Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Claude Code used 3x fewer tokens with one change. - Before: 10.4M tokens · 10 errors · $9.21 - After: 3.7M tokens · 0 errors · $2.81 (read the full setup guide below)

Daily Dose of Data Science

50,338 subscribers

377,641 views • 4 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end

Agent Zero

846,672 views • 1 month ago

Stop letting your AI agent guess what’s inside the iOS Simulator. I built RocketSim’s CLI + Agent Skill so agents can inspect screens, tap, type, recover from state changes, and even validate accessibility support with far fewer tokens. Benchmarked against a popular alternative: 19% faster, 63% fewer estimated tokens, 0 wrong taps. Demo below 👇

Stop letting your AI agent guess what’s inside the iOS Simulator. I built RocketSim’s CLI + Agent Skill so agents can inspect screens, tap, type, recover from state changes, and even validate accessibility support with far fewer tokens. Benchmarked against a popular alternative: 19% faster, 63% fewer estimated tokens, 0 wrong taps. Demo below 👇

Antoine v.d. SwiftLee 

29,098 views • 3 months ago

Claude Code just got a memory upgrade. And it’s kind of insane. A free tool called Claude Mem lets Claude remember everything across sessions. The result? Up to 95% fewer tokens used. Which means faster workflows and way cheaper AI automation. This fixes Claude Code’s biggest weakness.

Claude Code just got a memory upgrade. And it’s kind of insane. A free tool called Claude Mem lets Claude remember everything across sessions. The result? Up to 95% fewer tokens used. Which means faster workflows and way cheaper AI automation. This fixes Claude Code’s biggest weakness.

Julian Goldie SEO

11,989 views • 5 months ago

SFUND Migration Page is LIVE BNB Chain holders can burn $SFUND before Oct 9, 10:00 UTC to claim on day one after the Phoenix Raise Tokens bought after that time won't be eligible You have 1 full year to migrate If providing liquidity, remove it first to access your tokens

SFUND Migration Page is LIVE BNB Chain holders can burn $SFUND before Oct 9, 10:00 UTC to claim on day one after the Phoenix Raise Tokens bought after that time won't be eligible You have 1 full year to migrate If providing liquidity, remove it first to access your tokens

Seedify

11,404 views • 11 months ago

FREE 2M tokens. Opus 4.8, GPT-5.5, and every major coding model in one API key. Plugs directly into Claude Code. Inferall gives you access to the full model stack - Opus 4.8, GPT-5.5, and every other serious coding model - through one unified API. Here's the exact setup: → go to inferall(.)ai with VPN or proxy → sign in and register with any email (Google accounts work best if you hit rate limits) → create an API key - copy the key in format ifu_xxxxxxxxxxxxxxxx → go to Billing → Add a card → Activate free tier → add your card - a card with zero balance works fine(!!) → set country to United States during checkout Done. 2,000,000 free tokens loaded. Plug into Claude Code or any agent stack: BASE_URL: API_KEY: ifu_XXXXXXXXXXXXXX Works with Claude Code, OpenCode, Hermes Agent, any OpenAI-compatible setup. Opus 4.8 available immediately. 2M tokens is enough for weeks of serious coding sessions.

FREE 2M tokens. Opus 4.8, GPT-5.5, and every major coding model in one API key. Plugs directly into Claude Code. Inferall gives you access to the full model stack - Opus 4.8, GPT-5.5, and every other serious coding model - through one unified API. Here's the exact setup: → go to inferall(.)ai with VPN or proxy → sign in and register with any email (Google accounts work best if you hit rate limits) → create an API key - copy the key in format ifu_xxxxxxxxxxxxxxxx → go to Billing → Add a card → Activate free tier → add your card - a card with zero balance works fine(!!) → set country to United States during checkout Done. 2,000,000 free tokens loaded. Plug into Claude Code or any agent stack: BASE_URL: API_KEY: ifu_XXXXXXXXXXXXXX Works with Claude Code, OpenCode, Hermes Agent, any OpenAI-compatible setup. Opus 4.8 available immediately. 2M tokens is enough for weeks of serious coding sessions.

Atenov int.

25,328 views • 2 months ago

Anthropic pays $750K/ year per senior engineer. The creator of Claude Code just revealed his setup. 24 minutes. Free. Straight from Boris Cherny himself. Bookmark this before you forget. Boris Cherny: "100% of my code is written by Claude Code. I run around 100 agents at one time." Then read the guide below.

Anthropic pays $750K/ year per senior engineer. The creator of Claude Code just revealed his setup. 24 minutes. Free. Straight from Boris Cherny himself. Bookmark this before you forget. Boris Cherny: "100% of my code is written by Claude Code. I run around 100 agents at one time." Then read the guide below.

