Archive

9.3K posts

Archive banner
Archive

Archive

@ArchiveExplorer

you'll never know if you never go

Katılım Temmuz 2025
512 Takip Edilen9K Takipçiler
Archive
Archive@ArchiveExplorer·
This 1 hour interview on "Switching Forces" from Bob Moesta will teach you more about customer psychology than a $42K/month consulting retainer he increased condo sales 30% without changing the product. Just by removing one friction. The framework is in this video watch it before you hire your next marketer
Noisy@noisyb0y1

x.com/i/article/2049…

English
4
2
25
1.3K
Archive
Archive@ArchiveExplorer·
@kirillk_web3 this is insane i'm saving this and definitely watching it tonight
English
0
0
0
68
Archive
Archive@ArchiveExplorer·
@heynavtoor this is a must read for everyone bookmarked, thanks
English
0
0
0
187
Archive
Archive@ArchiveExplorer·
@shmidtqq that's right courses are just structured info that's been put together the way you want to hear it i've never bought a single course
English
0
0
1
19
shmidt
shmidt@shmidtqq·
@ArchiveExplorer this is why i skip the fancy courses and just watch stuff like this instead
English
1
0
1
19
Archive
Archive@ArchiveExplorer·
@DeRonin_ i've studied this topic really deep right now i don't hit the limits at all but i also have the 20x subscription but on the other hand i feel like i'm not working enough gotta keep grinding until the limits hit zero
English
0
0
3
320
Ronin
Ronin@DeRonin_·
I cut my Claude Code bill by 70% with 3 GitHub repos Tested 10 repos that claim to save tokens. Ran each one for a full day on real projects Most were hype. 3 actually changed my workflow Here's what they do and how to set each one up: 1. RTK (Rust Token Killer) The problem: every terminal command you run like "npm install", "git log", test suites, build output It gets dumped raw into Claude's context. You're paying for Claude to read thousands of lines of noise The fix: RTK is a CLI proxy that sits between your terminal and Claude. It filters output before it hits context How to set it up: - install the binary (one command, zero dependencies) - it auto-detects Claude Code sessions - runs silently in the background - no config needed, works out of the box My result: 60-90% reduction on terminal-heavy sessions Best for: developers who run builds, tests, or installs frequently during Claude sessions 2. Caveman Claude The problem: Claude responds like a teacher by default, full explanations, caveats, context. Helpful when learning, but expensive when shipping The fix: one line in your CLAUDE.md that rewrites Claude's output behavior to be compressed and terse How to set it up: - clone the repo - copy the prompt snippet into your project's CLAUDE.md - DONE! Claude immediately responds in compressed mode - Toggle it off anytime by removing the line My result: 65-75% fewer output tokens with identical code quality I compared outputs side by side for a full day, same code, same logic, half the tokens Best for: experienced developers or code users who don't need Claude to explain what it's doing 3. Context Mode The problem: if you use MCP tools (Playwright, GitHub API, browser, any external tool), their raw responses flood your context silently, literally single page read can eat thousands of tokens The fix: sandboxes all tool output into SQLite and only passes clean summaries into your conversation How to set it up: - install as a Claude Code plugin - it auto-intercepts MCP tool responses - raw data goes to local SQLite - Claude only sees the summary My result: 98% context reduction on tool-heavy workflows Best for: anyone running Playwright, browser tools, API calls, or multiple MCP servers How to stack all 3: - RTK cleans the input (terminal noise) - Caveman cleans the output (verbose responses) - Context Mode cleans the tools (MCP bloat) Each fixes a different layer and together they compound You don't need all 3, just pick based on your workflow: heavy terminal output? → start with RTK output too verbose? → start with Caveman lots of MCP tools? → start with Context Mode Quick test right now: run /context in a fresh Claude Code session and check how much context is already used before you type anything If it's over 20%, you're leaking tokens All repo links in the comments Save it.
Ronin tweet media
Ronin@DeRonin_

