Borrowing it
Nothing to install: this file belongs to freeeverett/deribit-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/freeeverett/deribit-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/freeeverett/deribit-mcpWrote 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/freeeverett/deribit-mcp/agents-md)<a href="https://agentmods.dev/instructions/freeeverett/deribit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/freeeverett/deribit-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/freeeverett/deribit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/freeeverett/deribit-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01457 | $0.01457 |
| Opus 5.5 | $0.00583 | $0.00583 |
| Sonnet 5.5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
deribit-mcp 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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A local stdio MCP server for the Deribit JSON-RPC v2 API. src/ is the only implementation; dist/ is build output.
Commands
npm run dev # run the sources directly via tsx, no build (development only)
npm run build # tsc -> dist/
npm run typecheck
npm test # = npm run smoke
npm run smoke # real stdio client + testnet regression, needs no credentials
npm run check:api # documentation drift detection; exit 1 = time to bump the version
npm run docs:coverage
Run at least npm test after any code change.
tsx is a devDependency only. The published artifact must be compiled JS, and bin points at dist/index.js: tsx drags startup from 77ms to 160ms (an MCP client launches the server once per session), grows a cold install from 24MB to 35MB (esbuild ships 26 platform binaries, and environments such as Alpine/musl then fail to run at all), and it bypasses the prepublishOnly type check, letting type errors ship silently to users' machines.
Non-negotiable conventions
- stdout carries JSON-RPC only. Every human-facing message goes to
process.stderr. One extra stdout line breaks client parsing. - Writes are never retried.
privateCall(..., { readOnly: false })sends exactly once. A replay is one extra real order. - Deribit's error responses come back as HTTP 400 and carry no
id. So theidis validated on successful responses only, and the body must be parsed before the status code is inspected. Keep this rule when editingsrc/deribit/client.ts— losing it degrades every business error into a useless id-mismatch message. - Handlers throw plain
Error/InvalidParamsError, which the SDK wraps into anisError: truetool result the model can read and retry from. Do not throwMcpError: that becomes a protocol error, which most clients render as a bare "call failed". - Every tool must declare
methods: [...]. It is the single source of truthcheck:apireconciles against, so a changed call must be mirrored there. - Declare no
outputSchemaand return nostructuredContent. Only a single text block. Responses such as an option chain are already large, and a structured copy would double the payload. - Cross-field constraints live in the handler, not in a Zod
.superRefine()— that keeps the error message under our control and delivers it as anisErrorresult to the model.
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.
- 2mo ago First seen · 63 lines · 1,457 tokens per session scan A 0bbd7f99c5a6
deribit-mcp AGENTS.md is an instructions file published in the GitHub repository freeeverett/deribit-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,457 tokens to every session, about $0.0058 per session on Opus 5.5. 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.
deribit-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deribit-mcp AGENTS.mdfreeeverett/deribit-mcp | Instructions file | 1 | 1mo ago | MIT | A | 1,457 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |