正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I’ve been asked a lot why I keep Claude Code auto-compact turned off. Here’s why 👇 If you configure commands, sub-agents, and hooks properly, you almost never hit auto-compact. Every time it triggered for me, I lost important context. After looking at how compaction actually works, it was clear... show more

Daniel San

32,511 subscribers

105,569 次观看 • 6 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Share Claude Code sessions with this command 👇 Just shipped v1.26.1 of claude-code-templates because I kept needing to hand off work mid-session. Run: npx claude-code-templates@latest --chats - All your sessions grouped by chat - Download any conversation To share a session: - Share the file, and add it to your project - Then run: claude "read @ chat-file .md and continue" Or if you are in the same account click on "Resume" and you will see the command: claude --resume session_id Built this to keep context flowing across the team without losing momentum.

Share Claude Code sessions with this command 👇 Just shipped v1.26.1 of claude-code-templates because I kept needing to hand off work mid-session. Run: npx claude-code-templates@latest --chats - All your sessions grouped by chat - Download any conversation To share a session: - Share the file, and add it to your project - Then run: claude "read @ chat-file .md and continue" Or if you are in the same account click on "Resume" and you will see the command: claude --resume session_id Built this to keep context flowing across the team without losing momentum.

Daniel San

10,787 次观看 • 8 个月前

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Daniel San

51,636 次观看 • 2 个月前

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

57,910 次观看 • 5 个月前

Claude Code Teams as a flow diagram Just run: npx claude-code-templates@latest --teams You’ll get a full view of how the lead and the team communicate: messages, tasks, and the tools they executed. The more observability you have into your Claude Code agents’ workflows, the better your workflows, and the better the results. Open source project:

Claude Code Teams as a flow diagram Just run: npx claude-code-templates@latest --teams You’ll get a full view of how the lead and the team communicate: messages, tasks, and the tools they executed. The more observability you have into your Claude Code agents’ workflows, the better your workflows, and the better the results. Open source project:

Daniel San

85,478 次观看 • 4 个月前

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anatoli Kopadze

309,726 次观看 • 1 个月前

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Daniel San

28,410 次观看 • 1 年前

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

Mnimiy

20,635 次观看 • 1 个月前

Working with Claude Code involves a lot of waiting around for Claude to figure out what it needs to complete a task. There's a better way though! Priming Claude Code with Repo Prompt context lets you get better code faster from agents like Claude Code. Let's dive in 👇

Working with Claude Code involves a lot of waiting around for Claude to figure out what it needs to complete a task. There's a better way though! Priming Claude Code with Repo Prompt context lets you get better code faster from agents like Claude Code. Let's dive in 👇

eric provencher

42,523 次观看 • 11 个月前

Best way to debug Claude Code sessions and inspect agent context. Just Run: npx claude-code-templates@latest --chats Browser interface with advanced search across all your sessions (name, ID, directory, dates, message content). Shows every tool call with exact JSON executed. Resume button lets you continue any session - efficient context loading. Runs completely local and open source 👏

Best way to debug Claude Code sessions and inspect agent context. Just Run: npx claude-code-templates@latest --chats Browser interface with advanced search across all your sessions (name, ID, directory, dates, message content). Shows every tool call with exact JSON executed. Resume button lets you continue any session - efficient context loading. Runs completely local and open source 👏

Daniel San

32,861 次观看 • 8 个月前

Introducing Claude Code Analytics Dashboard 🙌 Open source project to monitor your Claude Code agents in real-time as they work on your projects. Just run: npx claude-code-templates@latest --analytics Dashboard opens at localhost:3333 showing: - All active Claude Code sessions - Token usage & conversation stats - Real-time activity monitoring - Message history with export (CSV/JSON) Perfect for devs running multiple Claude Code agents - finally see what they're actually doing! The conversation view shows full chat history, token breakdowns, and current status. Finally understand your AI workflow patterns. Best part... Everything runs locally with total privacy! Sharing repo in first comment if you want to star or contribute 👇

Introducing Claude Code Analytics Dashboard 🙌 Open source project to monitor your Claude Code agents in real-time as they work on your projects. Just run: npx claude-code-templates@latest --analytics Dashboard opens at localhost:3333 showing: - All active Claude Code sessions - Token usage & conversation stats - Real-time activity monitoring - Message history with export (CSV/JSON) Perfect for devs running multiple Claude Code agents - finally see what they're actually doing! The conversation view shows full chat history, token breakdowns, and current status. Finally understand your AI workflow patterns. Best part... Everything runs locally with total privacy! Sharing repo in first comment if you want to star or contribute 👇

Daniel San

62,057 次观看 • 1 年前

1/ Keep running claude -p on your Claude Code subscription after June 15. A 200-line bash wrapper pipes your prompt into the Claude Code session you already have open. The call rides your subscription, not the new Agent SDK credit bucket. Looks like claude -p. Runs on the plan you already pay for. How it works 👇

