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 cost - After: 3.7M tokens · 0 errors · $2.81 cost I used InsForge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). With Supabase,... tables, RLS policies, auth providers, storage buckets, and edge functions were retrieved through separate calls. Each response entered the conversation history, so later calls carried more context. But InsForge returned the backend topology in one metadata call of roughly 500 tokens. InsForge repo: (don't forget to star it 🌟) Its instructions were also split into narrow skills for CLI operations, debugging, SDK usage, and integrations. Claude loaded only the instructions needed for the task. The CLI returned structured JSON with semantic exit codes as well. This made it clear whether a failure came from the operation itself or the code being executed, avoiding several retry loops. The token savings essentially came from replacing repeated backend discovery and debugging calls with one structured view of the backend. I wrote a detailed walkthrough of both builds, including where the extra calls, tokens, and errors came from. Read it below.show more

Avi Chawla

77,196 subscribers

65,041 views • 18 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

17 Comments

deezzex18 days ago

so basically you taught claude to ask once instead of 20 times. respect

Avi Chawla18 days ago

that's correct

Ben Ellsworth18 days ago

The one metadata call replacing a bunch of separate ones explains most of the token drop. Curious what was actually causing the 10 errors before, guessing it was drift from all that extra context piling up in the history

Bally_AgenticAI16 days ago

The 3x drop isn't from a smarter model - it's from replacing 5 chatty discovery calls with 1 structured state dump. Most token bloat is architecture, not reasoning. #ContextEngineering #AgenticAI @LangChain

kocer18 days ago

3x fewer tokens and zero errors is a clean result. most people just keep dumping more context instead of structuring it once

Marwan Atef18 days ago

tool schema is product design. raw API passthrough is how you burn context and teach the model to guess.

AXIALIS | Desktop App Tools18 days ago

How much of the token reduction survives if you normalize for the error retry loop in the baseline run?

rocket0x01 | ETHGas ⛽18 days ago

most teams skip evals because it feels like homework then a single prompt edit silently breaks 30% of their flows

Gregor18 days ago

10 errors to 0 is the real headline here

Viliana18 days ago

This is usefull content🫡

Varik Verilion18 days ago

10.4 over 3.7 is 2.8x, not quite 3x. the errors dropping to 0 is honestly the more interesting number here, that's the part that actually saves you debugging time, not just the token count.

AI Mastery Guide17 days ago

Zero errors too, not just cheaper

The Bull 🐂17 days ago

Thats called over engineering lmao

The AI Therapist18 days ago

3.7M tokens for zero errors? that’s not an efficiency hack. it’s the difference between a junior who asks questions and one who actually reads instructions. stop paying for curiosity. charge for answers

Corp17 days ago

3x fewer tokens is a serious systems win. — corp

Giordano Bruno17 days ago

This would cost around $0.10 cents on DeepSeek. I am genuinely shocked at the cost here. Just built Golang Htmx Alpine Tailwind Front end with Gitea worktrees and Go CMS system synced to Obsidian template tool with AI prompt injection for articles,scheduling etc $3 Wild.

How They Make Money17 days ago

Love a number with dirt on it—messy progress beats vanity graphs. That "Claude Code used fewer" line stuck.

Related Videos

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 • 3 months ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

123,101 views • 3 months ago

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 views • 1 year ago

Claude Code is now scary good at full-stack! I asked it to build a real-time weather intelligence dashboard with an interactive 3D globe and a forecasting layer that predicts weather 3 days ahead. It came back with a spinning globe that has a day/night cycle using NASA satellite imagery, city lights on the dark side, weather icons that switch between sun and moon based on local time, and a time travel slider that scrubs through 10 days of data. Claude Code built the whole thing in a single session, including the backend, database, data pipeline, and frontend. For the database, I needed something fast for time-series workloads since the app ingests hourly weather readings across many cities and serves time-range queries on every slider interaction. I used Tiger Cloud by Tiger Data - Creators of TimescaleDB, which gives you managed TimescaleDB on the Postgres you already know. Claude Code connected to it through the Tiger CLI MCP server and set up the entire backend directly: - Provisioned the database service - Created hypertables for time-partitioned weather storage - Set up continuous aggregates for pre-computed rollups - Built the data ingestion pipeline and the full NextJS + ThreeJS frontend The time travel slider queries thousands of rows on every position change. On a regular Postgres table, this would require manual partitioning and index tuning to stay fast as data grows. TimescaleDB partitions the data by timestamp automatically, so each query only hits the relevant time chunk. Continuous aggregates serve the trend charts and forecast layer from pre-computed rollups instead of rescanning raw data on every request. The video below shows the final build in action, and I worked with the Tiger Data team to put this together. Tiger CLI is open-source (Apache 2.0) and works with Claude Code, Cursor, Codex, Gemini CLI, and VS Code. To try this yourself: → Sign up for Tiger Cloud (I have shared the link in the replies). It gives you $1,000 free credits (no card needed) → Install Tiger CLI: curl -fsSL https(:)//cli(.)tigerdata(.)com | sh → Run tiger mcp install claude-code → Give Claude Code a prompt and let it build Find the sign-up link in the replies.

