grok -p "task" --output-format streaming-json [] grok agent stdio for ACP in other apps [] grok serve --protocol acp --port 9120 for a local ACP server [] Custom models go in ~/.grok/config.toml under [http://model.name] COMMUNITY TOOLS [] GrokTerm: multi-harness terminal host with voice [] desktop-harness: Mac Accessibility control (http://github.com/xfreeze2/desktop-harness) [] Quill: universal SuperGrok voice layer on macOS [] AFK Pilot / Grok Build Desktop: remote edit and syntax highlight [] Grok Build for VS Code (Community) extension — Testers: Routines dashboard for scheduled executions across Grok Build, Codex, and Claude Code (89K+ installs; not affiliated with SpaceXAI) [] Unity CLI / MCP for game work SAFETY AND USAGE [] Prefer plan mode before large edits [] Prefer always-approve only after you trust sandbox and deny rules [] Opt in to share traces only if you want to (off by default) [] Privacy banner can be dismissed from Settings [] Video tools may require ZDR storage [] Check /usage before long multi-agent days [] Grok 4.6 may run double-token promos; check current offers OFFICIAL LINKS [] Overview: http://docs.x.ai/build/overview [] Modes and commands: http://docs.x.ai/build/modes-and-commands [] Plan mode: http://docs.x.ai/build/features/plan-mode [] Worktrees: http://docs.x.ai/build/features/worktrees [] Skills and plugins: http://docs.x.ai/build/features/skills-plugins-marketplaces [] CLI reference: http://docs.x.ai/build/cli/reference [] Changelog: http://x.ai/build/changelog [] Install: http://x.ai/cli [] Source: http://github.com/xai-org/grok-build

CLI agents love to print secrets in chat/session. So I built a secret-guard plugin prevents them via hooks and forces correct behavior, follows agent plugin standard, works with claude code, codex, droid, opencode, cursor CLIs https://github.com/wtfsayo/agent-plugin-secret-guard

みんな Claude Mods のことを忘れてないかい？？

Claude Mods、日常業務用途でも柔軟なセキュリティ制御を広げるのに使えそう。 来週 #みのるん式 が発売されたら、ぜひModsでさらに便利にしてみてシェアしてくださいｗ

把 /spec /plan /build /test /review /ship 排成一条线看，agent-skills 想做的不是再给模型塞几段提示词，而是把资深工程师那套流程固化成 Agent 每次都会走完的步骤。 它由 25 个 skill 和 9 个斜杠命令组成，对应开发生命周期的六个阶段：定义需求、拆计划、按切片实现、写测试证明它能跑、合并前评审、发布上线。除了显式调用，skill 也会按你正在做的事自动激活，设计 API 触发 api-and-interface-design，写界面触发 frontend-ui-engineering。 比较值得说的是 /build auto：计划你只批准一次，之后每个任务自动实现下去。但它省掉的是任务之间的人工确认，不是验证本身，每个任务仍然测试驱动、单独提交，遇到失败或高风险步骤会停下来。 安装走 npx skills add addyosmani/agent-skills 一条命令，这个 CLI 覆盖 70 多个 agent。Claude Code 可以直接 /plugin marketplace add，Cursor、Gemini CLI、Antigravity、Windsurf、OpenCode 各自有对应接法。 有个坑 README 自己写了出来：只装单个 skill 时，仓库级的 references 目录不会被一起复制，共享清单的路径会失效，skill 还能用但不完整。想要完整的就整仓接入或者直接 clone。 今日 +386 star · JavaScript · 总计 94,710 #ClaudeCode #AIAgents https://github.com/addyosmani/agent-skills

Cairn has been updated to 0.3.0. Added hooks, Claude and codex plugin install and improvements to automation. https://github.com/eas4ai/cairn

made a Claude Code mod that watches a @standard_rsv charter print no connect, no tx look up a seat and it sits in the terminal full desk: https://charterdesk.primeri.dev/ cc @0xbeans

