Borrowing it
Nothing to install: this file belongs to monarch-initiative/dismech. 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/monarch-initiative/dismech/main/.claude/skills/coarse-phenotype-bindings/SKILL.mdgit clone --depth 1 https://github.com/monarch-initiative/dismechWrote 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/skills/monarch-initiative/dismech/coarse-phenotype-bindings)<a href="https://agentmods.dev/skills/monarch-initiative/dismech/coarse-phenotype-bindings"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/coarse-phenotype-bindings/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/skills/monarch-initiative/dismech/coarse-phenotype-bindings"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/coarse-phenotype-bindings.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 | $0.00117 | $0.01928 |
| Opus 5.5 | $0.00047 | $0.00771 |
| Sonnet 5.5 | $0.00023 | $0.00386 |
| Haiku 4.5 | $0.00012 | $0.00193 |
Grade A, and why
coarse-phenotype-bindings 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coarse phenotype bindings
A phenotype bound to a coarse HPO term — HP:0000478 Abnormality of the eye,
HP:0002664 Neoplasm, HP:0000077 Abnormality of the kidney — passes every
other gate while saying almost nothing. Schaaf-Yang_Syndrome named strabismus,
esotropia and myopia in its description and then discarded all three in the
binding.
Such a binding is not forbidden. It must say why.
just check-coarse-phenotypes # gate (offline, in `just qc`)
just list-coarse-phenotypes # census, incl. hub convergence
just update-coarse-phenotype-baseline # only ever to SHRINK
The four values
| Value | Means | Companion requirement |
|---|---|---|
VARIABLE_SPECTRUM |
involvement varies in form between patients | none — a bare declaration |
SOURCE_UNSPECIFIED |
the cited source characterizes it no further | none — the snippet is the proof |
NO_HPO_TERM |
narrower than any HP term | preferred_term ≠ the bound label; record term_gap |
PATHOGRAPH_HUB |
a deliberately unqualified convergence node | ≥1 causal edge targets it; no frequency |
Two take no companion at all. That is the point: the guard asks you to state a reason, not to do extra work proving it.
This is not a rule to prefer narrow terms
Manufacturing a specificity the source does not support is a worse defect than a
coarse binding, and the term contract forbids it. There is deliberately no depth
or information-content metric: HP:0004322 Short stature is the most-used HP
term in the KB, and HP:0001627 Abnormal heart morphology carries "Congenital
heart defect" as an EXACT synonym — so any such metric would flag the two terms
most often exactly right.
The coarse set is 56 hand-reviewed terms across two meaning:-bound schema
enums: PhenotypeCategoryEnum (the 23 organ-system roots, which are also the
browser's facet vocabulary) and CoarsePhenotypeTermEnum (33 terms below those
roots that still name a system, organ or region). Widening it is a schema PR
with an argument, not a threshold. coarse_phenotype_terms.yaml records the
inclusion rule and why each near-miss was left out.
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.
- 1mo ago First seen · 149 lines · 117 tokens per session scan A e36998474be2
coarse-phenotype-bindings is a skill published in the GitHub repository monarch-initiative/dismech (69 stars, last pushed today), licensed BSD-3-Clause. It adds 117 tokens to every session and 1,928 once invoked, about $0.0005 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 2026-09-21.
Other skills, from other repositories
dosdp-design-patterns
Skills for understanding and applying DOSDP (Dead Simple Ontology Design Patterns) to ensure consistent ontology term creation and maintenance. This skill is about recognizing patterns and ensuring consistency, not using dosdp-tools directly.
robot-obo-tool
Skills for using ROBOT, the OBO ontology command-line toolkit for reasoning, template-based term creation, quality control, format conversion, and ontology manipulation. Use this when working with OWL/OBO ontologies that need automated processing.
editing-obo-ontologies
Skills and tools for editing OBO format ontologies, including querying terms, checking out/checking in individual terms, and following OBO format conventions. Do not use this if the source for the ontology you are editing is not in obo format (e.g. ofn).
ontology-access-kit
Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
complexa-sweep
Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product hyperparameter scans, sweeper YAML authoring, configuration comparisons, ablations, tuning, success-rate ranking, or Pareto searches over quality and wall-clock cost. Do…