Community posts

¡Hola developer 👋🏻! Ahora puedes conectar tus agentes de IA a Obsidian con las skills oficiales que ha publicado su CEO, Steph Ango (@kepano). En lugar de improvisar, tu agente aprende a leer y escribir los formatos de Obsidian tal y como son: 🟣 obsidian-cli → leer, crear, buscar y gestionar notas desde la terminal 🟣obsidian-markdown → wikilinks, embeds, callouts y propiedades bien puestos 🟣 obsidian-bases → crear y editar .base con vistas, filtros y fórmulas 🟣 json-canvas → trabajar con los .canvas (nodos, conexiones y grupos) Siguen la especificación de Agent Skills, así que funcionan con GitHub Copilot, Claude Code, Codex, OpenCode, etc. Se instalan en un comando: /plugin marketplace add kepano/obsidian-skills /plugin install obsidian@obsidian-skills 📦 Repositorio: https://github.com/kepano/obsidian-skills ¿Ya has conectado tu agente a tu segundo cerebro? Cuéntamelo en los comentarios 💬 #Obsidian #AgentSkills #GitHubCopilot #Opencode #ClaudeCode #Codex #AI #Agents #AgenticAI #Productivity #SecondBrain #DevTools

Oikonさんが命を削って、Claude Modsから投稿しているw API関連の使い道は、めちゃくちゃ多そう！

Moved five guards into Claude Code's new function hooks. Then found the whole layer had been silently inert, a canary I'd trained myself to ignore, and a regex fix that disabled the guard instead of fixing it. https://x.com/i/article/2100602760114708480

this is literally f**king insane i found a 94K-star repo that gives claude code and codex persistent memory across sessions. instead of re-explaining the project every time, it captures what the agent did, compresses it, and brings the useful context into the next session. here’s how to set it up in 3 mins: → npx claude-mem install → select claude code + codex → restart the agent and open a fresh session for claude code: → /plugin marketplace add thedotmack/claude-mem → /plugin install claude-mem now the same project context survives the session → restart → next task loop instead of disappearing every time you close the agent. the interesting part isn’t more context. it’s finally giving coding agents memory that survives the session.

Open-sourcing what I built with Mods this week: /linear, a Claude Code pane for your Linear board — projects, milestones, an issue's comments, and plan/execute/product buttons that turn it straight into a session prompt. https://github.com/SaharCarmel/linear-mod

Big update with version 0.2.11! OOMU is already free but what if you could also connect the cloud AI accounts you already have to it without an API key? OOMU Browser Bridge turns your open ChatGPT, Claude, Gemini, and Grok tabs into local compute nodes for your Mac. Cloud AI with zero API bills. Get the official mod and Chrome extension today at https://oomu.io

GROK BUILD HOW TO USE Sources: official http://docs.x.ai/build + http://x.ai/cli + your Grok Build bookmark folder (319 posts) Updated: 2026-09-17 WHAT NEW TODAY - Folder now 319 posts (7 new vs 312 on Sep 16) - Official grok (Sep 16): Memory GA — remembers conventions, decisions, and project facts across sessions; /memory to browse; /dream to organize recent notes into topics - Official changelog Latest v1.0.34 · Sep 16, 2026 — Memory generally available; Markdown headings receive theme colors correctly (also lists v1.0.31–v1.0.33) - Testers (blankspeaker / bradshannon): v1.0.34 out — Markdown headings theme-color fix; alpha catch-up for 1.0.33–1.0.34 - Bookmarks also: Elon quote-repost of XFreeze v1.0.33 upgrade; mark_k / XFreeze / cb_doge on persistent session memory 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 - Official/Testers: v1.0.33 · Sep 15 — 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; SSH Alt+Enter footer; macOS paste image fix; and more (see changelog) - Official/Testers: v1.0.34 · Sep 16 — Memory generally available (remembers conventions, decisions, project facts across sessions; /memory browse; /dream organize notes into topics); Markdown headings receive theme colors correctly - Official changelog Latest v1.0.34 · Sep 16, 2026 (checked Sep 17; includes Memory GA + 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 [] /memory browses session/project memories [] /dream organizes recent notes into topics [] /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 MEMORY (v1.0.34 GA) [] Grok Build remembers conventions, decisions, and project facts across sessions [] Notes capture in the background after useful work [] /memory to browse and manage memories (delete with two-press x) [] /dream to organize recent notes into topics [] The more you build with it, the more useful it becomes (official grok) 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 [] Official (v1.0.34): /memory browse/manage; /dream organize notes; Memory GA across sessions [] 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

어 뭐야, Grok도 Unity Plugin 나왔었네?! 아직 베타인지 공식앱에는 아직 리스트업 안됐는데, cli 열고: grok plugin install Unity-Technologies/unity-agent-plugin --trust 치면 설치 가능. 이로서 Codex, Claude, Grok 다 Unity겟👏 🔗링크: https://docs.unity.com/en-us/ai/unity-plugin/grok