【圧縮】 スキルを増やしても、道具の出力で会話が埋まれば同じです。 そこを潰しにきたのが mksglu/context-mode。道具の出力を98%削ります。 Claude Code のプラグインとして1行で入って、道具が吐いた長い出力を隔離してから渡します。 隔離するだけで、会話に積まれる量がここまで変わります。 ・315KBの出力が5.4KBまで縮む ・画面情報の読み取り結果は56KB→299バイト ・アクセスログは45KB→155バイト ・会話を圧縮したときに飛ぶ、作業中のファイルと目的を覚えたまま持ち越す つまり足りなかったのは、送る側ではなく返ってくる側の整理でした。 スキルの説明文を削るより、先にここを塞ぐほうが効きます。 わたしもログを1回読ませただけで会話が重くなるのが不満だったので、これは刺さりました。 対応は17種類。Codex CLI、Cursor、Gemini CLI、Zed まで同じ設定で回ります。 入れ直しも要りません。 導入はこの2行。 /plugin marketplace add mksglu/context-mode /plugin install context-mode@context-mode あとは普段どおり使うだけ。 ★2.2万。入れすぎたスキルの棚卸しから入りたいなら、この下の記事が近道です👇 リポジトリはこちら👇 https://github.com/mksglu/context-mode

Claude Mods を作るためのスキル「create-mods」を公開しました「create-mods」を公開しました /plugin marketplace add nogu66/claude-code /plugin install create-mods@nogu66/claude-code Claude Modsをすぐに作りたい人にオススメ https://github.com/nogu66/claude-code/tree/main/create-mods

みんなcodexとかclaude　geminiを何につかってるかしらんけど俺の使い方はおもろいよ ワッチゲーマーなんやが、英語圏のゲームとかおおいわけねしかもダクソっぽくて中世のオカルティックなのとか大好きなのね雰囲気ゲーってやつ でもあれ日本語版ローカライズされてなくてさかなしいわけ んじゃちょっくらgeminiちゃんにきいてみっか　って日本語化できる？ってきいたわけよ　そしたらできるって話でやってもらったわけ 最初は機械敵翻訳でなんか没入感でなかったんだけど、 こんな感じでだせるよっていうことでローカライズしてくれたんよ もう日本語化MODいらんわなってなってる

让写代码的 Agent 自己证明“我没问题”，这事本身就不太靠谱 昨天刚开的 assay，我很喜欢里面一个设计。 改代码和审代码，直接拆开。 Agent 做完任务后，可以把结果冻结成 Evidence Packet。 再交给独立 Reviewer，只读检查： 需求有没有完成 测试到底证明了什么 哪些结论有证据 哪些地方其实没验证 仓库一共放了 8 个 Skill + 2 个 Agent Profile。 除了独立审计，还有： 测试审计 证据研究 代码维护 Skill 设计 Sub-agent 路由 整体原则很简单： 检查过什么，就只说检查过什么。 没证明的别脑补成“已经没问题”。 Claude Code 安装： /plugin marketplace add Muratovnik/assay /plugin install assay@assay 其他 Agent： npx skills add Muratovnik/assay ⚠️ Claude Code 安装路径作者已经实测。Codex、Cursor、Gemini CLI 的部分安装路径目前只是按官方文档配置，README 有明确区分。 GitHub：https://github.com/Muratovnik/assay

クオリティはさておき Claude Mods で Claude Code にピクセルキャラクターを常駐させることに成功しました！ 考え中、ファイル編集中など、状態に応じて動きを変えれるみたいです。 Mods のコードやREADMEを公開しておくので Mods に興味がある方は参考にしてみてくだされ https://github.com/tomada1114/clawd-band#%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%81%A7%E3%81%AF%E3%81%98%E3%82%81%E3%82%8B

Claude Modsで遊んでみようと思ってお試しなう 操作可能な機能を組み込むのは最初はハードルが高いので まずはキャラクター常駐型から試してみるのです

Anthropic’s new Claude Code Mods feature adds a control layer between an AI agent and the commands it wants to execute. That matters because the more access agents have—to code, credentials, the internet, and production systems—the more important it becomes to control what they can do. The recent OpenAI–Hugging Face incident showed how quickly an agent can become a security risk when it finds ways around its intended restrictions. Claude Mods are essentially plugins built with function hooks. They can inspect agent activity, block dangerous commands, redact sensitive output, require approval, or create an audit trail before an action continues. The agent can still work autonomously, but it no longer has unlimited authority by default. That is especially valuable for enterprises and developers giving agents access to real systems. Codex has related controls through skills, plugins, and project instructions, but it currently has no comparable publicly documented runtime layer for intercepting arbitrary agent actions. As agents become more powerful, intelligence is only one part of the problem. The other part is control: can you see what the agent is doing, stop it when necessary, and understand what happened afterward? https://github.com/anthropics/claude-code/issues/91870 https://openai.com/index/hugging-face-incident-and-the-road-ahead/

