Runesleo

I've always wanted to build an AI health management system for myself and my family, gradually filling it in with each checkup, doctor visit, and medication. These past few days while visiting my parents, I set up theirs too.
Inspired by @coolish's previous health management approach, I built this in a day using Claude Code + Obsidian:
📸 Photograph medicine boxes → AI automatically identifies drug names, dosages, frequency
📋 Photograph health reports (30+ pages) → AI reads each page, extracts abnormal markers, establishes trend comparisons
🗂 Organize by family member → Medical history, medi

166 Discord servers, cleaned down to 16.
A legacy of the airdrop era—ZK, Arb, OP, Starknet, NFT, nodes, GameFi, totaling 30,000 unread mentions. Opening Discord felt like walking into an abandoned mall every time.
Today I automated the entire cleanup in 2 minutes using Claude Code:
• Built a Discord Bot to gain server admin permissions
• Extracted the complete server list from the browser via Chrome CDP
• One Python script batch calling APIs—ran 120 servers at once, 0 failures
Also added a Telegram group-leaving script on the side: 54 groups + 89 channels can be cleared anytime.
I used to thin

As your Claude understands you more and more

Claude Opus 4.6 comes with 1M context, but you can't see by default how much you've used or how much is left. My previous clumsy workaround was to check the 😂 backend dashboard on the web.
Now I found that adding one line `statusLine` in settings.json displays real-time at the bottom: model version, context usage, git branch, session duration, and 7-day quota percentage.
Super useful when running multiple windows in parallel—one glance shows all statuses. Couldn't be more convenient!

You're an AI with an even worse temper than I do.

Claude Code's iteration speed is terrifying: every time you exit the terminal and come back, the version number goes up by 1.

You see a GitHub repository recommended by someone on X, click into it, think it's good, save it, and then most likely never open it again. Information originating from GitHub gets processed by KOLs, and by the time it reaches you, it's already secondhand.
Why not just get firsthand information yourself? Use GitHub Trending as an information source and integrate it into your daily digest workflow: cron scheduled scraping → AI filtering and evaluation based on your business direction → install and use what's worth trying → share what's worth sharing.
Every morning when you open your daily diges

I did something "useless but satisfying" with Claude Code——organizing my Chrome bookmarks.
262 bookmarks, 5 years of accumulation. Inside were defunct FTX, various old DeFi interaction projects, and airdrop tutorials. Claude directly read the local Bookmarks JSON, Python script recategorized and reorganized, created 10 folders, deleted 10 broken links.
Without writing code, let AI manage your local file system. Who says coding agents can only write code? 😁

Detected prompt injection attack from another species

Out of the first doubled Polymarket account.
Initial ~$190, cumulative PnL +$248, ROI 130%.
No overnight riches, just small dispersed positions, systematic execution, and gradual probability realization.
It proves that systematic execution of strategies validated by data can have positive EV.

X creator earnings just showed the first payout amount, $1,508.71, marking this milestone.
Started posting content in February 2023, and this is accumulated over three years. The first two years had basically no impressions, the past year was 16.7 M, with real growth in the most recent two to three months—the most recent pay period had around 3 million impressions, with estimated single-period earnings of $200-300.
Found something interesting after checking the backend: Article format has higher weight in the payout calculation. And looking at several creators, even very short content is being