Khairallah AL-Awady

207,524 views • 3 months ago

This 1-hour workshop on why your Claude Code runs out of tokens so fast will teach you more about making your sessions last longer than everything you've scrolled past this year. Bookmark this & watch, no matter what. After watching this, I built a CLI tool in Zig using that fixes the problem using Minimax-M2.7 on Claude code Here's how I built it; install it, then read the guide below by hoeem 🧵

This 1-hour workshop on why your Claude Code runs out of tokens so fast will teach you more about making your sessions last longer than everything you've scrolled past this year. Bookmark this & watch, no matter what. After watching this, I built a CLI tool in Zig using that fixes the problem using Minimax-M2.7 on Claude code Here's how I built it; install it, then read the guide below by hoeem 🧵

Avid

18,938 views • 4 months ago

Everyone uploading PDFs to Claude is burning 70,000 tokens before asking a single question. A 20-page document costs between 1,500 to 3,000 tokens per page. Formatting. Broken tables. Images. Junk metadata. Claude processes all of it before you even type “summarize this.” There’s a free fix. It’s called Markitdown. Microsoft built it. 10,000+ GitHub stars. Almost nobody in the Claude community is talking about it. It converts any file PDFs, Word docs, Excel sheets, PowerPoints, YouTube videos into clean Markdown text. Token usage drops by up to 70%. Answers get better, not worse. Claude was trained on millions of Markdown documents. It reads the format natively. You’re not compressing quality you’re removing noise. There’s an MCP server too. Connect it to Claude Desktop once. Every file you upload auto-converts to .md before Claude touches it. You do nothing. It just works. Old way: upload PDF → Claude burns 70k tokens on junk → mediocre answer New way: Markitdown → clean .md → 70% fewer tokens → sharper answer The tool is free. The MCP setup takes 10 minutes. The token savings are permanent. You’ve been paying for Claude to read garbage. Stop.

Everyone uploading PDFs to Claude is burning 70,000 tokens before asking a single question. A 20-page document costs between 1,500 to 3,000 tokens per page. Formatting. Broken tables. Images. Junk metadata. Claude processes all of it before you even type “summarize this.” There’s a free fix. It’s called Markitdown. Microsoft built it. 10,000+ GitHub stars. Almost nobody in the Claude community is talking about it. It converts any file PDFs, Word docs, Excel sheets, PowerPoints, YouTube videos into clean Markdown text. Token usage drops by up to 70%. Answers get better, not worse. Claude was trained on millions of Markdown documents. It reads the format natively. You’re not compressing quality you’re removing noise. There’s an MCP server too. Connect it to Claude Desktop once. Every file you upload auto-converts to .md before Claude touches it. You do nothing. It just works. Old way: upload PDF → Claude burns 70k tokens on junk → mediocre answer New way: Markitdown → clean .md → 70% fewer tokens → sharper answer The tool is free. The MCP setup takes 10 minutes. The token savings are permanent. You’ve been paying for Claude to read garbage. Stop.

Veltrx

109,383 views • 2 months ago

Cancel your Saturday night plans. Read the 33-page Claude Skills guide Anthropic just dropped. $5K/month. $10K/month. $20K/month. People are building systems that remember everything. automate everything. run everything. Meanwhile you're re-explaining your workflow to Claude. again. for the 100th time. While you're wasting tokens on context — someone just taught Claude their entire job in 15 minutes. Same Saturday. Different decision. One folder. One SKILL.md file. That's it. Guide below.

Cancel your Saturday night plans. Read the 33-page Claude Skills guide Anthropic just dropped. $5K/month. $10K/month. $20K/month. People are building systems that remember everything. automate everything. run everything. Meanwhile you're re-explaining your workflow to Claude. again. for the 100th time. While you're wasting tokens on context — someone just taught Claude their entire job in 15 minutes. Same Saturday. Different decision. One folder. One SKILL.md file. That's it. Guide below.

Kirill

16,060 views • 4 months ago

Boris Cherny (Claude Code's creator): I deleted my IDE in November and hasn't opened it since. I writes more code than ever. his actual words on stage: I don't prompt Claude anymore. I have loops that are running. They're the ones prompting Claude. My job is to write loops. the progression he described: → a year ago: writing code by hand with autocomplete → then: running 5-10 Claudes in parallel, prompting each one → now: he doesn't prompt at all - he writes the loops that prompt Claude what it's already done inside Anthropic: • ~3x more code shipped per engineer (he says that number is already outdated and higher) • Cowork - a full product - built in ~8 days, 100% with Claude Code • designers, the finance guy, even the chief of staff now ship code his advice to founders: give everyone as many tokens as possible, and underfund every project on purpose - 2 engineers + a pile of tokens instead of 4. the roles are melting into one "builder." Watch this, than read the article below

