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/berntpopp/orphanet-link/agents-mdgit clone --depth 1 https://github.com/berntpopp/orphanet-linkWrote 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/berntpopp/orphanet-link/agents-md)<a href="https://agentmods.dev/instructions/berntpopp/orphanet-link/agents-md"><img src="https://agentmods.dev/badge/instructions/berntpopp/orphanet-link/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 5.1 | $0.06011 | $0.06011 |
| Opus 5 | $0.03005 | $0.03005 |
| Sonnet 5 | $0.01202 | $0.01202 |
| Haiku 4.5 | $0.00601 | $0.00601 |
Grade A, and why
orphanet-link 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 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.
How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — orphanet-link
Guidance for agents and contributors working in this repository.
What this is
orphanet-link is an MCP + REST server that grounds rare-disease queries in
Orphanet's scientific knowledge files (Orphadata). It builds a local SQLite/FTS5
index from the eight English Orphadata XML products and serves 19 read-only tools
for disease lookup, gene and HPO associations, epidemiology, natural history,
functional consequences, classification hierarchy, and cross-ontology mapping.
It mirrors the sibling mondo-link stack/architecture and slots into
genefoundry-router under the orphanet namespace.
Two planes (non-negotiable boundary)
-
Data plane —
config.py,constants.py,identifiers.py,exceptions.py,logging_config.py,buildinfo.py,ingest/,data/,services/. Downloads the Orphadata XML files (conditional GET with ETag/Last-Modified), atomically builds the SQLite index, and returns plain Python dicts. It raises typed exceptions fromorphanet_link.exceptions; it never builds error envelopes and never imports fromorphanet_link.mcp. -
MCP plane —
mcp/. Domain-agnostic scaffolding copied and adapted frommondo-link.run_mcp_tool(inmcp/envelope.py) ownssuccess/_metaand converts exceptions into returned structured errors (never raised to the client). Tool modules undermcp/tools/call service methods and attach_meta.next_commands; they do not touch SQLite or raise domain exceptions.
The boundary is enforced structurally: the data plane has no knowledge of MCP types; the MCP plane has no knowledge of SQL or XML.
The eight Orphadata products and where each is parsed
| Product | Orphadata file | Parser module | Tables populated |
|---|---|---|---|
| 1 | en_product1.xml |
ingest/parsers/product1.py |
disorder, disorder_synonym, disorder_lookup, disorder_fts, xref |
| 3 | en_product3_<id>.xml (~33) |
ingest/parsers/product3.py |
classification_edge, classification_closure, specialty |
| 4 | en_product4.xml |
ingest/parsers/product4.py |
phenotype |
| 6 | en_product6.xml |
ingest/parsers/product6.py |
gene, disorder_gene |
| 7 | en_product7.xml |
ingest/parsers/product7.py |
linearisation |
| 8 (funct) | en_funct_consequences.xml |
ingest/parsers/funct.py |
disability |
| 9 prev | en_product9_prev.xml |
ingest/parsers/product9_prev.py |
prevalence |
| 9 ages | en_product9_ages.xml |
ingest/parsers/product9_ages.py |
age_of_onset, inheritance |
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 Changed · +103 lines · +1,616 tokens per session 2866acc19f69
- 4d ago First seen · 340 lines · 4,395 tokens per session scan A 55be9e246544
orphanet-link AGENTS.md is an instructions file published in the GitHub repository berntpopp/orphanet-link (0 stars, last pushed 3d ago), licensed MIT. It adds 6,011 tokens to every session, about $0.0301 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
hpo-link AGENTS.md
AGENTS.md instructions for berntpopp/hpo-link, covering agents.md — hpo-link, what this is, two planes (non-negotiable boundary), architecture: ingest → data dao → services → mcp and invariants.
hpo-link CLAUDE.md
Claude Code instructions for berntpopp/hpo-link, covering claude.md, role, directory layout, key make commands and tl;dr lint / test / build.
mgi-link AGENTS.md
AGENTS.md instructions for berntpopp/mgi-link, covering agents.md — engineering conventions for mgi-link, golden rules, architecture invariants (do not break), fleet deploy contract and data plane.
mgi-link CLAUDE.md
Claude Code instructions for berntpopp/mgi-link, covering claude.md, tl;dr, common commands and layout.
genefoundry-router AGENTS.md
AGENTS.md instructions for berntpopp/genefoundry-router, covering agents.md, what this project is, required check before handoff, coding standards and project-specific guidance.
genefoundry-router CLAUDE.md
Claude Code instructions for berntpopp/genefoundry-router, a project described as: MCP gateway federating 21 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.