Brad Mills 🔑⚡️

Bitcoin cycles are dead. The days of parabolic bitcoin booms & devastating crashes are done. Bitcoin is inevitable & we are at the beginning of the SaylorCycle ... are you positioned for the next 100X in Bitcoin? The chasm is crossed. tradingview.com/chart/BTCUSD/T…

2. self-healing docs for every system, and agents are instructed to keep them updated ... I tag the ones I know I need, or let the agent find them through AGENTS.md ... I also provide a more detailed summary in the first 7 lines of every doc, so they're easily greppable to find the right thing, and this is documented in AGENTS.md could I get more example on how you do this?

I'm just going to dump my whole agentic setup out here, because I see too many people missing giant chunks of this and it's hurting them. Here's what I have and recommend: 0. an AGENTS.md that is a router -- it sends the agent to the right skills, docs, tools 1. a standard workflow doc/skill customized to my needs ... (grab Matt Pocock skills if you don't already have something) ... I tag this in most sessions with `@/AGENT_WORKFLOW.md` and it pulls it in. 2. self-healing docs for every system, and agents are instructed to keep them updated ... I tag the ones I know I need, or let the agent find them through AGENTS.md ... I also provide a more detailed summary in the first 7 lines of every doc, so they're easily greppable to find the right thing, and this is documented in AGENTS.md 3. agents always run the app ... the agent should always actually run the app itself, and test its work and fix issues as it goes, especially if running autonomously / asynchronously 4. end-to-end tests and instructions to write more and keep up to date, and docs on how to write tests, what to avoid, and a list of all the tests and what they test in yet another markdown doc ... write and run targeted tests during implementation, improve and commit with work 5. custom linters at precommit hooks looking for any problems you run across, with `--fix` fixing the problems automatically, OR if that's not feasible, it shells out to a cheaper LLM like Composer 2.5 or Sonnet to fix the problems -- NOT just flagging them, but actually resulting in cleaned code 6. cross-agent review at each major point: research, plan, implementation, and wrap-up. I mean codex, claude, cursor, whatever -- but it shouldn't be the same model reviewing the same code. And specific docs for agent review, what to look for, how to approach it. Also, personas -- looking at the code from different perspectives, such as maintainability, code quality, security, performance, AI smells, domains (e.g. "financial services expert" or whatever) ... and each persona also "owns" a set of system docs too and keeps them up to date 7. agent traces / worksheets that track what the agent is doing each session. if the agent fails partway through, you should be able to hand this worksheet to another agent and it could finish the job. commit this worksheet with the work so it's all connected and easy to reference later (you will reference these later!!), also have the agent apply git tags that correspond to specific worksheet names so they're easy to find 8. automatic agent feedback to you at the end of the session, added to a doc that is also committed with the work, that you periodically ingest into an interactive session and improve your workflows 9. a tools or bin folder that contains python or bash scripts that the agent has skills to make to make its job easier (for example, I have an `agent_review` bash script that lets the agent kick off agent reviews via CLI without knowing each agent's particular incantations) ... docs on how to make scripts effectively, and instructions to constantly build these out more 10. periodic agent sweeps through recent commits, looking for problems / gotchas from a higher level across commits 11. a coding conventions doc that is just for specific coding conventions you want to see in the code base, your review agents use these a lot (but a lot of this should be in linters) 12. an agent loop / night shift skill for autonomous work, that lays out how the agent is to approach this, from an orchestration standpoint 13. a task queue that is accessible to the agent (mine is just a TODOS.md, but yours might be in Linear etc, with a CLI to fetch via API) 14. a periodic false-confidence test audit skill that looks for tests that aren't actually testing what you think they're testing, and that fix those 15. visual regression tests -- take screenshots, compare via tool and with agent visual review, commit with work (git lfs useful here) or at least push into the PR 16. automatic performance benchmark tests that notice when performance degrades 17. performance profiling tools that can be used by agents for targeted benchmarking, trying new techniques, comparing outputs, and comparing profiles 18. end-of-shift full validations, including running all tests, performance, agent reviews, sweeps, everything -- when you return, it's all as pristine as it can be If you have all this, your agentic coding experience is going to be very different than dry prompting and manually guiding it toward the right thing every time.