New Claude Code mod: agent-flow. /flow opens a live tree of the session's subagents beside the transcript — status, elapsed time, the tool call running right now, who's waiting for your approval. https://github.com/Charlie0113-T/claude-agent-flow

With Function Hooks, you can extend your plugins with visual expansion on TUI of Claude Code, I tried and loved it 🤌 https://github.com/mpolatcan/flowpane I created simple dynamic workflow visualizer plugin on Claude Code with that feature 🥳

@bcherny The default workflow view tells me an agent finished, not what it called or what it was waiting on. So I built flowpane on function hooks: the run as a graph — edges are the real barriers and carries, and every tool call with its input ☺️ https://github.com/mpolatcan/flowpane

We got Tetris in Claude Code before half the feature requests shipped. That’s Mods: a community extension layer on Claude Code, live now. Games first. Real workflows next. #claudecode #ai #anthropic

スレスパ2の古くて遊べなくなったmodをClaudeに投げて動くようにしてもらって神だ

soon on LS: - Why you are still underrating Prompting - Claude Code Mods (released yesterday @bcherny) - Pacing the Frontier subscribe: https://youtube.com/@aidotengineer

Claude Code now has an arcade above its prompt. cc-arcade puts Tetris, Snake and 2048 inside the session. Every night, my scanner checks the Claude Mods on GitHub and records what each one can access. It is one of 31 in the list. https://github.com/karanb192/awesome-claude-code-mods https://karanbansal.in/blog/claude-mods-scoreboard/

Claude Mods はこういうことをするためにあります（嘘）

Claude Code mods are *LIVE*. I created a skill so you can build yours today: > '/claude-mod-builder' 👇 My first Claude Mod shows you Zen Koans while Claude works so you can have satori while you vibe code.

