Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/macrocosm-os/apex/agents-mdgit clone --depth 1 https://github.com/macrocosm-os/apexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/macrocosm-os/apex/agents-md)<a href="https://agentmods.dev/instructions/macrocosm-os/apex/agents-md"><img src="https://agentmods.dev/badge/instructions/macrocosm-os/apex/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03146 | $0.03146 |
| Opus 5 | $0.01573 | $0.01573 |
| Sonnet 5 | $0.00629 | $0.00629 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
apex AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apex - Bittensor Subnet 1
Apex is Kaggle for decentralized intelligence. The difference: Kaggle captures predictions, while Apex captures intelligence — the actual models and algorithms that produce them. It runs open competitions where anyone can submit an algorithm or model to solve hard problems, scores every entry automatically, and pays out crypto rewards to the best solutions — no gatekeepers, no application process. Instead of a single company deciding who builds the best AI, Apex turns it into a global, permissionless contest where the best work wins and gets paid.
This guide takes you from a fresh machine to earning rewards on Apex. It assumes you've never used Bittensor or a blockchain before. Every unfamiliar word is explained the first time it appears.
What "mining Apex" actually means
You don't run a server or answer live requests. The loop is simple:
- Apex runs competitions (e.g. a strategy game, a simulation challenge).
- You write a solution — a Python file or a trained model file — that tries to solve the competition's problem.
- You submit that file using the Apex command-line tool (
apex). - Apex scores your submission against everyone else's.
- If your solution scores well, you automatically earn rewards.
That's it. Most of your time is spent writing good solutions. This guide covers the setup so you can submit them.
The few terms you can't avoid
You'll need a couple of crypto concepts. Here they are in plain English:
| Term | What it really is |
|---|---|
| TAO | The currency used in Bittensor (like dollars or pounds). You need a small amount to participate and is transferrable to fiat. |
| Alpha | The currency used in Apex (like dollars or pounds). This is what you'll earn and is transferrable to TAO by unstaking. |
| Wallet | Two keys that prove who you are. The coldkey is like your bank account (holds your TAO — keep it safe). The hotkey is like a login badge (it signs your submissions). One coldkey can have several hotkeys. |
| Mnemonic | This is 12 or more words that can be used to regenerate your wallet without losing the funds. Keep this safe. |
| Subnet | A project on the network. Apex is Subnet 1. |
| Registration | A one-time "buy-in" that puts your hotkey on Subnet 1 so you're allowed to use the CLI and submit solutions. It costs a small amount of TAO. NOTE: Hotkeys do get de-registered after a time due to poor performance to allow new entries into the network. |
| Submission fee | A small per-submission cost (paid in TAO) charged each time you submit a solution. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 320 lines · 3,146 tokens per session scan A 3f452473387c
apex AGENTS.md is an instructions file published in the GitHub repository macrocosm-os/apex (139 stars, last pushed today), licensed MIT. It adds 3,146 tokens to every session, about $0.0157 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Network AGENTS.md
AGENTS.md instructions for universalweb/Network, a project described as: The first Post-Quantum transitory cryptocurrency.
Get-Started-with-Web3 AGENTS.md
AGENTS.md instructions for beihaili/Get-Started-with-Web3, covering get started with web3 agent notes, 项目定位, ceo 运营目标, 常用命令 and ai-native 内容层.
LLM_trader AGENTS.md
AGENTS.md instructions for qrak/LLM_trader, covering llm trader — master architecture blueprint, 0. instruction authority, 1. system overview, 2. agent inventory and 3. application lifecycle.
platform AGENTS.md
AGENTS.md instructions for dashpay/platform, covering repository guidelines, project structure & module organization, architecture, technology stack and key components.
fearless-Android AGENTS.md
Instructions for soramitsu/fearless-Android, covering repository guidelines, project structure & modules, build, test, and dev commands, coding style & naming and testing guidelines.
all copilot-instructions.md
Instructions for animicaorg/all, covering copilot instructions for animica, architecture overview, key patterns, determinism & canonical encoding and configuration & policy.