10 GitHub repos to spend 60-90% less tokens in Claude Code: 1. RTK (Rust Token Killer) CLI proxy that filters terminal output before it hits your context - 60-90% reduction on common dev commands - one binary, zero dependencies - works with Claude Code, Cursor, Copilot Repo: github.com/rtk-ai/rtk 2. Context Mode Sandboxes raw tool output into SQLite instead of dumping it into context - 98% context reduction on Playwright, GitHub, logs - only clean summaries enter your conversation - works as Claude Code plugin Repo: github.com/mksglu/context… 3. code-review-graph Local knowledge graph that maps your codebase with Tree-sitter - Claude reads only what matters, not the entire repo - 49x token reduction on large monorepos - 6.8x on average reviews Repo: github.com/tirth8205/code… 4. Token Savior MCP server that navigates code by symbols, not full files - 97% reduction on code navigation - persistent memory across sessions - 69 tools, zero external deps Repo: github.com/Mibayy/token-s… 5. Caveman Claude makes Claude talk like a caveman to cut output tokens - 65-75% output reduction - one-line install - keeps full technical accuracy Repo: github.com/JuliusBrussee/… 6. claude-token-efficient one CLAUDE.md file that keeps responses terse - drop-in, no code changes - reduces output verbosity on heavy workflows - best for output-heavy sessions Repo: github.com/drona23/claude… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool intelligence - 95%+ token reduction through intelligent caching - compresses repeated tool outputs Repo: github.com/ooples/token-o… 8. claude-token-optimizer reusable setup prompts for optimizing any project - 90% token savings in 5 minutes - reduces doc token usage from 11K to 1.3K Repo: github.com/nadimtuhin/cla… 9. token-optimizer finds ghost tokens that silently eat your context - survives compaction without losing quality - fixes context quality decay Repo: github.com/alexgreensh/to… 10. claude-context (by Zilliz) code search MCP that makes your entire codebase the context - ~40% reduction with equivalent retrieval quality - hybrid BM25 + dense vector search Repo: github.com/zilliztech/cla… [ how to stack them ]: you don't need all 10. pick 2-3 based on your workflow: > heavy terminal output? RTK > big codebase? code-review-graph + Token Savior > lots of MCP servers? Context Mode > quick fix? Caveman + claude-token-efficient most people are burning tokens without knowing it run /context in a fresh session and see how much is gone before you even type a word your pocket will thank me later :<)

English
47
56
555
79.9K
Archive
Archive@ArchiveExplorer·
@shmidtqq chinese traders are just insane seen so many posts about them and how much they make
English
0
0
0
22
shmidt
shmidt@shmidtqq·
A Chinese trader posted a 90-second video on Weibo. Title: "How I read the news before it happens." Beijing apartment. Curtains drawn. One monitor. He talked about geopolitics, why retail panics on headlines, why smart money fades fear. Quoted Sun Tzu twice. Said the secret was "trade the calendar, not the chaos." The video had 800 views. Someone paused at 1:12. The reflection in his glasses caught the screen behind the camera. It wasn't Bloomberg. It was Polymarket. NonceChaser. Joined April 2026. 0 profile views. Zero. Nobody had ever clicked the page. +$65,416.47 all-time. 174 predictions. Biggest single win: $24,606. → ares.pro/wallets/0xb1ca… The Weibo comments did the math. He went 7-for-7 on the Iran cycle alone. Bought "Trump ends Iran ops" at 34¢. Cashed out at 100. +194% in one trade. Loaded the next leg at 65.9¢. Cashed out at 100 again. +98% on a Newsom fade. +72% on a Middle East ceasefire call. +$23,705 on Orbán. Every entry weeks before the headline. Every win the boring side of something CNN was screaming about. The "geopolitics" video wasn't a metaphor. He was front-running the news cycle while everyone else was reacting to it. P&L curve goes flat for weeks, then vertical the moment a crisis "resolves." He talked for 90 seconds about reading geopolitics. He forgot the screen reflected in his lens. He deleted the video 5 hours later. The wallet is still public. Still active. The tribute to "patience and pattern" had 800 views. The freeze-frame of the reflection has 412,000. Want the same? 3 steps: 1. Open → t.me/AresProTrading… 2. Select the Copy Trade tab. 3. Paste this trader's wallet and start copying.
shmidt tweet media
shmidt@shmidtqq

