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/pelazas/carrydesk/agents-mdgit clone --depth 1 https://github.com/pelazas/carrydeskWrote 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/pelazas/carrydesk/agents-md)<a href="https://agentmods.dev/instructions/pelazas/carrydesk/agents-md"><img src="https://agentmods.dev/badge/instructions/pelazas/carrydesk/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 | $0.02885 | $0.02885 |
| Opus 5 | $0.01443 | $0.01443 |
| Sonnet 5 | $0.00577 | $0.00577 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
carrydesk AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
report everything as filtered whether or not it is. Use `curl --max-time`. How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — context for an AI agent picking up carrydesk
Read this first. It tells you what this repo is, what state it is in, what is verified vs. assumed, and what you may do without asking.
1. What this is
carrydesk publishes a cross-sectional funding-carry ranking for Hyperliquid perpetuals and sells it per call in USDC.
Every rebalance, rank the liquid Hyperliquid perp universe by trailing 14-day mean funding. The most negative names pay you to hold them long; the most positive pay you to short them. The spread between the two legs is the carry — a structural risk premium, not a prediction.
The same signal is traded by a live market-neutral book, which is why the parameters are what they are. That book is a separate, private project; this repo neither imports from it nor connects to it.
| Surface | Audience | Payment |
|---|---|---|
/v1/free/* — top-5 each leg, delayed 24h |
the funnel | none |
/v1/carry/* — full live ranking + history |
devs, bots | x402, USDC per call |
| MCP server — the same data as agent tools | Claude/Cursor users | same, transparent |
No edge is being sold. Funding rates are public, the ranking is a transform of public data, and the strategy is a documented premium. What is sold is the computation, the archive, and the reliability.
2. Status
Live on Base mainnet, settling real USDC. Distribution barely started.
| Piece | State |
|---|---|
| Hyperliquid data client | ✅ verified live (177 perps, ~38 above the $1m/day floor) |
| Carry ranking maths | ✅ 14 unit tests |
| FastAPI service | ✅ deployed, HTTPS, real data |
| x402 paywall | ✅ real USDC settled on Base mainnet |
| MCP server | ✅ 6 tools, verified against production, paid path works |
| Ops monitor | ✅ every 10 min → Telegram, verified with a real alert |
| Snapshot archive | ✅ append-only, auto-committed daily |
| Mainnet payments | ✅ live, settlements confirmed on-chain — python scripts/revenue.py |
| Discovery surfaces | ✅ llms.txt, robots.txt, sitemap, JSON-LD, /archive |
| Distribution | ⚠️ passive only — nothing posted or listed by a human |
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 · 241 lines · 2,885 tokens per session scan A 83306be492ca
carrydesk AGENTS.md is an instructions file published in the GitHub repository pelazas/carrydesk (0 stars, last pushed 3d ago), licensed MIT. It adds 2,885 tokens to every session, about $0.0144 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.