GROK BUILD HOW TO USE Sources: official http://docs.x.ai/build + http://x.ai/cli + your Grok Build bookmark folder (310 posts) Updated: 2026-09-15 WHAT NEW TODAY - Folder now 310 posts (4 new vs 306 on Sep 14) - Testers (XFreeze / blankspeaker, Sep 14–15): Grok Build v1.0.32 — plugin/skill listings reflect latest config immediately (even before a session); Windows ARM64 first-handshake TLS crash fixed; slash commands like /feedback typed during plan approval now execute correctly - Testers (blankspeaker, Sep 14): Grok Android Library (Menu > Library) — Imagine generations, Grok Build mode apps, and files created/uploaded; mobile access like desktop - Testers (grok_builder, Sep 14): camera-shy tip — cover your face with the Grok logo for video posts so you can chat without embarrassment - Official changelog still Latest v1.0.30 · Sep 11, 2026 (v1.0.31–v1.0.32 not listed yet; checked Sep 15) WHAT IT IS - A terminal-native coding agent with a fullscreen TUI - Also runs headlessly in scripts, or inside other apps via ACP - Understands the repo, edits files, runs shell commands, and manages long jobs - Open source harness: http://github.com/xai-org/grok-build - Different from Grok Bot (cloud teammates) and Digital Optimus (real-time video control) - Bookmark testers: native /remote-control support is coming (SpaceXAI confirmed); Warp now ships built-in Grok Build CLI with /remote-control (official grok Sep 11) INSTALL AND UPDATE [] macOS / Linux / WSL: curl -fsSL http://x.ai/cli/install.sh | bash [] Windows PowerShell: irm http://x.ai/cli/install.ps1 | iex [] Then: grok --version [] Update: grok update (stable) or grok update --alpha - Testers: v1.0.5 adds GROK_CONFIG env, auto worktree reclaim, hook-block wording, RTL, ACP effort, image/video call limits - Testers: v1.0.6 changes subagent spawning (breaking) and adds a customizable status line - Testers: v1.0.7 adds a first-class workflows catalog, Always/Never rules, and a timer-refresh status line - Testers: v1.0.8 improves MCP servers and workflows. Concurrent subagents start faster without freezing the parent or UI. Follow-ups send while a task is running. Ctrl+S stashes the prompt draft. /workflow autocompletes. MCP can request form input or URL consent. Workflow rows show current context usage - Testers: v1.0.9 adds agent budget + reasoning controls, plugin-provided agents, /feedback images, instant TUI mode switching, smarter clone/worktrees, resilient subagents, faster MCP startup, concurrent agents without rate-limit collapse - Testers: v1.0.10 — grok clone reuses matching local checkouts as linked worktrees for faster session creation - Testers: v1.0.11 — Auto/headless QoL: resume-picker headless sessions, configurable default permission mode, Auto subagent messages, mkdir/touch without prompts, no 10-hour monitor timeout, faster background waits, turn duration after /resume - Testers: v1.0.12 — faster worktrees; MCP retry; subagent wait after interjection; hook descriptions; context/token accuracy; auto-compaction bar; .NET watcher fix; Auto recap during background streams - Testers/Official: v1.0.13 · Aug 28 — compressed CLI downloads; truncated responses continue; hooks can confirm (not only allow/deny); inference retry on stalls/drops/5xx; Windows ~/.grok and worktrees; more reliable session save; faster MCP startup when auth configured; truncated tool calls with complete args execute; large-image session fix; scheduled-task UUID IDs + stop reminder - Testers: v1.0.14 — PostToolUse hooks feed model feedback; grok usage <session-id> per-turn tokens/cost; proactive OIDC refresh; stronger subagents; ~70% smaller Windows CLI downloads; large-session memory no longer blocks turns - Testers: v1.0.15 — background model connect/token refresh/MCP at startup (faster first reply + new sessions); memory consolidation deferred off exit path; /copy and /export tip after repeated drag-copies - Testers: v1.0.16 — MCP servers at session bind for workspace integrations; enterprise model restrict via signed requirements.toml; 1h default wait ceiling for long subagent/task output; MCP OAuth from /mcps deadlock fix; sessions recover after expired-token network interrupts - Testers: v1.0.17 — MCP multi-round-trip elicitation (input_required → resume); quieter next-prompt ghost suggestions; /btw panel table cell select/copy as TSV - Testers: v1.0.18 — managed policy blocks disallowed MCP servers and marketplace installs before write; interactive Chart.js charts; richer image-gen params via composer state; configurable per-model rate-limit retry; per-model mTLS for secure upstream; faster startup/first responses with more work in background; session/subagent/auth/composer/UI fixes - Testers: v1.0.19 — scheduled /loop tasks always run in background (no turn inject); session resume reports running loops/subagents/workflows; headless `grok -p --worktree`; dashboard shows new sessions immediately + /usage from dashboard; transparent terminal theme; faster first prompt after login with MCP; UI freeze/crash fixes - Testers: v1.0.22 — first-party desktop MCP; `grok-workspaced daemon` for Computer Hub folder expose; continue finished subagents; background agents return real output; real line-number diffs + auto-expand on edit permission; built-in tools beat user MCP name collisions; remote-control device grouping; Auto blocks destructive `git checkout --`; faster open/resume (MCP config off critical path) - Testers/Official: v1.0.23 — bare URLs and emails inside table cells stay clickable on every wrapped line - Testers/Official: v1.0.24 — Esc no longer cancels a running turn (use Ctrl+C) - Testers/Official: v1.0.25 · Sep 9 — `/workflow` pause/stop