Claude Codeを利用することによるセキュリティ・安全面に対する、Claude Modsの事例はこれから増えてきそう 内部のブラックボックスだった部分に対して、アプローチが可能になったから、今までよりも深い部分から対策が可能になりと思う 環境変数を読んでしまう問題とかも解決できそう

必须关注的爆款 Pi 插件🔥 全网玩家把 Pi 玩成了下一代「终端里的应用商店 + 多厂模型直通车 + 开源权重弹匣 + 云端全家桶 + 十库外科刀」： 1️⃣ wyattferguson/pi-plugin-manager（https://github.com/wyattferguson/pi-plugin-manager） 键盘优先插件管理 TUI：已装 / 更新 / 搜索 / 一键 u 升级，不再在五个终端里切 pi install。 pi install npm:pi-plugin-manager “极简派第一次有应用商店前台，而不是每个作者发明一套文件夹”！ 2️⃣ luongnv89/pi-extensions（https://github.com/luongnv89/pi-extensions） 12 扩展 + 主题 + 技能：Claude Code / Grok / OpenCode / Cursor / 9router 本地 CLI 当供应商，一条命令进 π。 pi install git:http://github.com/luongnv89/pi-extensions “极简核保留，外围武装按供应商补齐。别再手写五份 provider 配置”！ 3️⃣ jellydn/pi-clinepass-provider（https://github.com/jellydn/pi-clinepass-provider） ClinePass 供应商：GLM-5.2、Kimi K2.7 / K3、DeepSeek V4、Qwen3.7 等 11 个开源权重编码模型直接进 π。 pi install git:http://github.com/jellydn/pi-clinepass-provider “开源权重第一次按弹匣上膛，而不是每次换模型都改一页 YAML”！ 4️⃣ jellydn/pi-qwencloud-provider（https://github.com/jellydn/pi-qwencloud-provider） QwenCloud 一路通：Qwen3.8、DeepSeek V4、GLM-5.2，外加 Wan 出图、HappyHorse 出视频。 pi install git:http://github.com/jellydn/pi-qwencloud-provider “极简终端第一次能写、能画、能剪，而不是编码完还要切三个网站”！ 5️⃣ nsyan/pi-plugins（https://github.com/nsyan/pi-plugins） 十库接入刀：PostgreSQL / MySQL / Oracle / 达梦 / Redis / ES / Mongo / Neo4j / Hive / Spark，查询、扫表、建连、安全闸一条链。 pi install git:http://github.com/nsyan/pi-plugins “数据库第一次是工具而不是事故现场。Agent 碰库之前先过安检”！ // 这波直接把极简 Pi 从「四个工具的毛坯房」推到「有货架、能吃多厂、能打开放权重、能出图出视频、能安全碰库」的完整生产力系统。谁先装上这五件套，谁就提前进入 2026 下半场极简派武装。直接冲。

Claude Code の画面に、Gitのコミット履歴の構造と中身を表示できる Claude Mods作ってみた！

Two things shipped days apart: programmable hooks (code mod) in Claude Code, and @typesafeai's Jev, a model returning typed decisions, not text. Wired together, my agent stops asking me things. It asks Jev. 406 tokens, 166ms, $0.000016.

You can install the Pacman mod in Claude Code by running just one command: npx claude-code-templates@latest --mod games/pacman That’s it!

Cloudflareのsecurity audit skill https://github.com/cloudflare/security-audit-skill Claude Code の /security-review や security-guidance plugin は変更箇所に対して継続的にレビューする用途だと思うが、こっちは現在のリポジトリを網羅的にレビューするものっぽいので、継続的なレビューをする前段階で使うと良さそう？

Claude Code Templates now support Mods! The http://aitmpl.com/mods/ Mods catalog is live, with mods you can install with a single command To install the Snake mod, just run: npx claude-code-templates@latest --mod games/snake Then start Claude Code with: CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 claude Now run /snake and start playing Enjoy! Let me know how it goes with the other mods too Everything is still in beta, so feedback is very welcome!

Claudeくんに書き直してもらった(loraも使った) ぶっちゃけた話GTAはmodで出来るからようやくAIを使う意味が出てきたといえる ただこのAI特有のカメラワークの下手くそさは何とかしたい #ヒカマーズアニメ

Claude Code 2.1.274、毎日アプデが来てる https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md ・メモリ不足が危険域時の警告追加 ・MCP接続待ち時間の設定 ・壊れた会話履歴の無限リトライ現象修正 ・MCP切断/認証/タイムアウト修正 ・/goalがContext超過やResumeで消える現象修正 ・Subagent/Background Agentの結果消失修正 ・長時間Session大規模の負荷軽減 ・Plugin再読込やBashの待ち時間削減 ・その他、細かい修正多数 長時間運用で、固まる消える繋がらないを改善 #ClaudeCode #Claude #Anthropic #AI

Added the ability to add inline reply for each decision. Claude Mods is 🤯💥

I just tried Claude Mods, which lets me customize Claude Code by adding a board on the right side to track each agent’s progress and list everything the lead agent needs my input on.