Boris Cherny (Claude Code's creator): I deleted my IDE in November and hasn't opened it since. I writes more code than ever. his actual words on stage: I don't prompt Claude anymore. I have loops that are running. They're the ones prompting Claude. My job is to write loops. the progression he described: → a year ago: writing code by hand with autocomplete → then: running 5-10 Claudes in parallel, prompting each one → now: he doesn't prompt at all - he writes the loops that prompt Claude what it's already done inside Anthropic: • ~3x more code shipped per engineer (he says that number is already outdated and higher) • Cowork - a full product - built in ~8 days, 100% with Claude Code • designers, the finance guy, even the chief of staff now ship code his advice to founders: give everyone as many tokens as possible, and underfund every project on purpose - 2 engineers + a pile of tokens instead of 4. the roles are melting into one "builder." Watch this, than read the article below

Morty

136,663 views • 3 months ago

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

Avi Chawla

113,219 views • 2 months ago

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

raymel 👋

201,405 views • 3 months ago

Claude is actually a beast for web design. this guy just dropped a full guide on how to design and build interactive animated 3D websites with Claude Code watch the video and read the full guidelines on the article below

Claude is actually a beast for web design. this guy just dropped a full guide on how to design and build interactive animated 3D websites with Claude Code watch the video and read the full guidelines on the article below

Rahul

62,098 views • 19 days ago

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓

codila

544,510 views • 1 month ago

Boris Cherny has merged around 1,700 pull requests, added 400,000 lines of code, and deleted 250,000, all with Claude Code, this year. And used 8 billion tokens. “100% of my code has been written by Claude Code since Opus 4.5. That was around November of last year. ... Most of my coding now happens on my phone.” ---- From "Scale" YouTube channel, (full video link in comment)

Boris Cherny has merged around 1,700 pull requests, added 400,000 lines of code, and deleted 250,000, all with Claude Code, this year. And used 8 billion tokens. “100% of my code has been written by Claude Code since Opus 4.5. That was around November of last year. ... Most of my coding now happens on my phone.” ---- From "Scale" YouTube channel, (full video link in comment)

Rohan Paul

14,397 views • 1 month ago

Dylan on why access to the most intelligent AI models will determine who wins in every industry: "What really matters is access to the most intelligent tokens and leveraging them at the highest-value tasks. A lot of folks will want tokens, but the shitty SaaS startup in SF who is using Claude is not necessarily creating a ton of value, and therefore they're going to get priced out of tokens. Anthropic only released Mythos to certain companies for cybersecurity. You also don't want people to distill your model so you release them to a fewer and fewer customers. Those customers are now wrestling over the tokens. Token usage and therefore the additional value generated on top of those tokens aggregates among fewer and fewer companies. I don't have Mythos but you know who has Mythos, top banks. There are people like Ken Griffin of Citadel who can just sign a deal with OpenAI or Antrhopic for access to your models. I'll buy the first $10 billion worth of tokens each year. So whenever you release the model, I'll spend the first 10 billion tokens and then everyone else can get the model after that. Now, he's going to crush everyone in the markets. I can envision because I have an enterprise Anthropic contract and Anthropic people like me, they're willing to give us slightly earlier access or higher rate limits, and then my competitor doesn't have that, and I'm able to f*cking crush them."

Dylan on why access to the most intelligent AI models will determine who wins in every industry: "What really matters is access to the most intelligent tokens and leveraging them at the highest-value tasks. A lot of folks will want tokens, but the shitty SaaS startup in SF who is using Claude is not necessarily creating a ton of value, and therefore they're going to get priced out of tokens. Anthropic only released Mythos to certain companies for cybersecurity. You also don't want people to distill your model so you release them to a fewer and fewer customers. Those customers are now wrestling over the tokens. Token usage and therefore the additional value generated on top of those tokens aggregates among fewer and fewer companies. I don't have Mythos but you know who has Mythos, top banks. There are people like Ken Griffin of Citadel who can just sign a deal with OpenAI or Antrhopic for access to your models. I'll buy the first $10 billion worth of tokens each year. So whenever you release the model, I'll spend the first 10 billion tokens and then everyone else can get the model after that. Now, he's going to crush everyone in the markets. I can envision because I have an enterprise Anthropic contract and Anthropic people like me, they're willing to give us slightly earlier access or higher rate limits, and then my competitor doesn't have that, and I'm able to f*cking crush them."