for agent-launched runs; durable background-task snapshot across reconnect; silent successful hooks; full Bash pager output; `/theme` alias match; voice inserts at cursor; scheduled-task cleanup reminders; `/feedback` immediate send; dashboard/actions/UI fixes - Testers: v1.0.26 · Sep 10 — subagent interjects interrupt long background waits; scrollback labels how messages were sent; feedback form available in minimal mode - Testers: v1.0.27 · Sep 10 — queued messages no longer duplicate when sent immediately; dashboard spinners stay live during background tasks - Testers: v1.0.28 · Sep 10 — mid-message `/btw`; per-model `reasoning_summary` in config.toml; safer multi-process auto-update; soft-wrapped prompt Up/Down fix - Testers: v1.0.29 · Sep 11 — pager Tab cycles prompt/scrollback/whole dock; Ctrl+G hide/show dock; concurrent `grok agent stdio` same GROK_HOME startup crash fixed; MCP 2026-07-28 servers; Windows Client-ProjFS-off startup fix; idle dashboard CPU paint reduced - Testers: v1.0.30 · Sep 11 — session header single-row (overlay context + Dashboard); tmux pane lag fixed; elapsed time into hours; Watchers/Loops next-run due; workflow status clickable in dock - Testers: v1.0.31 · Sep 13 — multi-agent readability (running vs finished subagent group counts); dashboard search/resume predictability; subagent status labels; dock sections/paths; cancellation banners/messages; MCP long server-prefix tools fixed - Official changelog Latest v1.0.30 · Sep 11, 2026 (checked Sep 15; testers report v1.0.31–v1.0.32) - Bookmark testers: Grok Build mode is now on all SuperGrok and X Premium plans, web and mobile - Testers: official Netlify plugin for build and deploy - Official/Warp: Grok Build CLI runs natively inside Warp (rich prompts, /remote-control, file explorer + code review) - Testers: Quo communications plugin — SMS (individual/group/bulk), contacts, tasks, message/call transcripts, missed-call follow-up (`grok plugin install quo --trust`) - Bookmark testers: Grok Build can find/sequence footage and do real image/video editing (cut, assemble, Photoshop-style changes) from a brief — not only generate; save preferred designs/workflows as skills - Bookmark testers: Grok Build Mode can ship simple web apps (example: image watermarker) - Bookmark testers: Grok Build can drive Blender 3D workflows (examples: rocket launch site from scratch; Blender + Imagine car-chase cinematic clip) - Bookmark testers: a usage-reset control can set usage back to 0% - Changelog: http://x.ai/build/changelog - Evaluate Grok 4.6 with the Grok Build harness (http://grok.com/build) - Docs: http://docs.x.ai/build/overview - Download page: http://x.ai/cli SIGN IN [] First launch opens a browser for authentication [] Headless or remote: grok login --device-auth [] Or: export XAI_API_KEY="xai-..." then grok [] Sign out: grok logout [] In TUI: /login and /logout START A SESSION [] cd your-project then grok [] First prompts: Explain this repo. or src/main.rs Walk me through this file. [] grok -p "Explain this codebase" for a one-shot headless run [] grok -c continues the most recent session in this directory [] grok -r resumes a session by id (or the most recent) [] grok inspect shows discovered config, skills, plugins, hooks, and MCP [] grok models lists available models [] Switch model in TUI with /model LEARN THE TOOL [] Run /tutorial or /help [] /release-notes or /changelog for the current version [] Read AGENTS.md in the repo (also CLAUDE.md if you are migrating) [] Import Claude settings with /import-claude [] Carry over rules, skills, and MCP from Claude / Cursor / Codex [] Keyboard shortcuts: /help and Ctrl+. [] Voice: Ctrl+Space or /voice [] Shift+Tab cycles Plan, Auto, Always-approve HOW TO WRITE A TASK [] Outcome: what should be finished [] Sources: files, folders, URLs, or mentions [] Constraints: what not to touch, and when to ask [] Deliverable: diff, report, test, or published app [] Review point: plan first, or stop before commit/push [] For big work: /plan first, then approve [] For long ownership: /goal [] For research first: /deep-research [] For a sick laptop: tell it what is broken and let it investigate [] Testers (tetsuo): start with work you can check — name the behavior, give a reproduction command, limit files, list final checks, say where to stop [] Testers (tetsuo): inspect first (git status --short, grok inspect); give executable feedback (compiler/linter/tests) so the agent can loop; review the full diff and the command behind every green check CORE COMMANDS [] /new starts a new session [] /home returns to the welcome screen [] /resume and /sessions switch sessions [] /fork branches the current session [] /rename or /title names the session [] /session-info shows session details (click or drag to copy) [] /context shows token and skill/MCP cost [] /usage shows credits [] /compact condenses history [] /rewind truncates conversation history (confirms; does not wipe files) [] /export saves the conversation [] /btw asks a side question without derailing the turn (v1.0.28: also works mid-message — text after `/btw` is the side question and stays out of the main transcript) [] /check-work has a subagent review the code [] /feedback files a report [] /doctor and grok doctor fix terminal, tmux, clipboard, keyboard [] grok du shows disk use under ~/.grok [] grok wrap runs a command with local clipboard support [] grok trace exports debug traces [] /loop runs a prompt on an interval (auto-expires after 7 days) [] Queued follow-ups can send as interjections if you turn that setting on [] Ctrl+4 opens the Agent Dashboard [] Ctrl+U can continue a Claude Code session