A plugin update can hand an attacker a shell your agent never sees. New research on lifecycle hooks: config entries that bind a shell command to session start, a tool call or a file edit. A trojanized plugin writes the hook, and the harness runs it when the event fires. No model decision. No approval prompt. The agent never even sees it. The numbers: all 7 harnesses tested were compromised, Claude Code and Codex CLI included, with up to 92.5% success per harness. Microsoft Defender detected 0% of it. That config write is exactly what our Write Guard refuses: every agent-config write inspected, SessionStart-style hooks blocked across .claude, .cursor, .gemini and .vscode, baseline hashing flagging out-of-band edits. What we can't stop: the upstream plugin compromise itself. We stop it from living on your machine. http://arxiv.org/abs/2609.03884

Claude Codeの新機能「Claude Mods」のチートシート: https://github.com/anthropics/claude-code/issues/91870

The melee decompile + ai vibe coding esp Claude has sped up the modding scene. This image will be REAL! #ProAi (some cases) genuinely dc if that’s controversial I also saw a mod where they made flying animated in a pokemon rom hack w many regions. Anything to cure depression !

You can now play pacman inside Claude Code... Ok, I think Claude Mods is getting a little out of control 😂 But this is helping me experiment with how far I can push it. First, I’m building a few games Then I’ll start modifying Claude Code’s internal functions to better fit the workflows and MCPs we’re building So far, everything looks and works great! I’ll be sharing more Mods and how to install them on http://aitmpl.com soon

Claude Code writes too much code and you pay for every line. Ponytail is a free plugin that makes it check the codebase first and reuse what already exists. It only builds when there's nothing to use. Works on any AI model. https://github.com/DietrichGebert/ponytail

I stopped trusting AI when it tells me: “yeah, this startup idea has potential.” So I built something different. Idea Diamond 💎 https://github.com/luckysharda/idea-diamond An open-source Claude Code plugin that tries to kill your startup idea before you waste months building it. /plugin marketplace add luckysharda/idea-diamond /plugin install idea-diamond@startupresearch Then: /idea-diamond Should I build an AI meal-planning app for busy parents? Here’s how it works ↓

Anthropic just cracked open a new layer in Claude Code with Function Hooks / Mods. I’m using the preview to figure out what this makes possible across LegCLI, DashClaw, CostClaw, Agnostic AI, handoffs, memory, and more. https://x.com/i/article/2100212668497838080

Herdr を学びたくなったので、Claude Codeの画面にショートカット一覧が出る Claude Mods を作ってみた！

I loved @dexhorthy's show-me skill, but in the Claude Code terminal, the diagram came out as raw mermaid text. So I built a plugin that renders mermaid right in the terminal window. Shipped it end-to-end with @mattpocockuk's workflow. https://github.com/lucaswx2/mermaid-for-claude

Claude Mods は、 新しいプラグイン名というより「Claude Codeの実行パスに差し込むミドルウェア」 Function Hooks で Claude Codeのイベントに関数を差し込み、 入力・実行・結果・UI・ツール・状態まで扱える ・ModsはClaude Codeの実行エンジン内部への拡張 ・Skillsは知識・手順 ・Hooksはライフサイクルの自動処理 ・Pluginsは拡張を配布する箱 ・MCPは外部サービスとの接続 Modsが一段深いのは、 モデルに頼むだけではないこと ・実行前に危険操作を止める ・ツール結果から秘密情報を消す ・必要な文脈を注入する ・画面に状態を表示する ・独自ツールやコマンドを生やす ・外部サービスへ通知する 個人なら、 ・危険コマンド実行をdeny・確認 ・APIキーやPIIを検出し、モデルへ渡す前にredact ・コストやコンテキスト残量をHUD表示、長時間タスクを通知 組織なら、 ・ツール呼び出しをSIEMや監査基盤へ送り、操作を記録 ・本番デプロイに二段階承認を挟む ・mainへの直接pushや危険な権限変更を強制ブロック ・プラグインのファイル・プロセス・ネットワーク利用を審査 だから、Claude Modsは「便利機能」として入れるより、実行権限を持つコードとして見るべき 導入前に見るのは、何ができるかだけではない。 ・どのファイルを読むか ・プロセスを起動するか ・ネットワークへ出るか ・・秘密情報へ触れるか 組織のポリシーで制御できるか Claude Modsは、 個人の安全装置にも、 組織のガバナンスにも、 Claude Codeの作業環境をプロダクト化する手段にもなりうる まずは個人なら危険操作を1つ止める 組織なら監査ログを1つ取る 小さなModから始めるのが、いちばん現実

It's so annoying Claude Code doesn't pay attention to its own usage limits. Isn't the model smart enough to pace itself more evenly throughout the day? I think it is. Releasing an av/terse Claude Code plugin today that does exactly this! https://github.com/av/terse