Claude Code is now scary good at full-stack! I asked it to build a real-time weather intelligence dashboard with an interactive 3D globe and a forecasting layer that predicts weather 3 days ahead. It came back with a spinning globe that has a day/night cycle using NASA satellite imagery, city lights on the dark side, weather icons that switch between sun and moon based on local time, and a time travel slider that scrubs through 10 days of data. Claude Code built the whole thing in a single session, including the backend, database, data pipeline, and frontend. For the database, I needed something fast for time-series workloads since the app ingests hourly weather readings across many cities and serves time-range queries on every slider interaction. I used Tiger Cloud by Tiger Data - Creators of TimescaleDB, which gives you managed TimescaleDB on the Postgres you already know. Claude Code connected to it through the Tiger CLI MCP server and set up the entire backend directly: - Provisioned the database service - Created hypertables for time-partitioned weather storage - Set up continuous aggregates for pre-computed rollups - Built the data ingestion pipeline and the full NextJS + ThreeJS frontend The time travel slider queries thousands of rows on every position change. On a regular Postgres table, this would require manual partitioning and index tuning to stay fast as data grows. TimescaleDB partitions the data by timestamp automatically, so each query only hits the relevant time chunk. Continuous aggregates serve the trend charts and forecast layer from pre-computed rollups instead of rescanning raw data on every request. The video below shows the final build in action, and I worked with the Tiger Data team to put this together. Tiger CLI is open-source (Apache 2.0) and works with Claude Code, Cursor, Codex, Gemini CLI, and VS Code. To try this yourself: → Sign up for Tiger Cloud (I have shared the link in the replies). It gives you $1,000 free credits (no card needed) → Install Tiger CLI: curl -fsSL https(:)//cli(.)tigerdata(.)com | sh → Run tiger mcp install claude-code → Give Claude Code a prompt and let it build Find the sign-up link in the replies.

Avi Chawla

14,838 views • 4 months ago

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

Srishti

12,998 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$

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

Yarchi

56,177 views • 3 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

300,695 views • 5 months ago

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 860 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 860 stars. basically nobody is looking yet bookmark this before it gone

alex

14,212 views • 1 month ago

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

alex

158,896 views • 1 month ago

someone just rebuilt claude code in pure python and made it ~230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it ~230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

Argona

51,369 views • 2 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

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.

Ado

71,910 views • 7 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

68,057 views • 1 month ago

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,491 views • 7 months ago

Hermes keeps finding ways to make agent work cost fewer tokens. And the latest cuts are automatic. Recent changes reduced recurring context overhead across several parts of Hermes: • Desktop’s model-facing UI tool schema dropped 41% • Memory and Skills guidance went from 537 to 255 tokens • Desktop’s always-served guidance was trimmed again • roughly another 727 tokens were removed from recurring platform and steering instructions That matters whether you use Hermes for coding, research, content, automations, business workflows, or long-running agent tasks. Every token spent explaining tools, Skills, memory, or platform behavior is context that isn’t being spent on your actual work. Hermes was already notably lean here. Composio recently put that to the test using the same K3 model across competing agent harnesses. Hermes came out among the strongest on completion while also posting the lowest average cost per task in their comparison. And the Hermes team clearly isn’t treating that as good enough. They continue cutting token waste across tools, Skills, memory, platform instructions, compression, and other parts of the agentic process. The goal is simple: more of your context goes toward the work you actually asked Hermes to do. Clip via Tom