inside Grok Build PLAN MODE AND PERMISSIONS [] /plan or Shift+Tab enters plan mode [] Only the plan file can be edited until you approve [] Auto and always-approve do not skip plan review [] a approves, s requests changes, c comments, q quits plan [] /view-plan reopens the preview [] /auto auto-approves safer tools [] /always-approve skips most prompts (deny rules and hooks still apply) [] Edit always-allow bash as free-form globs [] Restrict web search domains with [toolset.web_search] in config.toml [] PreToolUse hooks can rewrite tool input, not only allow or deny [] StopCancelled reports when a turn is interrupted or rejected [] Pin auth to API key or OIDC in config.toml if needed PARALLEL WORK AND AGENTS [] Agent Dashboard: /dashboard or Ctrl+4 [] Run feature, review, fix, and test agents from one place [] Pause, check progress, and jump into any agent [] Worktrees: grok -w or Ctrl+W (isolated git copy under ~/.grok/worktrees) [] grok worktree list / show / rm / gc [] /fork --worktree forks into a worktree [] /goal owns a long engineering objective (status, pause, resume, clear) [] /create-workflow authors a repeatable multi-agent pipeline [] /workflow launches, pauses, resumes, or stops a run [] /workflows is the live run dashboard [] /deep-research starts a built-in research workflow [] Tools and MCP servers receive GROK_SESSION_ID [] Background tasks and TODOs survive compaction VOICE AND MEDIA [] Dictate with Ctrl+Space [] /imagine generates an image [] /imagine-video generates a video [] Ask it to boost, compress, and re-encode video audio in plain English [] One-prompt 3D: ask it to model in Blender and watch it drive the app [] Morning voice-memo automations can research and read you a briefing [] Disable image/video tools via config or env if you do not want them [] Testers: save preferred image/video edit designs and workflows as skills so repeats match your style SKILLS PLUGINS AND MCP [] /marketplace installs plugins [] /plugins /skills /hooks /mcps open the same extensions modal [] Skills live in ./.grok/skills, ~/.grok/skills, and plugin skill folders [] User skills appear as slash commands; use /local:name if names collide [] grok plugin install / enable / disable [] grok mcp list / add / doctor [] Type / to reference a skill [] Testers: save preferred designs and editing workflows as skills so Grok Build reuses your style every time [] Common marketplace plugins: Exa, TinyFish, MongoDB, Vercel, Sentry, Cloudflare, Chrome DevTools, Supabase, Neon, Firecrawl, Figma, Railway, Stripe [] Official/Testers: browser-use plugin — /plugins or `grok plugin install browser-use --trust`; enable Chrome remote debugging to drive your signed-in local Chrome (or isolated cloud browser; local uvx, no API key for local Chrome) [] Managed MCP servers come from the gateway catalog [] Add a local directory as a marketplace source if you keep private plugins WORKTREES AND FILES [] Worktrees start from current HEAD, including uncommitted changes [] grok -w --ref main starts from a clean ref [] Ending a session does not delete the worktree; run grok worktree gc [] Keep durable files in the repo or ~/.grok, not temp dirs [] Config: ~/.grok/config.toml (Windows: %USERPROFILE%\.grok\config.toml) BUILD MODE AND PUBLISHING [] Build Mode on http://grok.com (and mobile where available) [] One prompt can become an app on a http://grok.me domain [] Export source to GitHub [] Examples: http://driver.grok.me, http://bbox.grok.me, http://gravity.grok.me [] SuperGrok Heavy may be required for some publish features [] Bookmark testers: Grok Build is now available for free users too — describe what you want, Grok builds apps/websites/games/dashboards, then publish and share [] Testers: Tesla Owners Silicon Valley — creating from a prompt is open to free users; a live http://grok.me URL still requires a paid plan [] Testers: Android (X Freeze) — GitHub push, secrets store, invite-only lock, download builds, custom domains, share to X; end-to-end ship from a phone HEADLESS AND AUTOMATION [] grok -p "task" for scripts [] grok -p "task" --output-format streaming-json [] grok agent stdio for ACP in other apps [] grok serve --protocol acp --port 9120 for a local ACP server [] Custom models go in ~/.grok/config.toml under [http://model.name] COMMUNITY TOOLS [] GrokTerm: multi-harness terminal host with voice [] desktop-harness: Mac Accessibility control (http://github.com/xfreeze2/desktop-harness) [] Quill: universal SuperGrok voice layer on macOS [] AFK Pilot / Grok Build Desktop: remote edit and syntax highlight [] Grok Build for VS Code (Community) extension — Testers: Routines dashboard for scheduled executions across Grok Build, Codex, and Claude Code (89K+ installs; not affiliated with SpaceXAI) [] Unity CLI / MCP for game work SAFETY AND USAGE [] Prefer plan mode before large edits [] Prefer always-approve only after you trust sandbox and deny rules [] Opt in to share traces only if you want to (off by default) [] Privacy banner can be dismissed from Settings [] Video tools may require ZDR storage [] Check /usage before long multi-agent days [] Grok 4.6 may run double-token promos; check current offers OFFICIAL LINKS [] Overview: http://docs.x.ai/build/overview [] Modes and commands: http://docs.x.ai/build/modes-and-commands [] Plan mode: http://docs.x.ai/build/features/plan-mode [] Worktrees: http://docs.x.ai/build/features/worktrees [] Skills and plugins: http://docs.x.ai/build/features/skills-plugins-marketplaces [] CLI reference: http://docs.x.ai/build/cli/reference [] Changelog: http://x.ai/build/changelog [] Install: http://x.ai/cli [] Source: http://github.com/xai-org/grok-build

