正在加载视频...

视频加载失败

Claude Code just shipped three updates. None of them need installing (they're already on your machine). 1. Sessions can talk to each other ↳ @ a session by name, same as tagging a person 2. /design ↳ editable artboards on a canvas, inside Claude Code 3. Concise output style...

23,408 次观看 • 1 个月前 •via X (Twitter)

32 条评论

Muhammad Ayan 的头像
Muhammad Ayan1 个月前

I’m weirdly excited by session tagging. I lose more time passing context between chats than doing the actual work :)

Charlie Hills 的头像
Charlie Hills1 个月前

Yep 😂 Half the work is just catching the next chat up.

Yohaku 的头像
Yohaku1 个月前

Need to try this updates from Claude Code

Charlie Hills 的头像
Charlie Hills1 个月前

Go for it :)

Hussain Hashim | Building SundayBack 的头像
Hussain Hashim | Building SundayBack1 个月前

@charliejhills sessions talking to each other is a game changer. saves so much time when juggling multiple projects. love this update!

Maryam Asim 的头像
Maryam Asim1 个月前

This sounds like controlled chaos and I loooove it

Charlie Hills 的头像
Charlie Hills1 个月前

Haha controlled chaos is exactly what it felt like

Gabriel Millien 的头像
Gabriel Millien1 个月前

The ability for sessions to talk to each other is a game changer. Claude Code is becoming a much more powerful workflow, not just a coding tool.

Charlie Hills 的头像
Charlie Hills1 个月前

Yeah, this is way beyond just coding now.

Saman Ahmed 的头像
Saman Ahmed1 个月前

No installing is my favorite part of this whole thing hehe

Charlie Hills 的头像
Charlie Hills1 个月前

Honestly same

Gregor 的头像
Gregor1 个月前

The concise output switch is the sleeper one. On long debugging sessions, Claude narrating each step was eating roughly 40% of my context window before doing any actual work. Effective session length roughly doubled once I flipped it.

Charlie Hills 的头像
Charlie Hills1 个月前

This one quietly makes long sessions way better.

Liam | AI Tools & News 的头像
Liam | AI Tools & News1 个月前

Sessions talking to each other might be the biggest update here.

Charlie Hills 的头像
Charlie Hills1 个月前

Yep, that one could completely change workflows.

AI Mastery Guide 的头像
AI Mastery Guide1 个月前

Sessions talking to each other, that's new

Charlie Hills 的头像
Charlie Hills1 个月前

It really is

AI Mastery Guide 的头像
AI Mastery Guide1 个月前

nice

A.W.E.S.O.M.-O 4000 的头像
A.W.E.S.O.M.-O 40001 个月前

Five stars after that is honestly an absolutely legendary reviewContext sharing between sessions could seriously change how teams build

Charlie Hills 的头像
Charlie Hills1 个月前

I’ll take legendary 😂 Appreciate it!

Arfa Farheen 的头像
Arfa Farheen1 个月前

/design is gonna be fun to play with fr

Charlie Hills 的头像
Charlie Hills1 个月前

For real 😂

Pranav Ramesh 的头像
Pranav Ramesh1 个月前

The 2nd one is interesting and useful, the design part on Claude Code itself. If you want something to be explained in a simple but visual way, this skill will be useful

Charlie Hills 的头像
Charlie Hills1 个月前

Yeah /design is really useful for turning ideas into something visual.

Meet Anghan 的头像
Meet Anghan1 个月前

the thing that breaks with parallel sessions isn't context, it's ownership. two of mine both "fixed" the same file and i spent an hour reconciling. naming them by what they own instead of what layer they sit in fixed it. did your four terminals ever step on each other?

Apollon Foivos Bakis 的头像
Apollon Foivos Bakis1 个月前

Cross-session communication unlocks better agent workflows.

Charlie Hills 的头像
Charlie Hills1 个月前

Exactly. It opens up some really interesting agent workflows.

emily rose 的头像
emily rose1 个月前

Sessions tagging each other? They'll be planning a pub trip next.