Hermes keeps finding ways to make agent work cost fewer tokens. And the latest cuts are automatic. Recent changes reduced recurring context overhead across several parts of Hermes: • Desktop’s model-facing UI tool schema dropped 41% • Memory and Skills guidance went from 537 to 255 tokens • Desktop’s always-served guidance was trimmed again • roughly another 727 tokens were removed from recurring platform and steering instructions That matters whether you use Hermes for coding, research, content, automations, business workflows, or long-running agent tasks. Every token spent explaining tools, Skills, memory, or platform behavior is context that isn’t being spent on your actual work. Hermes was already notably lean here. Composio recently put that to the test using the same K3 model across competing agent harnesses. Hermes came out among the strongest on completion while also posting the lowest average cost per task in their comparison. And the Hermes team clearly isn’t treating that as good enough. They continue cutting token waste across tools, Skills, memory, platform instructions, compression, and other parts of the agentic process. The goal is simple: more of your context goes toward the work you actually asked Hermes to do. Clip via Tom

Hermes Release Watch

19,845 views • 27 days ago

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. Alex Albert is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. Alex Albert is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

Hayrettin Tüzel

26,854 views • 5 months ago

Most discussions around Claude Code focus on model quality or capability. But when you actually use it, the friction shows up earlier, more at the system level than the model itself. Token limits get the blame, but a lot of it comes from inefficient sessions: repeated context, extra tool calls, and small loops that quietly stack up. So it starts to feel less like “is the model good enough?” and more like “is the workflow slowing it down?” That’s where WozCode comes in. It helps streamline sessions, less repetition, smarter batching of tool calls, and tighter context usage so you can actually get more work done within the same limits. Woz just launched on Product Hunt. If Claude Code felt a bit restrictive before, it’s worth trying again with a cleaner workflow setup. Same model. Smoother execution. Upvote here:

Most discussions around Claude Code focus on model quality or capability. But when you actually use it, the friction shows up earlier, more at the system level than the model itself. Token limits get the blame, but a lot of it comes from inefficient sessions: repeated context, extra tool calls, and small loops that quietly stack up. So it starts to feel less like “is the model good enough?” and more like “is the workflow slowing it down?” That’s where WozCode comes in. It helps streamline sessions, less repetition, smarter batching of tool calls, and tighter context usage so you can actually get more work done within the same limits. Woz just launched on Product Hunt. If Claude Code felt a bit restrictive before, it’s worth trying again with a cleaner workflow setup. Same model. Smoother execution. Upvote here:

Parul Gautam

15,079 views • 4 months ago

THIS GUY HAD OPUS 4.8 BUILD A FULL LEAGUE OF LEGENDS CLONE IN UNDER A DAY AND CALLED IT "LMAO" temu league of legends, fully playable, multiplayer, and all built by claude ALL the art is claude too he had claude generate every character, animation, and background as SVG code then converted them to procedural canvas for smooth animation. used dedicated sub-agents for each champion the tech stack: typescript, react, canvas, and partykit for multiplayer the workflow: > used /goal to kick off the entire project > ultracode workflows for big tasks like optimization > /goal again to queue up lists of bug fixes > treated claude like a dev team the original champion names claude came up with: the original champion names claude came up with: Teehee" instead of Teemo. "CtrlAltDefeat" as a champion name. he had to run through and clean them all up so nothing infringed on riot's IP claude even built the bots on its own with "chill," "normal," and "sweaty" difficulty levels the token bill was 2.7 billion total tokens consumed. mostly cache reads. 15.5 million actual output tokens. would have cost roughly $6,600 at list price but he just used his pro max subscriptions people are already benchmarking claude by how good of a game clone it can build game developers are watching someone build a multiplayer MOBA in a day with zero art skills and zero game dev experience 2026 is wild (and its going to get even wilder)

THIS GUY HAD OPUS 4.8 BUILD A FULL LEAGUE OF LEGENDS CLONE IN UNDER A DAY AND CALLED IT "LMAO" temu league of legends, fully playable, multiplayer, and all built by claude ALL the art is claude too he had claude generate every character, animation, and background as SVG code then converted them to procedural canvas for smooth animation. used dedicated sub-agents for each champion the tech stack: typescript, react, canvas, and partykit for multiplayer the workflow: > used /goal to kick off the entire project > ultracode workflows for big tasks like optimization > /goal again to queue up lists of bug fixes > treated claude like a dev team the original champion names claude came up with: the original champion names claude came up with: Teehee" instead of Teemo. "CtrlAltDefeat" as a champion name. he had to run through and clean them all up so nothing infringed on riot's IP claude even built the bots on its own with "chill," "normal," and "sweaty" difficulty levels the token bill was 2.7 billion total tokens consumed. mostly cache reads. 15.5 million actual output tokens. would have cost roughly $6,600 at list price but he just used his pro max subscriptions people are already benchmarking claude by how good of a game clone it can build game developers are watching someone build a multiplayer MOBA in a day with zero art skills and zero game dev experience 2026 is wild (and its going to get even wilder)

