Loading video...

Video Failed to Load

Go Home

How to manage secrets with worktrees: Files that are untracked in Git will NOT be copied over to new worktrees (Codex, Claude Code, & Conductor included) Claude Code introduced .worktreeinclude, which uses glob syntax to copy untracked files into new directories - these can be .env files, secrets, or...

mattyp's profile picture

matt palmer

43,038 subscribers

27,552 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!
6:22

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!

Chris ☕️

70,187 views • 4 months ago

New easy way to earn for free with our phone using the DePIN project DeNet and their newly launched "Watcher node" feature. Also very impressive to see DeNet migrating to join peaq , a layer 1 chain designed for #DePIN and all the various DePIN devices that are utilized. With the new "Watcher node" feature in their app anyone is able to join and start validating files in their decentralized storage network. From validating files we earn the $WN that will determine how much of their upcoming airdrop we will get. To validate files we can simply run the app in the background of the phone and it will validate files daily/earn WN. To get 1000 WN instantly anyone can put in the following ref code in the app if you want: 0x2580c735fcebab94ddd88d6f45dbf453ecbe8780 Or you can get straight to the DeNet app (not a ref link) on your phone through here: There are also additional ways to be able to validate more files per day/earn more WN by completing social tasks that are available in the app and also referring friends.
0:57

New easy way to earn for free with our phone using the DePIN project DeNet and their newly launched "Watcher node" feature. Also very impressive to see DeNet migrating to join peaq , a layer 1 chain designed for #DePIN and all the various DePIN devices that are utilized. With the new "Watcher node" feature in their app anyone is able to join and start validating files in their decentralized storage network. From validating files we earn the $WN that will determine how much of their upcoming airdrop we will get. To validate files we can simply run the app in the background of the phone and it will validate files daily/earn WN. To get 1000 WN instantly anyone can put in the following ref code in the app if you want: 0x2580c735fcebab94ddd88d6f45dbf453ecbe8780 Or you can get straight to the DeNet app (not a ref link) on your phone through here: There are also additional ways to be able to validate more files per day/earn more WN by completing social tasks that are available in the app and also referring friends.

Nordic

67,368 views • 1 year ago

"Every morning, I type '/today' into Claude Code and watch it generate my to-do list." Here's my new episode with Teresa Torres where she demos how she uses two Claude Code terminals and a note taking app (Obsidian) to run her entire life and business. We cover: ✅ Her 3-layer context system (global rules → project rules → reference files) ✅ Writing 9,000-word blog posts in 1.5 days with Claude Code as a thought partner ✅ How to set up a personal OS with Claude Code step by step Some quotes from Teresa: "Whenever you explain something to Claude, stop and ask—will I have to explain this again? Then capture it in a context file." "I wrote 9,000 words in 1.5 days. There's no way I would have done this myself." "You don't have to get here overnight. Every time you do a new task, just ask—how can Claude help with this?" 📌 Watch now:
1:01

"Every morning, I type '/today' into Claude Code and watch it generate my to-do list." Here's my new episode with Teresa Torres where she demos how she uses two Claude Code terminals and a note taking app (Obsidian) to run her entire life and business. We cover: ✅ Her 3-layer context system (global rules → project rules → reference files) ✅ Writing 9,000-word blog posts in 1.5 days with Claude Code as a thought partner ✅ How to set up a personal OS with Claude Code step by step Some quotes from Teresa: "Whenever you explain something to Claude, stop and ask—will I have to explain this again? Then capture it in a context file." "I wrote 9,000 words in 1.5 days. There's no way I would have done this myself." "You don't have to get here overnight. Every time you do a new task, just ask—how can Claude help with this?" 📌 Watch now:

Peter Yang

258,567 views • 7 months ago

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor
1:05

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor

Chris Ashby

11,258 views • 1 month ago

🚨NEW: Stephen A. Smith *DOUBLES DOWN* on CALLING OUT Dems for not releasing Epstein Files under Biden🚨 "Don't tell me that you could not have done it! ... Where there's a will, there's a way! And you can't tell me that if you wanted those Epstein files opened over the previous 4 years that you couldn't have found a way to get those files open!" "It appears, particularly as we learn more and more and more, that there was an incentive for various elected officials not to prioritize getting these files opened." Daily Caller
1:56