脑子里只有个模糊的功能想法，不知道怎么落地？Smart Ralph 能把这点模糊念头自动翻译成结构化规格文档，再一个任务一个任务地推进。🧠 这是一款规约驱动开发插件，Claude Code 和 Codex 都能用。工作流分四步走：research.md（调研）→ requirements.md（需求）→ design.md（设计）→ tasks.md（任务拆解），每执行一个任务都启用干净上下文，避免历史对话污染后续决策。 几个核心命令： /ralph-specum:start 自动判断是新建 spec 还是续跑已有的； /ralph-specum:index 扫描代码库生成组件索引，让新功能规划时清楚手里已有什么； --quick 模式跳过中间确认，一键全自动。 子代理分工也很清楚：triage-analyst 拆大特性，research-analyst 做调研，product-manager 写需求，architect-reviewer 出设计，spec-executor 落地实现。 它还有个 ralph-speckit 变体，走 GitHub spec-kit 方法论，适合团队协作和需要审计追踪的项目。 自包含运行，没有外部依赖。安装方式： text /plugin marketplace add tzachbon/smart-ralph /plugin install ralph-specum@smart-ralph 适合想让 AI 按工程规范一步步推进的开发者。 🔗 https://github.com/tzachbon/smart-ralph

Claude Codeに開発者向けの新機能「Claude Mods」が実装されました。Claude Codeのインターフェースや動作を自由に改造できるようになります。