Om Patel

336,185 views • 3 months ago

I've been using Ring-2.6-1T on OpenRouter for my documentation pipeline this week. My usual flow: I dump a raw codebase or a long spec doc into the model and ask it to generate structured docs, flag inconsistencies, and draft a changelog. With other models, I was splitting this into 3 separate prompts because of context limits. Each split costs tokens. Each split loses some coherence between sections. With Ring-2.6-1T, I sent the whole thing in 1 prompt. 38,000 tokens. got back structured docs, a flagged inconsistencies list, and a changelog draft in a single response. Coherence was intact across all 3 outputs. No context bleed between sections. Still running it through more workflows, but the single-prompt full-doc processing alone has already cut my per-task token spend significantly. And then the cost showed $0.00, and I sat there for a second 👉 #BuildInPublic #OpenSource

I've been using Ring-2.6-1T on OpenRouter for my documentation pipeline this week. My usual flow: I dump a raw codebase or a long spec doc into the model and ask it to generate structured docs, flag inconsistencies, and draft a changelog. With other models, I was splitting this into 3 separate prompts because of context limits. Each split costs tokens. Each split loses some coherence between sections. With Ring-2.6-1T, I sent the whole thing in 1 prompt. 38,000 tokens. got back structured docs, a flagged inconsistencies list, and a changelog draft in a single response. Coherence was intact across all 3 outputs. No context bleed between sections. Still running it through more workflows, but the single-prompt full-doc processing alone has already cut my per-task token spend significantly. And then the cost showed $0.00, and I sat there for a second 👉 #BuildInPublic #OpenSource

Parul Gautam

48,658 views • 4 months ago

THE GUY WHO WON ANTHROPIC'S HACKATHON JUST GAVE AWAY HIS ENTIRE CLAUDE CODE PLAYBOOK FOR FREE. 10 MONTHS OF WORK, ALL PUBLIC Affaan Mustafa won the Anthropic x Forum Ventures hackathon by building a full startup in 8 hours with Claude Code. Then he open-sourced the exact setup that did it. It's called Everything Claude Code, and it turns Claude from one assistant into an entire engineering team Repo: affaan-m/ecc This isn't a prompt pack. It's a system he refined over 10+ months of daily use shipping real products What's inside: A huge library of skills, dozens of specialized subagents, and ready-made commands, all working together. Each piece does one job. One subagent reviews security against OWASP standards. One optimizes memory so Claude stops forgetting earlier decisions around hour three. One learns from your past sessions and projects so the setup gets smarter the more you use it. Others handle planning, test-driven development, and language-specific code review Instead of one assistant writing code, you get an orchestrated team. A main session delegates to the right specialist when the task calls for it, the way a real dev team splits work The best part: it's not locked to one tool. It runs in Claude Code, Cursor, Codex and OpenCode, across Windows, Mac and Linux. Free, MIT licensed This is the difference between using Claude like a search box and running it like a team that ships. The guy spent 10 months figuring out what actually works so you don't have to Bookmark this

THE GUY WHO WON ANTHROPIC'S HACKATHON JUST GAVE AWAY HIS ENTIRE CLAUDE CODE PLAYBOOK FOR FREE. 10 MONTHS OF WORK, ALL PUBLIC Affaan Mustafa won the Anthropic x Forum Ventures hackathon by building a full startup in 8 hours with Claude Code. Then he open-sourced the exact setup that did it. It's called Everything Claude Code, and it turns Claude from one assistant into an entire engineering team Repo: affaan-m/ecc This isn't a prompt pack. It's a system he refined over 10+ months of daily use shipping real products What's inside: A huge library of skills, dozens of specialized subagents, and ready-made commands, all working together. Each piece does one job. One subagent reviews security against OWASP standards. One optimizes memory so Claude stops forgetting earlier decisions around hour three. One learns from your past sessions and projects so the setup gets smarter the more you use it. Others handle planning, test-driven development, and language-specific code review Instead of one assistant writing code, you get an orchestrated team. A main session delegates to the right specialist when the task calls for it, the way a real dev team splits work The best part: it's not locked to one tool. It runs in Claude Code, Cursor, Codex and OpenCode, across Windows, Mac and Linux. Free, MIT licensed This is the difference between using Claude like a search box and running it like a team that ships. The guy spent 10 months figuring out what actually works so you don't have to Bookmark this

Yarchi

818,112 views • 3 months ago