开发系统最极致高效的Agents.md,没有之一:
# AGENTS.md
## Core Principles
- Choose the simplest implementation that fully satisfies the current requirements. Avoid unnecessary abstraction, configuration, indirection, or speculative extensibility.
- Make the smallest necessary change that fixes the root cause. Do not refactor unrelated modules or change strategy semantics unless explicitly requested.
- Grow the system in layers. Start from the smallest working end-to-end version and add new capabilities incrementally. Never replace a working system with unfinished complexity.
- Reuse existing project components before creating new ones. Prefer extending proven modules over introducing parallel implementations.
- Prefer well-maintained libraries when they reduce overall complexity or improve reliability. Do not reimplement common functionality without a clear benefit.
- Keep components modular with clearly defined responsibilities. Avoid unnecessary coupling between strategy logic, execution, accounting, replay, and infrastructure.
- Design for long-term maintainability once a feature or strategy has been validated. Do not over-engineer speculative ideas before evidence exists.
---
## Strategy Development
- Validate hypotheses with historical replay before introducing forward-only logic whenever historical validation is possible.
- Every trading strategy must progress through Replay → Shadow → Canary → Live. Do not skip validation stages.
- Base design decisions on measurable evidence rather than intuition. Optimize only after demonstrating that an edge exists.
- Treat every strategy as an independent contract. Do not silently alter frozen behavior without explicit authorization.
---
## Existing Systems
- Do not break running Shadow or Live systems for unrelated work.
- Preserve compatibility only when required by active production or validation workflows. Otherwise, remove obsolete code instead of accumulating compatibility layers.
- Reuse existing infrastructure whenever possible, including replay engines, accounting, execution, wallet management, order book handling, logging, monitoring, and daemon frameworks.
---
## Engineering Standards
- Prefer deterministic behavior over hidden automation.
- Fail loudly when assumptions are violated. Do not silently ignore errors or fall back to unexpected behavior.
- Keep configuration minimal. Introduce new configuration only when behavior genuinely needs to vary.
- Remove dead code instead of leaving unused paths behind.
- Write code that is easy to inspect, replay, test, and reason about.
- Keep implementation consistent with existing project architecture unless an architectural change is explicitly requested.
---
## Scope Discipline
- Implement only the requested scope.
- Do not introduce unrelated optimizations, redesigns, migrations, or feature expansions.
- Non-blocking findings outside the requested scope may be noted separately but must not be merged into the current task.
- Consider a task complete once its agreed acceptance criteria are satisfied. Treat subsequent improvements as separate work items.
显示更多
Hot take… isn’t it kinda crazy that nobody is really using AI Agents? I don’t mean software engineers or AI early adopters. I mean “college friends talking about it in group chat,” the feeling you got when everyone started using Instagram or TikTok.
These frontier AI models are *insane* (as are the harnesses & tool calls & the like). And every large tech co has an AI agents platform, not to mention all the YC startups doing vertical agents. Yet all of your friends and family outside of tech — who spend all day staring at their iPhones and get paid to work in browser tabs — don’t really care or find themselves using any AI agents yet.
Yes ChatGPT, Claude, etc. are extremely popular… but if you look at the engagement data the vast majority of people are still using these aI chat tools like a glorified Google + Grammarly. That’s why the AGI labs are all pushing desktop apps for Codex, Cowork, etc. so hard to non-technical ppl. And yes exceptions for lawyers and customer service but even those have some asterisks and exceptions to rule.
Look I’m not saying the ChatGPT moment for AI Agents is not coming… it most definitely is! Remember we pivoted from Arc to Dia precisely because we believe computing is going to be radically reimagined around these AI primitives. No doubt. But that’s my point: it’s just so surprising it hasn’t happened yet because all of the tech you’d need is there.
Again if you stop for a second and think about it… for all the press and money and hype and models and crazy ARR numbers… this “AI Agent” moment does not *feel* like the other breakthrough tech moments we’ve lived through (e.g. think the shift to Stories via Snapchat & Instagram, or shift to on-demand via Uber/Airbnb/Doordash).
Which is a long way of saying: if you can figure out the answer to “why” most people don’t care about AI agents yet (and have no enduring interest in using them) — especially since the models and harnesses are here and ready — the answer to that question will allow you to capture a lot of marketshare and make a lot of money in 2027.
Theoretically, the tech is ready for AI Agents to totally transform how we work and live our lives… but alas the general public dgaf… that’s the generational puzzle to solve for the next 12 months for anyone not working on the models themselves.
显示更多
Watch the full recording of our Q2 2026 earnings call.
Prepared Remarks
00:00:00 - Welcome
00:01:20 - 843,775 BTC, 203,683 sats per share, $17B raised year to date, and Strategy’s position as the largest institutional holder of Bitcoin
00:03:27 - Q2 balance sheet: $49.7B of digital assets, $3.75B current USD reserve, lower debt, higher preferred equity, and strong stress-case coverage
00:08:57 - Bitcoin KPIs: 4.5% BTC Yield, 29,997 BTC Gain, and ~3.6x growth in Bitcoin per share since 2020
00:12:47 - Q2 execution: higher Bitcoin holdings, lower debt, larger USD reserves, stronger Bitcoin per share, and active capital management
00:15:03 - Strategy as a net buyer of Bitcoin and net issuer of Digital Credit: 48x more BTC bought than sold and 300x more Digital Credit issued than repurchased
00:18:47 - Returning $STRC to $99–$100 through USD reserves, Bitcoin monetization, repurchases, dividend management, and disciplined issuance
00:24:50 - Bitcoin liquidity: why Strategy’s bitcoin purchases and sales are not material to overall Bitcoin trading volume
00:33:03 - Bitcoin as Digital Capital: website metrics, the 200-week moving average, current headwinds, Bitcoin Dominance, banking adoption, and security coordination
00:44:08 - $STRC as flagship Digital Credit: liquidity, lower volatility, market depth, yield, investor base, path to par, and updated credit metrics
01:05:04 - Equity framework: hurdle rate, breakeven rate, floor rate, market skepticism, $MSTR outperformance, franchise advantages, and Strategy’s long-term ambition
Q&A
01:19:31 - Why Bitcoin-backed borrowing is not currently the preferred path to build USD reserves
01:23:11 - Why Strategy is consolidating around $STRC instead of creating more instruments or selling volatility
01:40:37 - Equitizing, repaying, or refinancing convertible debt
01:43:18 - Covered calls, cash-secured puts, Digital Credit, Bitcoin as money, and marketing products to the 99% outside Bitcoin
01:59:22 - USD reserve minimums and the path to $STRC trading at par
02:00:55 - Amplification, USD/BTC reserve mix, and countercyclical capital management
02:12:04 - Why Strategy does not intend to issue $STRC below par
02:20:34 - Lessons from 2022 and 2026, tokenized securities, Digital Money, and the June 26 dislocation
02:34:54 - Closing remarks
显示更多