Grzegorz Brzęczyszczykiewicz 🐀 的头像
Grzegorz Brzęczyszczykiewicz 🐀1 个月前

For 3, you can make this a default by adding to ~/.claude/settings.json "outputStyle": "Concise", In context: "theme": "dark-daltonized", "editorMode": "vim", "outputStyle": "Concise", "agentPushNotifEnabled": true,

Wallchain Community Hub 的头像
Wallchain Community Hub1 个月前

need to test these multi terminal sessions

Tony Tong | Founder | Ancient Systems x AI 的头像
Tony Tong | Founder | Ancient Systems x AI1 个月前

New features change what's possible, not what's worth asking. In 2018 I ran an LTV and churn analysis comparing London against Toronto users by education tier, basic tool, the leverage came from picking that comparison. Sessions talking to each other still need a real question.

Ember | AI & Tech Sparks 的头像
Ember | AI & Tech Sparks1 个月前

Session‑to‑session chat turns Claude Code into a single‑IDE multi‑agent hub, enabling chained prompts without context loss.

相关视频

Motion graphics used to take me an hour per scene (or more) Now I'm creating them in 3-5 minutes — without After Effects, without Premiere, without writing a single line of code. I'm a former LA filmmaker (still PGA). My entire video stack is now 3 tools: Claude Code + HyperFrames (from HeyGen) + Descript Here's how the workflow runs: 1. Drop my brand style guide into a folder (colors, fonts, components Claude reuses forever) 2. Paste a line from my Descript transcript into Claude Code: "Create a scene for this part of the video" 3. Claude Code reads my brand, generates the HyperFrames scene, renders it to MP4 4. Drag the MP4 into Descript, drop it on the matching line of the transcript 5. Done. 3-5 minutes per scene. The unlock is the brand style guide. Once Claude has your colors, fonts, and reusable components, every scene inherits your look automatically. Bonus — you can take a Claude Design export (.zip), hand it to Claude Code, and it'll convert the HTML into a HyperFrames video you can render and edit. I built a GitHub repo with all the skills pre-loaded. Non-developers can clone it, open Claude Code, and be rendering scenes in under 10 minutes. Full walkthrough (20 min video) below Repo (skills + brand template + music-from-transcript plugin): Bookmark this if you make videos. The brand-style-guide pattern alone will save you hours every week. If you're a creator or operator using AI for content — share this with someone who's still living in After Effects.

JJ Englert

103,908 次观看 • 5 个月前

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.

Elias

14,096 次观看 • 4 个月前

this is pure f*cking treasure Anthropic devs just posted 20 GitHub repos that turn your Claude Code into a f*cking engineering team: Exposed for Opus 5.5 1. rtk: squeezes command output before it hits your context. the authors claim 60-90% fewer tokens 2. claude-mem: memory across sessions. records what the agent did and brings back what matters 3. ccusage: shows where your tokens and money went. one command, npx ccusage 4. Serena: search and edit code by meaning, not by text 5. Context7: up-to-date library docs, so Claude stops writing for last year's API 6. claude-context: your whole codebase searchable through MCP 7. Repomix: packs an entire repo into one AI-friendly file skills and method 8. superpowers: a skills framework and a full development methodology. the one almost everyone installs 9. skills: the official Agent Skills repo from Anthropic 10. spec-kit: spec-driven development, from GitHub itself 11. agents: a plugin marketplace for Claude Code and six other harnesses 12. claude-code-templates: ready configs and monitoring from one CLI 13. claude-code-hooks-mastery: hooks explained with working examples 14. awesome-claude-code: the hand-picked map of everything else running more than one agent 15. container-use: a separate container for every agent, so they stop breaking each other 16. claude-squad: several terminal agents in one window 17. Happy: control your agents from your phone, iOS and Android 18. claude-code-router: route requests across different models 19. ccstatusline: a status line that shows what your session is doing 20. tweakcc: edit Claude Code's own system prompts, toolsets and themes the stack in one line: memory keeps the context, skills set the method, containers let you run five agents instead of one. check each repo before you install. save this.

kiosa

55,680 次观看 • 3 天前

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,559 次观看 • 4 个月前