Patrick OShaughnessy

36,100 views • 4 months ago

AMD'S NEW MINI PC RUNS CLAUDE CODE OFFLINE FOR $0/MONTH AND REPLACES $200 OPENAI + $200 CLAUDE CODE SUBSCRIPTIONS amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 coder 30b at 40 to 50 tokens per second and llama 3.3 70b at 20 to 25 tokens per second locally. on linux you get 110gb of usable vram out of 128gb setup takes 90 minutes. wipe windows for linux, install ollama with one command, pull the model, point claude code at localhost. same interface, same agent loop, nothing leaves your network a heavy ai user pays $200 for claude code max, $200 for chatgpt pro and $20 for cursor. that's $5,040 a year and the box pays itself off in 5 months after break-even every month is $420 that used to leave your account. three year math is roughly $13,000 not paid to ai companies plus zero rate limits on overnight agents bookmark this and read the article below

AMD'S NEW MINI PC RUNS CLAUDE CODE OFFLINE FOR $0/MONTH AND REPLACES $200 OPENAI + $200 CLAUDE CODE SUBSCRIPTIONS amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 coder 30b at 40 to 50 tokens per second and llama 3.3 70b at 20 to 25 tokens per second locally. on linux you get 110gb of usable vram out of 128gb setup takes 90 minutes. wipe windows for linux, install ollama with one command, pull the model, point claude code at localhost. same interface, same agent loop, nothing leaves your network a heavy ai user pays $200 for claude code max, $200 for chatgpt pro and $20 for cursor. that's $5,040 a year and the box pays itself off in 5 months after break-even every month is $420 that used to leave your account. three year math is roughly $13,000 not paid to ai companies plus zero rate limits on overnight agents bookmark this and read the article below

starmex

33,516 views • 2 months ago

$THIS GUY AUDITED 926 CLAUDE CODE SESSIONS AND FOUND MOST OF THE TOKEN WASTE WAS ON HIS SIDE everyone is blaming anthropic for the limits, so he decided to actually look at the data 858 sessions, 18,903 turns, and $1,619 estimated spend across 33 days here's what he found: 1\ one default setting was burning 14,000 tokens per turn Claude Code loads the full JSON schema for every tool into context at session start. whether you use them or not. 20,000 tokens of tool definitions sitting there on every single turn. the fix: one line in your settings.json "ENABLE_TOOL_SEARCH": "true" context dropped from 45K to 20K instantly. across 858 sessions that one setting was wasting an estimated 264 million tokens 2\ cache expiry is the single biggest waste 54% of his turns came after a 5+ minute idle gap. every one of those turns re-processed the entire conversation at full price which caused a 10x cost jump you go grab coffee. come back 5 minutes later. type your next message. everything rebuilds from scratch. the context didn't change. you didn't change. the cache just expired. 12.3 million tokens wasted on idle gaps alone 3\ 42 skills loaded. 19 of them used twice or less across 858 sessions. every one of those skill schemas sat in context on every turn eating tokens for nothing. 4\ 1,122 redundant file reads where the same file was read 3+ times one session read the same file 33 times. he ALSO built a full token auditor dashboard that shows you exactly where your waste is coming from 19 charts, opens in your browser, free AND open source$

THIS GUY AUDITED 926 CLAUDE CODE SESSIONS AND FOUND MOST OF THE TOKEN WASTE WAS ON HIS SIDE everyone is blaming anthropic for the limits, so he decided to actually look at the data 858 sessions, 18,903 turns, and $1,619 estimated spend across 33 days here's what he found: 1\ one default setting was burning 14,000 tokens per turn Claude Code loads the full JSON schema for every tool into context at session start. whether you use them or not. 20,000 tokens of tool definitions sitting there on every single turn. the fix: one line in your settings.json "ENABLE_TOOL_SEARCH": "true" context dropped from 45K to 20K instantly. across 858 sessions that one setting was wasting an estimated 264 million tokens 2\ cache expiry is the single biggest waste 54% of his turns came after a 5+ minute idle gap. every one of those turns re-processed the entire conversation at full price which caused a 10x cost jump you go grab coffee. come back 5 minutes later. type your next message. everything rebuilds from scratch. the context didn't change. you didn't change. the cache just expired. 12.3 million tokens wasted on idle gaps alone 3\ 42 skills loaded. 19 of them used twice or less across 858 sessions. every one of those skill schemas sat in context on every turn eating tokens for nothing. 4\ 1,122 redundant file reads where the same file was read 3+ times one session read the same file 33 times. he ALSO built a full token auditor dashboard that shows you exactly where your waste is coming from 19 charts, opens in your browser, free AND open source

Om Patel

299,832 views • 4 months ago

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast

Mnimiy

1,380,902 views • 4 months ago

10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens 1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. 2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. 3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. 4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. 5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. 6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. 7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. 8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. 9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. 10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. Save this before your next agent session burns through your subscription 👇

10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens 1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. 2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. 3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. 4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. 5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. 6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. 7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. 8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. 9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. 10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. Save this before your next agent session burns through your subscription 👇

unicode

66,891 views • 19 days ago