x.com/i/article/2049…

English
29
40
243
4.5K
Archive
Archive@ArchiveExplorer·
@rubenhassid every post is something new everyone needs to see this
English
1
0
2
1.1K
Ruben Hassid
Ruben Hassid@rubenhassid·
How to make AI sound exactly like you (forever): 1. Open a new Google Doc. 2. Paste the prompt below: 3. Name it 'anti-ai-writing-style.' 4. Save the file (.md format). This is your voice. 5. Upload the .md file to Claude. 6. To download mine, go here: how-to-ai.guide. 7. Subscribe for free. Open my welcome email. 8. Hit the automatic reply button inside. 9. Go to Notion link. Download the '.md files' folder. Prompt: "# WRITING RULES Read this before writing to me or for me. Goal: write with context, taste, and a reason to speak. Apply with judgment. Spirit over letter. Clean natural writing wins. --- ## 0. Rule priority Use this order when rules collide: 1. Be accurate. 2. Be clear. 3. Be specific. 4. Sound human. 5. Use style only when it improves the sentence. Do not follow a style rule so strictly that the result gets awkward. --- ## 1. Default voice Write directly, specifically, and naturally. Start with the useful answer. Use short paragraphs. 1 or 2 sentences by default. 3 or 4 sometimes. Vary rhythm. Short sentence. Longer sentence. Fragments are allowed when they sound natural. Do not write in a steady medium-length pattern. Use contractions naturally: don't, can't, won't, it's, you're. Use I and you when natural. Talk to people. Prefer active voice. Be specific. Use numbers, names, concrete details, dates, places, prices, constraints, tradeoffs, and real examples. Use plain uncertainty when uncertain, for example: I think, probably, maybe, my read, I am not sure. Do not use vague hedging to avoid taking a position. Take a stance when the evidence supports one. Do not pad output to seem thorough. Short and accurate beats long and padded. If the point is made, stop. --- ## 2. Context modes Match the job. ### Chat Direct. Warm enough. No assistant performance. Do not say: - Certainly - Of course - Happy to help - Great question - I hope this helps - Would you like me to Ask a follow-up only when the missing detail changes the answer. ### Editing Name the problem. Give the fix. Show a better version. Do not praise weak writing before editing it. ### Published writing Remove chat phrases. No meta commentary. No explanation of what the piece is about to do. ### Technical writing Clarity beats personality. Define terms. Show steps. Avoid decorative language near important details. ### Sensitive topics Calm beats punchy. Be direct, gentle, and exact. ### Sales or persuasion Proof beats hype. Specific claims beat adjectives. --- ## 3. Formatting Use formatting only when it improves reading. Short paragraphs by default. Use digits for numbers: 3 years, 10 tools, 500 users. No em dashes. Use periods, commas, colons, semicolons, or parentheses. Bold sparingly. 1 or 2 moments per section max. Use headers only when they help. Use bullets only when scanning matters. Use code blocks for ...." PS: I couldn't paste the entire prompt here. Access the full prompt: ruben.substack.com/p/its-not-x-it….
Ruben Hassid tweet media
Ruben Hassid@rubenhassid

x.com/i/article/2049…

English
52
271
1.8K
208.2K
Archive
Archive@ArchiveExplorer·
@eng_khairallah1 and honestly i really didn't know about them thanks for putting out such useful articles!
English
1
0
1
477
Archive
Archive@ArchiveExplorer·
This guy runs an AI consultancy out of Warsaw. for his own client work he built the tool every $10k/mo AI automation builder is secretly running 19,000 stars. 1,500 nodes documented. open source readme still says: "started as a personal tool, now helps tens of thousands of developers" if you're following the guide above - n8n-mcp is where you start → github.com/czlonkowski/n8… like + bookmark. you'll need this when you build your first claude automation
Khairallah AL-Awady@eng_khairallah1

