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/orodruinlabs/cryptoexchanges.net/claude-mdgit clone --depth 1 https://github.com/OrodruinLabs/CryptoExchanges.NetWrote 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/orodruinlabs/cryptoexchanges.net/claude-md)<a href="https://agentmods.dev/instructions/orodruinlabs/cryptoexchanges.net/claude-md"><img src="https://agentmods.dev/badge/instructions/orodruinlabs/cryptoexchanges.net/claude-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 5.1 | $0.00489 | $0.00489 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
CryptoExchanges.Net CLAUDE.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 5d 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.
What it actually says
CryptoExchanges.Net — Project Instructions
Git Convention
- The default branch is
main(protected). Branch + PR for every change; squash-merge tomain.
Code Conventions
- One type per file. Every top-level type (record/class/DTO/enum/interface/struct/exception) lives in its own file named after the type. No exchange prefix on file or type names — the namespace carries the exchange.
- Wire DTOs are
internaland live in each exchange'sDtos/folder.Coreis the shared cross-exchange contract (Core.Models/Core.Interfaces); never add a shared DTO project. - DTO naming (house rule). Name every wire DTO
{Concept}Dtousing the canonicalCore.Modelsconcept it maps to — identical across all exchanges regardless of the vendor's term (TickerDto,OrderDto,TradeDto,OrderBookDto,ServerTimeDto,FillDto,SymbolInfoDto,BalanceDto,AccountDto). Vendor vocabulary lives ONLY in[JsonPropertyName], never in the type name.- No
Response/Result/Historyon leaf DTOs. Reserved wrappers only:ResponseDto<T>/ResponseObjectDto<T>(transport envelope — the ONLY use of "Response") andListDto<T>(a{ list:[...] }payload — the ONLY use of "List"). Never write a typed list-wrapper. - Two-level balance shapes: per-asset leaf →
BalanceDto, container →AccountDto. An exchange's own executed-trades/fills shape →FillDto.
- No
- Comments & XML docs (LEAN). No banner / section-separator comments (
// ── X ──,#region,// === X ===). No comments that restate the code; keep comments only for non-obvious business logic / exchange quirks. XML docs are a short<summary>(plus<param>/<returns>/<exception>only where they add information the signature doesn't) — no<remarks>/<para>essays. Interface members carry the docs; implementations use<inheritdoc/>. When cloning a reference file, do not copy its comment noise — clean it to these rules.
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.
- 5d ago First seen · 13 lines · 489 tokens per session scan A 5f16daba4f4f
CryptoExchanges.Net CLAUDE.md is an instructions file published in the GitHub repository OrodruinLabs/CryptoExchanges.Net (7 stars, last pushed 10d ago), licensed Apache-2.0. It adds 489 tokens to every session, about $0.0024 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 2026-08-31.
Other instructions, from other repositories
binance-trading-bot AGENTS.md
AGENTS.md instructions for chrisleekr/binance-trading-bot, covering engineering charter, project, architecture principles, core invariants and stack.
binance-net
Use Binance.Net when generating C#/.NET code that interacts with the Binance cryptocurrency exchange — including Spot, Margin, USD-M Futures, COIN-M Futures, Options, sub-accounts, brokerage, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on any request…
Binance.Net copilot-instructions.md
Copilot instructions for JKorf/Binance.Net, covering copilot instructions for binance.net, use binance.net, not raw http, client setup, result handling and api structure.
netrock CLAUDE.md
Claude Code instructions for fpindej/netrock, covering claude.md, hard rules, backend, frontend and cross-cutting.
bitfinex-net
Use Bitfinex.Net when generating C#/.NET code that interacts with Bitfinex, including Spot, margin, derivatives symbols, funding, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on Bitfinex integration requests in C#, .NET, dotnet, F#, or VB.NET context.
Bitfinex.Net copilot-instructions.md
Copilot instructions for JKorf/Bitfinex.Net, covering copilot instructions for bitfinex.net, use bitfinex.net, not raw http, client setup, result handling and api structure.