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/cyanheads/gnomad-genetics-mcp-server/claude-mdgit clone --depth 1 https://github.com/cyanheads/gnomad-genetics-mcp-serverWhat 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 | $0.06274 | $0.06274 |
| Opus 5 | $0.03137 | $0.03137 |
| Sonnet 5 | $0.01255 | $0.01255 |
| Haiku 4.5 | $0.00627 | $0.00627 |
Grade A, and why
gnomad-genetics-mcp-server 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 yesterday.
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.
This is a copy
78% identical to obsidian-mcp-server AGENTS.md — 352 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Protocol
Server: gnomad-genetics-mcp-server
Version: 0.2.0
Framework: @cyanheads/mcp-ts-core ^0.12.3
Engines: Bun ≥1.3.0, Node ≥24.0.0
MCP SDK: @modelcontextprotocol/server ^2.0.0
Zod: ^4.4.3
Read the framework docs first:
node_modules/@cyanheads/mcp-ts-core/CLAUDE.mdcontains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
Core Rules
- Logic throws, framework catches. Tool/resource handlers are pure — throw on failure, no
try/catch. PlainErroris fine; the framework catches, classifies, and formats. Use error factories (notFound(),validationError(), etc.) when the error code matters. - Use
ctx.logfor request-scoped logging. Noconsolecalls. - Use
ctx.statefor tenant-scoped storage. Never access persistence directly. - Need input the caller didn't supply?
return ctx.requestInput(...)and readctx.inputswhen the handler is re-entered. Neverawaitfor user input mid-handler. - Secrets in env vars only — never hardcoded.
- Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.
Patterns
Real definitions from this server, condensed. The full versions live under src/mcp-server/.
Tool (src/mcp-server/tools/definitions/gnomad-get-gene-constraint.tool.ts)
import { tool, z } from '@cyanheads/mcp-ts-core';
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
import { getGnomadService } from '@/services/gnomad/gnomad-service.js';
import { datasetField, geneField, referenceGenomeField } from '../shared-schemas.js';
export const gnomadGetGeneConstraint = tool('gnomad_get_gene_constraint', {
title: 'gnomad-genetics-mcp-server: get gene constraint',
description: 'Fetch gnomAD loss-of-function constraint for a gene — pLI, LOEUF, …',
annotations: { readOnlyHint: true, openWorldHint: true, idempotentHint: true },
input: z.object({ gene: geneField, dataset: datasetField, reference_genome: referenceGenomeField }),
output: z.object({
gene_id: z.string().describe('Ensembl gene ID resolved for the gene.'),
symbol: z.string().describe('HGNC gene symbol.'),
pli: z.number().nullable().describe('pLI — probability of LoF intolerance; >0.9 intolerant.'),
// … remaining flat constraint fields, all nullable
constraint_flags: z.array(z.string()).describe('Constraint caveat flags (e.g. v4 beta notes).'),
}),
// Typed error contract — ctx.fail('gene_not_found', …) is type-checked against this union.
errors: [
{ reason: 'gene_not_found', code: JsonRpcErrorCode.NotFound,
when: 'No gene matched the symbol or Ensembl ID in this build.',
recovery: 'Check the symbol spelling or resolve a stable Ensembl gene ID via ensembl_lookup_gene.' },
],
async handler(input, ctx) {
const svc = getGnomadService();
const dsCtx = svc.resolveDatasetContext(input.dataset, input.reference_genome);
const constraint = await svc.getGeneConstraint(input.gene, dsCtx, ctx);
if (!constraint) throw ctx.fail('gene_not_found', `Gene "${input.gene}" not found.`);
return constraint;
},
// format() populates content[] — the markdown twin of structuredContent.
// Different clients read different surfaces (Claude Code → structuredContent,
// Claude Desktop → content[]); both must carry the same data.
// Enforced at lint time: every field in `output` must appear in the rendered text.
format: (result) => [{ type: 'text', text: `## ${result.symbol} (${result.gene_id})` }],
});
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.
- yesterday First seen · 421 lines · 6,274 tokens per session scan A 5deda681a275
gnomad-genetics-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/gnomad-genetics-mcp-server (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 6,274 tokens to every session, about $0.0314 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to obsidian-mcp-server AGENTS.md, differing in 352 lines, and is treated as a copy.
Other instructions, from other repositories
ClawBio AGENTS.md
AGENTS.md instructions for ClawBio/ClawBio, covering agents.md — clawbio guide for ai coding agents, project overview, setup, clone and install dependencies.
SciAgent-Skills AGENTS.md
AGENTS.md instructions for jaechang-hits/SciAgent-Skills, covering skills — workflow guide, directory layout, workflow: topic → entry (5 steps), step 2. choose category and step 3. gather reference material.
SciAgent-Skills CLAUDE.md
Claude Code instructions for jaechang-hits/SciAgent-Skills, a project described as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.
ClawBio CLAUDE.md
Claude Code instructions for ClawBio/ClawBio, covering claude.md — clawbio agent instructions, homepage (index.html) — strict, key files, slash commands and skill routing table.
open-genome-agent AGENTS.md
Instructions for 45ck/open-genome-agent, covering agents.md, core policy, mission, mandatory rules and delegation rules.
mygene-mcp AGENTS.md
AGENTS.md instructions for nickzren/mygene-mcp, covering agent guide — mygene-mcp, what this server is, run locally (stdio), use this server for and triage hints.