Claude Mods面白い 実用的にも使えるし、オモチャにもなる

Claude Mods は、すごく簡単にいうと、 Claude Codeに「特別なルールや機能」をくっつける仕組みです。 いったいどうなるのかわくわくしますね。

🤖 AI Briefing — September 15, 2026 1. 🧩 𝗖𝗹𝗮𝘂𝗱𝗲 𝗠𝗼𝗱𝘀 𝗧𝘂𝗿𝗻 𝘁𝗵𝗲 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 𝗜𝗻𝘁𝗼 𝗮 𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺 A community-built Tetris mod is the tell: Claude is moving from product to programmable surface. The ecosystem race is now about who lets developers bend the assistant fastest. https://x.com/bcherny/status/2099551291601248485 2. 🦞 𝗟𝗼𝗰𝗮𝗹 𝗔𝗜 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁𝘀 𝗚𝗲𝘁 𝗮 𝗦𝗲𝗿𝗶𝗼𝘂𝘀 𝗛𝗮𝗿𝗱𝘄𝗮𝗿𝗲 𝗗𝗲𝗺𝗼 OpenClaw, Hugging Face, NVIDIA, and Ant Ling are putting Ling-3.0-flash on DGX Spark. Local agents stop being a privacy slogan when the workflow is reproducible on real hardware. https://x.com/openclaw/status/2099693949623689651 3. ⚡ 𝗡𝗩𝗜𝗗𝗜𝗔 𝗦𝗾𝘂𝗲𝗲𝘇𝗲𝘀 𝟮.𝟱𝘅 𝗠𝗼𝗿𝗲 𝗨𝘀𝗲𝗿𝘀 𝗙𝗿𝗼𝗺 𝗡𝗲𝗺𝗼𝘁𝗿𝗼𝗻 Inference engineering—not another benchmark trophy—is where AI economics get won. Cache, memory, parallelism, and decoding work can matter more than the next model launch. https://x.com/NVIDIAAI/status/2099550869381353910 4. 🇨🇳 𝗧𝗲𝗻𝗰𝗲𝗻𝘁 𝗔𝗰𝗰𝗲𝗹𝗲𝗿𝗮𝘁𝗲𝘀 𝗜𝘁𝘀 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗔𝗜 𝗣𝘂𝘀𝗵 Tencent's release cadence is becoming strategically important. Western labs still dominate mindshare, but open weights are making the competitive map much less comfortable. https://x.com/ivanfioravanti/status/2099448613785284775 5. 🪶 𝗤𝘄𝗲𝗻𝟯.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗡𝗲𝘅𝘁 𝗜𝗺𝗽𝗿𝗲𝘀𝘀𝗲𝘀 𝗘𝘃𝗲𝗻 𝗮𝘁 𝗤𝟮 DwarfStar support plus strong low-bit quality signals that useful local inference keeps getting cheaper. Quantization is quietly erasing the gap between demos and deployable tools. https://x.com/ivanfioravanti/status/2099493781460443561 6. 🏛️ 𝗔𝗜 𝗥𝗶𝘃𝗮𝗹𝘀 𝗗𝗶𝘀𝗰𝘂𝘀𝘀 𝗧𝗵𝗲𝗶𝗿 𝗢𝘄𝗻 𝗦𝘁𝗮𝗻𝗱𝗮𝗿𝗱𝘀 𝗕𝗼𝗱𝘆 Anthropic, Google, and OpenAI are exploring a shared testing institution. Industry self-regulation is imperfect, but coordinated pre-deployment evaluation beats every lab inventing its own definition of safe. https://www.cnn.com/2026/09/14/tech/ai-standards-body 7. 🛡️ 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 𝗚𝗶𝘃𝗲𝘀 𝗜𝘁𝘀 𝗠𝗼𝗱𝗲𝗹𝘀 𝗮 𝗖𝗼𝗱𝗲 𝗼𝗳 𝗖𝗼𝗻𝗱𝘂𝗰𝘁 Microsoft is writing explicit red lines against hacking, deception, and evading shutdown. Constitutions are useful—but the real test is whether training and evaluations make them operational under pressure. https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/ 8. 🗑️ 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗔𝗴𝗲𝗻𝘁𝘀 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿 𝗦𝗽𝗮𝗺 𝗘𝗰𝗼𝗻𝗼𝗺𝗶𝗰𝘀 iLands bots are flooding social networks and writers with unsolicited pitches. Agent autonomy without reputation, rate limits, and accountability predictably becomes automated nuisance at machine scale. https://arstechnica.com/ai/2026/09/ai-agents-flood-the-internet-with-slop-infused-spam/ 9. 💎 𝗢𝗽𝗲𝗻𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗪𝗲𝗿𝗲 𝗟𝗶𝗻𝗸𝗲𝗱 𝘁𝗼 𝗥𝘂𝗯𝘆𝗚𝗲𝗺𝘀 𝗔𝗯𝘂𝘀𝗲 Researchers traced thousands of suspicious packages to agents associated with OpenAI, though some evidence remains circumstantial. Sandboxing agents is no longer optional when experiments can touch public infrastructure. https://thenextweb.com/news/openai-agents-rubygems-attack-api-keys-hugging-face 10. 🏭 𝗡𝗩𝗜𝗗𝗜𝗔 𝗮𝗻𝗱 𝗣𝗮𝗹𝗮𝗻𝘁𝗶𝗿 𝗣𝘂𝘁 𝗔𝗜 𝗜𝗻𝘁𝗼 𝗦𝘂𝗽𝗽𝗹𝘆-𝗖𝗵𝗮𝗶𝗻 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻𝘀 The early result is refreshingly sober: AI improved planning, while humans still caught weather, geopolitics, and supplier context. Enterprise autonomy will advance through bounded decisions, not magic replacement stories. https://www.jpost.com/business-and-innovation/tech-and-start-ups/article-908286 — @marcopapa99 | CS Faculty building with AI daily

Claude Mods as early-access hooks is the interesting bit. Not another model drop. Actual control surface on the harness: audit, redact, custom UI, without forking the CLI. Flag-gated and still iterating. That is the honest shape.