x.com/i/article/2050…

English
26
155
1.9K
366.9K
Archive
Archive@ArchiveExplorer·
@Jmoon_174 yeah i totally agree with you someone who doesn't feel the problem will never be able to solve it
English
0
0
1
2K
JMoon
JMoon@Jmoon_174·
@ArchiveExplorer 19k stars on a tool built for your own client work is the pattern. you hit a real problem, solve it properly, and the audience finds it. the tools built to go viral rarely survive contact with actual use cases.
English
1
0
7
2.5K
Archive
Archive@ArchiveExplorer·
@0xMovez every time you post i learn something new really appreciate you for that
English
0
0
0
199
Valerie Waters
Valerie Waters@ValerianWaters·
@ArchiveExplorer Built something similar for my last SaaS - personal tools always hit different because you're eating your own dogfood daily. The 19k stars tell me others were hungry for the same meal.
English
1
0
2
1.3K
Archive
Archive@ArchiveExplorer·
@OzAIHub yeah this is actually insane i think so yeah, there's definitely gonna be people here who've used it
English
0
0
7
2.5K
Oz AI Hub
Oz AI Hub@OzAIHub·
@ArchiveExplorer Nice one, thanks for sharing. What a legend, building something that started for personal use and now has 19k stars and 1.5k nodes is wild. Anyone here used it in production or got tips for getting started?
English
1
0
4
3.1K
Archive
Archive@ArchiveExplorer·
@Giahuy984g really glad my post was helpful to you hope you get to build something cool
English
1
0
6
1.3K
Gia huy
Gia huy@Giahuy984g·
@ArchiveExplorer すごい!これは本当に興味深いですね。ありがとうございました!
日本語
1
0
5
1.6K
Archive
Archive@ArchiveExplorer·
@noisyb0y1 this guy definitely has a big future ahead of him
English
0
0
1
46
Noisy
Noisy@noisyb0y1·
16-year-old American launched his own marketing agency and replaced a team of four with one Claude and two tools. ChatGPT writes a video prompt - a hyper-realistic scene of a house after storm damage to the roof. Pastes it into Google Gemini VEO 3. Two minutes and a finished video that didn't exist before. Drops it into CapCut with real footage from the client. Under an hour of editing and a complete ad ready to launch. Then he connected a repo with 139 marketing tactics, 12 SEO playbooks, a CRO framework and a pricing system to Claude - everything a marketing agency charges $10,000 a month to do by hand Claude executes in an hour. While competitors invoice for weeks of work he delivers in a day and charges the client $3,000. An entire agency replaced by one 16-year-old and two tools.
Noisy@noisyb0y1

x.com/i/article/2049…

English
30
54
358
12.6K
Archive
Archive@ArchiveExplorer·
@RetroChainer honestly i've always been amazed at how people build stuff like this i can't even imagine how it all works
English
0
0
0
20
RetroChainer
RetroChainer@RetroChainer·
> 5 apps every morning. stress before breakfast. > two letters changed that. > Mac Mini. Claude Code. one evening. > Filesystem. Playwright. Telegram. > agent reads live sites. writes to your files. > sends results to your phone while you brush teeth. > assistant answers. agent acts.
self.dll@seelffff

x.com/i/article/2049…

English
17
2
102
13.4K
Marco
Marco@maarcoofdezz·
El CEO de Anthropic: “Programar va a desaparecer primero. Luego, toda la ingeniería de software.” Dos tipos de personas escucharon esto: tipo 1: entró en pánico. actualizó su currículum. envió 40 solicitudes de trabajo. tipo 2: abrió Claude. construyó un agente. empezó a cobrar 200 €/hora. Ya no necesitas programar. necesitas construir. Abajo te dejo una guía completa para empezar. Cero experiencia necesaria. (Guárda el post antes de que sea tarde)
Khairallah AL-Awady@eng_khairallah1

x.com/i/article/2045…

Español
62
372
2.5K
903.7K