Systems Computer Engineer. Building websites, online apps, e-commerce projects, since 1999.
Ibiza, Spain
Joined March 2026
- Tweets150
- Following366
- Followers134
- Likes57
JeanOnCode retweeted
just pick 2–3 of these Github repos to save millions of tokens in Claude
10 GitHub repos that cut your Claude Code token usage by 60–90%
This will help you when creating your own trading bots and tools for Polymarket, as well as for any other tasks
Here's the full list
1. RTK (Rust Token Killer)
CLI proxy that filters terminal output before it hits your context window. 60–90% reduction on common dev commands. One binary, zero dependencies. Works with Claude Code, Cursor, Copilot.
GitHub: github.com/rtk-ai/rtk
2. 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 dependencies.
GitHub: github.com/Mibayy/token-savi…
3. Context Mode
Sandboxes raw tool output into SQLite instead of dumping it straight into context. 98% context reduction on Playwright, GitHub, logs. Only clean summaries enter your conversation. Works as a Claude Code plugin.
GitHub: github.com/mksglu/context-mo…
4. 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.
GitHub: github.com/tirth8205/code-re…
5. Caveman Claude
Makes Claude respond like a caveman to cut output tokens. 65–75% output reduction. One-line install. Full technical accuracy stays intact.
GitHub: github.com/JuliusBrussee/cav…
6. token-optimizer-mcp
MCP server with caching, compression, and smart tool intelligence. 95%+ token reduction through intelligent caching. Compresses repeated tool outputs automatically.
GitHub: github.com/ooples/token-opti…
7. claude-token-efficient
One CLAUDE.md file that keeps responses terse. Drop-in, no code changes needed. Reduces output verbosity on heavy workflows. Best for output-heavy sessions.
GitHub: github.com/drona23/claude-to…
8. 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.
GitHub: github.com/zilliztech/claude…
9. 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.
GitHub: github.com/nadimtuhin/claude…
10. token-optimizer
Finds ghost tokens that silently eat your context. Survives compaction without losing quality. Fixes context quality decay over long sessions.
GitHub: github.com/alexgreensh/token…
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 already gone before you type a single word.
Like/RT/Bookmark if this was helpful
Follow me for more!
JeanOnCode retweeted
In the last 6 months at @Ahrefs, we analyzed over 1 billion data points across 14 studies. Here's what we learned about AI search optimization:
1) "Best X" blog listicles are the single most prominent content format cited by AI chatbots. They make up 43.8% of all page types cited by ChatGPT specifically.
2) 67% of ChatGPT's top 1,000 citations come from sources marketers can't influence: Wikipedia (29.7%), homepages (23.8%), app stores (6.6%). Only 32.3% are influenceable content like educational pages, reviews, news, and blog posts.
3) 28.3% of ChatGPT's most-cited pages have zero Google organic visibility. These pages get cited repeatedly by ChatGPT despite not ranking in Google at all. A completely separate discovery layer.
4) ChatGPT only cites about 50% of the URLs it retrieves. It fetches dozens of pages per query but uses half as background context without attribution. This means that being retrieved and being cited are very different things.
5) Adding schema markup had zero meaningful impact on AI citations. AI Overviews actually dipped −4.6%, while AI Mode (+2.4%) and ChatGPT (+2.2%) showed changes indistinguishable from zero.
6) YouTube mentions have the highest correlation (0.737) with AI brand visibility out of all the factors we studied (including all the conventional SEO metrics like backlinks, page count, DR, etc). This held true for both Google-owned and OpenAI products.
7) AI Overviews reduce clicks to the #1 result by 58%. That’s up from 34.5% just 10 months earlier. The trend is accelerating.
8) 99.9% of AI Overviews appear on informational intent queries. Transactional, navigational, and local searches are almost entirely AIO-free. Shopping triggers AIOs just 3.2% of the time.
9) For a given search query, Google’s AI Mode and AI Overviews reach the same conclusions 86% of the time — but cite almost entirely different sources (only 13.7% citation overlap).
10) AI Overviews change every 2.15 days on average, with 70% of content differing between consecutive observations. But semantic similarity stays at 0.95. The words, sources, and entities constantly shuffle, but the actual meaning barely moves.
JeanOnCode retweeted
Today, we’re open-sourcing the draft specification for DESIGN.md, so it can be used across any tool or platform. We’re also adding new capabilities.
DESIGN.md lets you easily export and import your design rules from project to project. Instead of guessing intent, agents know exactly what a color is for and can even validate their choices against WCAG accessibility rules.
Watch David East break down this shared visual language in action👇. New capabilities and links in 🧵
JeanOnCode retweeted
This skill makes Claude write impeccable code.
It enforces best practices, clean structure, and production-level standards automatically.
No more messy outputs. Just code you’d actually ship.
github.com/pbakaus/impeccabl…
JeanOnCode retweeted
can ai agents invent writing on their own? recent pet project: 2 agents share a world but each sees only half. their only communication: 7×7 pixel glyphs. they develop symbols, build theories of meaning, and evaluate their own writing. no convergence yet but fascinating to watch!
JeanOnCode retweeted
The Tech Career Evolution Nobody Talks About:
> 2022 - Student
> 2023 - Developer
> 2024 - Prompt Engineer
> 2025 - Vibe coder
> 2026 - AI agent
> 2027 - Farmer 🌱
JeanOnCode retweeted
There are over 3.5k job openings at Europe's leading startups.
Tech is the fastest growing segment of the European economy, and it is quickly overtaking finance and law as the most in-demand grad jobs.
There's never been a better time to get into tech with some amazing jobs at some of the fastest growing startups across europe:
> @attio
> @synthesiaIO
> @fuseenergy
> @peec_ai
Jan-Willem Denys has built StartupMap - a new platform tracking the continent's open roles and there are some great roles out there.
It's a great resource - will drop the link below
JeanOnCode retweeted
Gemini vs Claude
Claude has started to get really damn good at design.
Prompt below ↓
JeanOnCode retweeted
Claude Code can control your computer now!
