cheapskate's 3 rules that stop an agent PAYING for its own output: Copy these into your CLAUDE.md or AGENTS.md: -> Tail, don't cat. Never dump more than 100 lines of command output. -> Edit, don't rewrite the file. -> Run the one test, not the whole suite. Why: every turn re-sends the whole conversation, so every line the agent prints is paid for again on each later turn. In my A/B test on one 60-file repo, these rules and the rest of the set cut the cost 13% ($0.43 to $0.37). One task, so test it on yours. github.com/codegobrrrr9/chea…

Your brief got f**king worse the moment it left your head. so switch from rereading your own brief to a contractor read before it goes out... it catches what rereading never will, for the cost of one extra prompt [here is how to set it up in any agent workflow in one prompt] 1. second prompt → paste the brief → read it as a contractor who has never seen the repo 2. list every question they'd have to ask → mark anything nobody can answer as MISSING 3. ready to go Full breakdown below.

I've started looking into other hardware wallet options. One that caught my attention is @Tangem with their seedless model. But after digging deeper, I have a few concerns. The seedless concept is interesting. No seed phrase, you can use NFC cards to store your private keys and sign transactions through your phone. You can have up to 3 cards holding the same keys, so losing your phone or one card doesn't mean losing access to your funds. My concerns: 1. What if Tangem shuts down? Tangem uses its own wallet app to interact with the cards. The app is open-source, and Tangem says transactions don't depend on its servers. So technically, the cards should continue working even if the company disappears. But what happens 10 years from now if the app is no longer maintained or compatible with newer phones? Unlike a traditional seed phrase, you can't simply import your seedless Tangem wallet into another hardware wallet. You're relying on the cards and compatible software to remain usable. 2. What if I lose all my cards? With a traditional hardware wallet, losing the device isn't a disaster as long as you have your recovery phrase. With seedless Tangem, losing all your cards means permanently losing access to your funds. You also can't export the private key as a backup. Of course, losing your seed phrase and every other copy of your keys would create the same problem with traditional wallets. But the recovery models are fundamentally different. 3. What if I lose my phone and forget my access code? Tangem uses Face ID for convenience, but it's not actually tied to your wallet's ownership. If you lose your phone, you can install the Tangem app on a new one, scan your card, and enter your original Tangem access code. But what if you forget that code too? Apparently, Tangem lets you reset it using two cards from the same wallet, as long as access-code recovery hasn't been disabled. So losing your phone and forgetting your code isn't necessarily a disaster. But this introduces another trade-off. If someone manages to steal two of your cards, they could potentially reset the access code and access your funds without knowing your original password. Tangem does offer an optional seed phrase setup, which solves much of the portability concern, but also brings back the risks of managing a seed phrase. Still exploring alternatives to Ledger and Trezor for long-term cold storage. Curious if anyone here has been using Tangem or has other recommendations.

Just hit 8B tokens on Claude Code. Are these rookie numbers or is Dune the rookie??

Peak gaming is back ladies and gentlemen. If im inactive, it is because of Halo 3.

You can't make money with just any AI agent. Not because the model is expensive. the example agent in this one costs about $0.75 a run on Sonnet 5.5. They fail because they're built first and sold second. an agent doesn't earn. a job does. the agent is how you do that job in less time than the client pays for. So I wrote the setup in the other order: find work people already pay a human for, make the deliverable by hand, get paid, then build. 10 steps, a worked example (weekly competitor reports for small online shops), the full agent loop in about forty lines, and the cost per client.

Ethena turned off its token subsidies before the buyback engine even started. A pretty bold bet on $USDe growth. So how does @ethena expect to keep growing without paying users more $ENA? I think the answer comes down to two things: yield and distribution. For context, USDe is currently sitting around $4.9B. And $ENA incentives tied to USDe supply growth ended in Sep, while the first buyback threshold only kicks in once USDe reaches a $7.5B supply. 1. Yield: Equity-perp basis trade Ethena is expanding its basis trade beyond crypto into tokenized equities. The strategy is relatively straightforward: Long tokenized stock + short the corresponding equity perp = collect funding while hedging most of the directional exposure. And the opportunity is potentially meaningful. Ethena's Risk Committee found that approved Binance equity-perp names were averaging around 7% annualized funding, while approved OKX names ranged from 8-16% at the time of the study. Of course, these aren't guaranteed yields. Funding constantly changes, can turn negative, and the hedge still carries execution, basis and counterparty risks. But it gives Ethena another market to generate yield beyond BTC/ETH funding. The equity-perp market already had roughly $2.9B in one-sided open interest across the venues studied. That's a potentially important expansion of USDe's yield opportunities. 2. Distribution: Ethena Pay The second bet is that people increasingly hold USDe because it's useful, not because they're being paid token incentives. USDe is already integrated across 100+ venues and protocols. Now Ethena Pay is trying to take it beyond crypto-native users and into everyday payments, savings and spending. The interesting part is that Ethena is moving beyond relying entirely on third-party platforms to distribute USDe. With Ethena Pay, it's building a direct consumer distribution channel. Of course, launching a payment product doesn't automatically translate into meaningful USDe adoption. But if it works, that's another source of demand that doesn't depend on continuously distributing $ENA. And this is where the tokenomics become interesting. The old growth model relied heavily on: $ENA incentives ↓ USDe growth ↓ More incentives to sustain demand The new model Ethena is betting on looks more like: Attractive yield + broader distribution ↓ Organic USDe demand ↓ More USDe supply ↓ Potentially larger revenue base ↓ $7.5B supply threshold ↓ Revenue-funded $ENA buybacks The buyback allocation starts at 5% of protocol revenue at $7.5B USDe supply and scales up at higher milestones. So USDe growth alone isn't enough. The protocol also needs to generate sustainable revenue from that supply. That's why I think USDe supply, alongside protocol revenue, might be the most important thing for $ENA holders to watch right now. Ethena is effectively testing whether it can grow without relying on token emissions as its main incentive. And with USDe around $4.9B, there's still a meaningful gap before the first buyback threshold. If supply keeps growing now that the incentives have ended, that's a much stronger signal of genuine demand than growth driven by continuously paying users more $ENA. Whether that demand can eventually translate into meaningful value accrual for holders is the next question. That's the experiment I'm watching.