@udiWertheimer @rot13maxi 💯

there won’t be fireworks on the day bip110 loses there will be no heroic battles, no celebrations. no price chart to watch going to zero no victory speeches, no body bags simply nothing. it will be an ordinary day like any other and nobody will notice that anything happened

@rot13maxi What is it? Is it something that you run or someone you know?

Higher

@Rob1Ham @rot13maxi @AnchorWatch @CoinCorner @BitGo 👏

Today, @AnchorWatch is launching Multi-Institution Custody. Built on our Trident Vault infrastructure, it lets individuals and companies secure bitcoin without managing keys themselves. We’ve partnered with @CoinCorner and @BitGo as institutional custody providers. Our YubiKey integration adds phishing-resistant authentication and stronger protection against deepfake-enabled social engineering. Available with optional 1:1 insurance coverage through Lloyd’s of London, bringing institutional-grade custody and comprehensive bitcoin protection together in one product.

@rot13maxi You try my game yet? You still doing yours?

@bradmillscan Ah nvm then

lolol wow ChatGPT 5.6 Sol SUX so bad. I did a 1 hour and 30 minute gstack CEO Review question & answer session for my AIAIO game, and after it was done it didn't bother to save any durable artifact. Been having a lot of problems with it, it's almost as bad as GPT 5.4 was.

@TokenFires Hey awesome I’m glad you played it. You got any suggestions for me?

If you haven’t tried this, it’s pretty fun! Use a long session with multiple compactions and it’s a hilarious bit of nostalgia making when you’re working with AI. “Oh yeah! *THAT SESSION!” 😂

No engine. No Three.js. No dependencies. 130KB of Canvas 2D, WebAudio synthesis, and the browser's own TTS all using your own agent sessions for levels. It's really fun. Actually makes me laugh and smile. Would love to see get feedback!

Major update of Agents in Amnesia! AIAIO beta 2! -Improved graphics & style. -Improved audio & narrator jokes. -A true-story campaign! (12-level campaign is now an autobiographical reconstruction of my Openclaw Bitcoin / Nostr / Opus / AI Psychosis Journey) -Level select is now a timeline of your sessions. -The compaction wall never leaves. Just like in real life, the forgetting grinds at the edge, always there. -ENRICH YOUR HISTORY. One button and your own AI reads your redacted session history and authors you a personal campaign. -Talking subagentss -The Observer holds grudges within a run and never repeats a line. -Your agent is the installer. hermes skills install … and your Hermes agent sets the game up, curates your best levels, and writes custom announcer commentary about your actual history. -Level progression memory ... win or die, the recap shows exactly what advanced Hades style. -full settings (audio mix, captions, reduced motion… and an optional subagent that swears) -keyboard-first navigation and 20+ bugfixes from watching real agents and a real human play. Play it / build yours: sene1337.github.io/aiaio/ github.com/sene1337/aiaio

@majidmanzarpour @threejs @grok what's the benefit here

Whatever you're doing with Codex and @threejs make sure you tell it to build visual test harnesses to validate it's work

@majidmanzarpour @threejs do you have to use blender with fable / codex to make threeJS games?

@rot13maxi No that’s codex app isn’t it?

@bradmillscan Are you using gstack in the chatgpt web interface?

@ChrisWCDN Yea

Used GPT-5.6 Sol Ultra to migrate the people table to use guids instead of SharePoint ids. 18 hours later it was still running. Turns out it was trying to find and fight against any possible edge case imaginable before implementing it. Ultra sucks.

@GlitterPixely why does that look familiar

NEW: Plebs have created a new PSA anti-Fabian ad to promote BIP-110

How to vaporize your Fable budget in 10 minutes

@DocumentingBTC *this bitcoin wallet* why?

A unique new feature of this Bitcoin wallet shows the block your transaction is published inside of

people telling me the reasons it sucks is because gstack sucks? Is that true? What's better?

@embw_l0x why does it sucK?

@bradmillscan your using gstack bro

@CLAM102 why?

@bradmillscan Your first mistake was using gstack