🚨NEW: Stephen A. Smith *DOUBLES DOWN* on CALLING OUT Dems for not releasing Epstein Files under Biden🚨 "Don't tell me that you could not have done it! ... Where there's a will, there's a way! And you can't tell me that if you wanted those Epstein files opened over the previous 4 years that you couldn't have found a way to get those files open!" "It appears, particularly as we learn more and more and more, that there was an incentive for various elected officials not to prioritize getting these files opened." Daily Caller

Jason Cohen 🇺🇸

40,618 views • 8 months ago

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.
0:22

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,240 views • 5 months ago

Mike Benz explains how we can get the rest of the Jeffrey Epstein files released He says a new bill must be created by Congress specifically directed at the CIA “What it may require, because all these disclosures are forced by a bill from Thomas Massie that passed 426 to 1 for the Justice Department side of these disclosures. It is my view that the files around Epstein's intelligence ties are not held at DOJ. It may take a separate legislative bill to coerce disclosures from our intelligence agencies, which was how we got the JFK files in the 1990s. When Congress passed a bill forcing the CIA to begin disclosing JFK files, that may be the next step if these files are insufficient. That's where we got to go. And Congress has to step in and force the CIA to release those files.”
0:41

Mike Benz explains how we can get the rest of the Jeffrey Epstein files released He says a new bill must be created by Congress specifically directed at the CIA “What it may require, because all these disclosures are forced by a bill from Thomas Massie that passed 426 to 1 for the Justice Department side of these disclosures. It is my view that the files around Epstein's intelligence ties are not held at DOJ. It may take a separate legislative bill to coerce disclosures from our intelligence agencies, which was how we got the JFK files in the 1990s. When Congress passed a bill forcing the CIA to begin disclosing JFK files, that may be the next step if these files are insufficient. That's where we got to go. And Congress has to step in and force the CIA to release those files.”

Wall Street Apes

184,416 views • 6 months ago

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.
0:24

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

Yarchi

62,979 views • 1 month ago

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:
1:18

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:

Daniel San

20,460 views • 7 months ago

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
31:22

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

311,034 views • 2 months ago

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
13:23

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 views • 2 months ago

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering
0:56

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

Om Patel

159,475 views • 4 months ago

the engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work I've seen $300 courses that don't cover what he shows in the first 10 minutes CLAUDE.md files, memory shortcuts, parallel sessions, prompting patterns all in one video and completely free works whether you're a developer, a beginner, or someone who's been using Claude for months based on this, I put together 18 things you can copy and use in Claude today full guide in the article below
27:52

the engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work I've seen $300 courses that don't cover what he shows in the first 10 minutes CLAUDE.md files, memory shortcuts, parallel sessions, prompting patterns all in one video and completely free works whether you're a developer, a beginner, or someone who's been using Claude for months based on this, I put together 18 things you can copy and use in Claude today full guide in the article below

Anatoli Kopadze

6,309,522 views • 2 months ago

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 views • 1 month ago

Building “RAG 2.0” is just making Claude Code running over your filesystem 🤖🗂️ To make this work well, you need to solve three things 1️⃣ Virtualize your filesystem to prevent the agent from messing stuff up. AgentFS by Turso is a nice example of how you can give the agent access to a copy of all your files without messing up your raw data. 2️⃣ Parse unstructured documents like PDFs, pptx, Word into an LLM-ready format. Agentic OCR solutions like LlamaParse can help here 3️⃣ Creating an agentic loop with human-in-the-loop. If you want to control the agent implementation instead of using Claude Code out of the box, you can use LlamaIndex 🦙 workflows to help orchestrate these long-running agent tasks. Shoutout Clelia Bertelli (🦙/acc), check it out! Blog: Repo:
1:35