Ouch. $75k is worst case scenario tho. I think $BTC can bounce back from $80k and if not brace for impact!

You are one paying client away from proving an AI agent can earn, and the code that serves that client is about forty lines of Python. Ready to copy and paste below.

AutomationBench rose from 26.9% on Opus 5 to 40.0% on Opus 5.5! GPT-6 Astra scores 41.4%, so this is not a clean win. multi-app work still fails the same way. across email, documents, spreadsheets and a CRM, the model acts before it looks around. Anthropic's guide has a fix that needs no new model: one sentence in the prompt telling it to explore the relevant sources before it acts. Anthropic says that made it complete noticeably more multi-app tasks correctly. and the sentence cuts both ways. a model told to act on what it finds will act on an injected instruction too, so it only goes at sources you trust. Which of your sources would you not point it at?

If you were in crypto during the FTX collapse, this trailer probably hits a little differently SBF was once one of the biggest names in the industry Now his story with Caroline Ellison, the rise and fall of FTX, and the $8 billion fraud is getting the Netflix treatment Crypto history is one wild ride Now we’re getting the Netflix version Crypto OGs, you watching this?

Explaining the brand again got f**king old. so switch from a fresh chat for every task to one project per client... it keeps the colours, the type and the tone in view on every task, no re-pasting [here is how to set it up in minutes] 1. claude.ai → Projects → Create project 2. add files to project knowledge → brief, brand guide, approved past work Ready to go. Full breakdown in the article below.

I edited one utility file in hono. src/utils/filepath.ts. shortlist, 756ms later: RUN 7 of 137 test files (95% skipped) And a reason on every line. src/hono.test.ts ← imports src/utils/filepath.ts. Same for the logger middleware, the presets, the color util, the dev helper, and the file's own test. Then the exact command: npx vitest run with those seven paths. What it follows: imports, re-exports, require, dynamic import(), vi.mock and jest.mock, tsconfig path aliases, workspace package names, Python imports and conftest.py scope. What makes it give up and run everything: anything it can't trace. A lockfile, a Node version file, a .go file, the workflow that runs the tests. A tool that picks tests has one job before speed: say why. Every line has a because. github.com/codegobrrrr9/shor…

Opus on every client task got f**king expensive. So switch from Opus for everything to Sonnet 5.5 on your production seats... It lands near the same quality for $0.96 instead of $4.79 and finishes in 10.8 minutes instead of 22.7 [here is how to set it up in claude code, once] 1. .claude → agents → copywriter.md, designer.md, developer.md 2. add model: sonnet, set effort to medium 3. ready to go

I A/B tested my own token-saving skill on a real 60-file repo. It cut cost 13%. Here is the test, so you can run it on any skill you install: 1. A fresh copy of a real repo for every run. No leftover context. 2. Same task, same prompt, word for word. Mine: add a scanner check, plant an example, extend the test, make npm test pass. 3. Baseline with no instructions, then the skill installed. Nothing else changes. 4. A run only counts if the tests pass afterwards. 5. Score from the agent's own usage report: context, output, cost, turns. My result, one run each on Sonnet 5: Baseline: 789K context, 10K output, $0.43, 17 turns. With the skill: 702K context (-11%), 7K output (-26%), $0.37, 15 turns. Protocol and raw rows are in the repo. github.com/codegobrrrr9/chea…

The moment I sold solana:8nPoBHiBM6pybxMws9PA2JRb9BjkppBfqcZGmot4DMBC it went to 4M Mcap. Happy with my profits either way. The trenches are back.

One weekend of setup... this is the best freelance agency setup on X. 1 operating file, 5 seats, 10 steps, all built on Anthropic's own docs write it once, run every client job through it.

Twenty jobs split across two models, each one with its own effort setting attached. One afternoon. zero guesswork. no model switched without setting effort first. use the guide below and never hit your usage limit again:

AI crypto sector: $15B market cap. $NEAR: +183% in September. $RENDER: +27% in a week. $FET: +51% in a month. The sector is waking up while the crowd sleeps.

I asked Opus 5.5 to create an explainer video for my usage monitor I built. Karpathy gave the best advice so I used it. It is called Monere and free to use on github. I tend to use mulitple LLMs at a time and this was the best way to track usage across each of them. The repo is in the replies