dismech: Skill for Claude Code

.claude/skills/claim-disease/SKILL.md

claim-disease is a skill for Claude Code from monarch-initiative/dismech. It costs 102 tokens per session (5,868 once invoked), scanned A, original, BSD-3-Clause.

A workflow for choosing and claiming diseases to curate in dismech, a repository for structured disease-mechanism information. It checks existing claims and the remaining queue before opening a claim issue.

In plain words
What is it for?
Use it when choosing the next disease to curate or claiming one or more diseases for work.
Why use it?
It prevents two contributors from taking the same disease and keeps the selection tied to the repository’s current work queue.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is monarch-initiative/dismech's own configuration. It tells Claude Code how to work on dismech itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dismech configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/monarch-initiative/dismech/main/.claude/skills/claim-disease/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/monarch-initiative/dismech

Made for: Claude Code.

Wrote 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.

agentmods badge for claim-disease

README.md
[![agentmods](https://agentmods.dev/badge/skills/monarch-initiative/dismech/claim-disease/github.svg)](https://agentmods.dev/skills/monarch-initiative/dismech/claim-disease)
Your own site
<a href="https://agentmods.dev/skills/monarch-initiative/dismech/claim-disease"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/claim-disease/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.

agentmods 80×15 button for claim-disease

Your own site · 80×15
<a href="https://agentmods.dev/skills/monarch-initiative/dismech/claim-disease"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/claim-disease.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.05868
Opus 5 $0.00051 $0.02934
Sonnet 5 $0.00020 $0.01174
Haiku 4.5 $0.00010 $0.00587

Measured 11d ago against content hash 531bb0b9073b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claim-disease 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 11d 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.

`gh`, which is absent there — and `curl https://api.github.com` fails too:
.claude/skills/claim-disease/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claim-disease

Claim the next disease(s) to curate. The queue of remaining work is stubs/; the live lock on who has what is an open GitHub issue labelled claim. This skill checks both, then files the claim, and then commences work.

When to use

  • "What should I curate next?"
  • "Claim the next disease"
  • "Pick me the next 3 diseases and open issues"

Skip when:

  • The user names a specific disease — just open that issue directly.

The queue is a directory, not a ranking

stubs/ holds one YAML per disease we intend to curate. There is no score. The only ordering is a hand-set priority band (HIGH / NORMAL / LOW) that a person put there in a pull request; within a band the order is an arbitrary (hash-based, reproducible) spread and carries no information.

So just next-stubs gives you a pool, not a ruling. Pick the disease you actually know something about. If the first row is outside what you can curate well, skip it and say so. Skipping is expected, not a failure.

You are also allowed — encouraged — to stop and ask the user, especially when a candidate looks like it should not be a disorder entry at all.

Candidates to be suspicious of

Read the label and ask whether it names one disease with one reasonably conserved pathograph. If it does not, do not file a curation issue. Instead, edit the stub: set entry_type and explain in notes.

Watch for:

  • Groupings — a union of distinct diseases. lysosomal storage disease, RASopathy, B-cell non-Hodgkin lymphoma. These belong in kb/groupings/ (see the Disease Groupings section of CLAUDE.md), not kb/disorders/. Set entry_type: GROUPING.
  • Over-broad categoriessoft tissue sarcoma has roughly 800 NCIT subclasses. There is no single mechanism to curate. Set entry_type: GROUPING or OUT_OF_SCOPE.
  • Multiple mechanisms under one namerickets (nutritional, X-linked hypophosphatemic, vitamin-D-dependent) is several diseases sharing a radiographic finding. Usually GROUPING.
  • Phenotypes, not diseasesmicrocephaly is a finding. OUT_OF_SCOPE, unless the specific disease entity is meant.
  • Susceptibility / predisposition terms — usually OUT_OF_SCOPE.
  • Cancers — deprioritize for now. The project does not yet have a settled lump/split strategy for neoplasms (see #7082). Prefer a non-cancer candidate, or ask the user.

Read the full file on GitHub · 478 lines

Changes

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.

  1. 11d ago First seen · 478 lines · 102 tokens per session scan A 531bb0b9073b

Subscribe to this mod's changes

claim-disease is a skill published in the GitHub repository monarch-initiative/dismech (60 stars, last pushed today), licensed BSD-3-Clause. It adds 102 tokens to every session and 5,868 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

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.

ai4curation/curation-skills · 52 tokens

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.

ai4curation/curation-skills · 47 tokens

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).

ai4curation/curation-skills · 63 tokens

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.

ai4curation/curation-skills · 39 tokens

cuopt-numerical-optimization-formulation

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

NVIDIA/skills · 42 tokens

nemo-mbridge-perf-expert-parallel-overlap

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.

NVIDIA/skills · 56 tokens