1/ Keep running claude -p on your Claude Code subscription after June 15. A 200-line bash wrapper pipes your prompt into the Claude Code session you already have open. The call rides your subscription, not the new Agent SDK credit bucket. Looks like claude -p. Runs on the plan you already pay for. How it works 👇

AI Builder Club

25,901 次观看 • 1 个月前

update: the blackhole pivoted ⚫️ it started as a break reminder. then Jeryd asked "can it grow based on how many tokens I'm using?" and Romina Roman made the fair point that the $20 plan is already a built-in break reminder 😅 so now it's a context usage indicator for Claude Code: the more context you burn, the bigger it gets the blackhole reminds you to /compact 💀

update: the blackhole pivoted ⚫️ it started as a break reminder. then Jeryd asked "can it grow based on how many tokens I'm using?" and Romina Roman made the fair point that the $20 plan is already a built-in break reminder 😅 so now it's a context usage indicator for Claude Code: the more context you burn, the bigger it gets the blackhole reminds you to /compact 💀

s13k

27,592 次观看 • 24 天前

Here's what you get when you let Claude Code run wild on an idea. I didn't add any specific prompts for these details. The first prompt was to create a theme park, then let it keep iterating and improving. The result looks amazing

Here's what you get when you let Claude Code run wild on an idea. I didn't add any specific prompts for these details. The first prompt was to create a theme park, then let it keep iterating and improving. The result looks amazing

Dilum Sanjaya

16,310 次观看 • 5 个月前

Anthropic didn't build a better model to make Claude Code work. They built a better environment around it. 55 directories. 331 modules. Context compaction so sessions run for hours. Streaming tool execution that saves seconds per turn. Read this article for full breakdown.

Anthropic didn't build a better model to make Claude Code work. They built a better environment around it. 55 directories. 331 modules. Context compaction so sessions run for hours. Streaming tool execution that saves seconds per turn. Read this article for full breakdown.

Rohit

124,966 次观看 • 2 个月前

Claude Code Templates now supports Settings & Hooks! just got a major update. You can now: ✅ Browse and install Settings & Hooks alongside Agents, Commands & MCPs ✅ Build complete stacks with one command ✅ Customize your Claude Code experience exactly how you want Select what you need → Add to cart → Copy command → Install. Done 🙌 Check it out on GitHub

Claude Code Templates now supports Settings & Hooks! just got a major update. You can now: ✅ Browse and install Settings & Hooks alongside Agents, Commands & MCPs ✅ Build complete stacks with one command ✅ Customize your Claude Code experience exactly how you want Select what you need → Add to cart → Copy command → Install. Done 🙌 Check it out on GitHub

Daniel San

29,737 次观看 • 10 个月前

built a small CLI tool that moves your AI coding session context between Claude Code, Gemini, Copilot, Codex and OpenCode when you hit rate limits. no more re-explaining what you were doing, or painful copy/paste from terminal that lose tool-call context. just `npx continues`

built a small CLI tool that moves your AI coding session context between Claude Code, Gemini, Copilot, Codex and OpenCode when you hit rate limits. no more re-explaining what you were doing, or painful copy/paste from terminal that lose tool-call context. just `npx continues`

Yigit Konur

213,557 次观看 • 4 个月前

$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$

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

55,345 次观看 • 25 天前

Claude Code is now free to run. Most people still think you need a paid setup. Here’s the basic flow: → Install Claude Code with the official installer. → Create a free OpenRouter account. → Grab your API key. → Install Claude Code Router. → Point Claude Code to the local router. → Choose a free model with the :free suffix. → Run CCR code instead of normal Claude Code. → Check /status to confirm it works. You keep the Claude Code workflow. You just route it through a free model.

Claude Code is now free to run. Most people still think you need a paid setup. Here’s the basic flow: → Install Claude Code with the official installer. → Create a free OpenRouter account. → Grab your API key. → Install Claude Code Router. → Point Claude Code to the local router. → Choose a free model with the :free suffix. → Run CCR code instead of normal Claude Code. → Check /status to confirm it works. You keep the Claude Code workflow. You just route it through a free model.

Julian Goldie SEO

17,618 次观看 • 1 个月前

So many people wanted to see my knowledge management system in Claude code, so here it is. All you need is Obsidian, Claude Code, GitHub, and the will to live and you too can set up your second brain in under 2 hours. If you want to learn how to build this, here’s the demo link:

So many people wanted to see my knowledge management system in Claude code, so here it is. All you need is Obsidian, Claude Code, GitHub, and the will to live and you too can set up your second brain in under 2 hours. If you want to learn how to build this, here’s the demo link:

Allie K. Miller

51,555 次观看 • 2 个月前

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

24,787 次观看 • 6 天前