Building “RAG 2.0” is just making Claude Code running over your filesystem 🤖🗂️ To make this work well, you need to solve three things 1️⃣ Virtualize your filesystem to prevent the agent from messing stuff up. AgentFS by Turso is a nice example of how you can give the agent access to a copy of all your files without messing up your raw data. 2️⃣ Parse unstructured documents like PDFs, pptx, Word into an LLM-ready format. Agentic OCR solutions like LlamaParse can help here 3️⃣ Creating an agentic loop with human-in-the-loop. If you want to control the agent implementation instead of using Claude Code out of the box, you can use LlamaIndex 🦙 workflows to help orchestrate these long-running agent tasks. Shoutout Clelia Bertelli (🦙/acc), check it out! Blog: Repo:

Jerry Liu

55,620 views • 7 months ago

Claude Code just shipped v2.1.69 with a new built-in skill: /claude-api It detects your language, picks the right surface (direct API, tool use, or Agent SDK), and loads the relevant reference docs directly into context. Covers streaming, batches, files API, structured outputs, tool use patterns, MCP, also sets model defaults so you're not guessing. Useful when you're building on top of Claude and don't want to context-switch to the docs every 5 minutes.
0:29

Claude Code just shipped v2.1.69 with a new built-in skill: /claude-api It detects your language, picks the right surface (direct API, tool use, or Agent SDK), and loads the relevant reference docs directly into context. Covers streaming, batches, files API, structured outputs, tool use patterns, MCP, also sets model defaults so you're not guessing. Useful when you're building on top of Claude and don't want to context-switch to the docs every 5 minutes.

Daniel San

152,831 views • 5 months ago

Claude Code Templates now has a web interface for browsing and contributing templates 🙌 What it does: Install templates for different languages/frameworks to get started with Claude Code faster. How to use: - Go to - Run: npm install -g claude-code-templates - Pick a template from the site - Copy and run the template command - Start coding with Claude Code The whole thing runs on GitHub - no fancy backend, no hidden stuff. Everything you're installing is right there in the repo for you to inspect. Contributing: Want to add your own template? Just follow the contribution guide and send a PR. Once merged, it automatically shows up on the site. That's it... nothing fancy, just something to save a few minutes when starting new projects with Claude Code Repo:
2:15

Claude Code Templates now has a web interface for browsing and contributing templates 🙌 What it does: Install templates for different languages/frameworks to get started with Claude Code faster. How to use: - Go to - Run: npm install -g claude-code-templates - Pick a template from the site - Copy and run the template command - Start coding with Claude Code The whole thing runs on GitHub - no fancy backend, no hidden stuff. Everything you're installing is right there in the repo for you to inspect. Contributing: Want to add your own template? Just follow the contribution guide and send a PR. Once merged, it automatically shows up on the site. That's it... nothing fancy, just something to save a few minutes when starting new projects with Claude Code Repo:

Daniel San

60,766 views • 1 year ago

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.
10:52

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 views • 7 months ago

#WATCH | Lucknow: Samajwadi Party chief Akhilesh Yadav says, "We don't want to discuss the Epstein files. Social media is a big problem. The Epstein files must have been created long ago, and they came out after so many days. There are many countries in the world that have created their own social media... Therefore, in this changing world, it is necessary that we remain cautious, and the Epstein files are just one topic. You have handed over your entire market to America... We will give them a market worth $500 billion, and just a few days ago we bought Rafale jets... So what will happen to Make in India? What will happen to Skill India?..."
1:57

#WATCH | Lucknow: Samajwadi Party chief Akhilesh Yadav says, "We don't want to discuss the Epstein files. Social media is a big problem. The Epstein files must have been created long ago, and they came out after so many days. There are many countries in the world that have created their own social media... Therefore, in this changing world, it is necessary that we remain cautious, and the Epstein files are just one topic. You have handed over your entire market to America... We will give them a market worth $500 billion, and just a few days ago we bought Rafale jets... So what will happen to Make in India? What will happen to Skill India?..."

ANI

141,797 views • 5 months ago