dismech: Skill for Claude Code

.claude/skills/dismech-references/SKILL.md

dismech-references is a skill for Claude Code from monarch-initiative/dismech. It costs 88 tokens per session (3,047 once invoked), scanned A, original, BSD-3-Clause.

A workflow for adding and checking evidence references in a medical or scientific knowledge base. It works with identifiers such as PMID, DOI, and clinical-trial registration numbers, and requires quoted text copied exactly from the cited source.

In plain words
What is it for?
Use it when adding, reviewing, repairing, or validating references in knowledge-base YAML or research reports. It helps check evidence snippets, normalize citation formatting, and regenerate reference caches from source records.
Why use it?
It reduces unsupported claims, incorrect citations, and quotations that do not actually prove the statement they accompany. It also prevents manually editing cached reference files in ways that could hide errors.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/dismech-references/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 dismech-references

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/monarch-initiative/dismech/dismech-references"><img src="https://agentmods.dev/badge/skills/monarch-initiative/dismech/dismech-references.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00088 $0.03047
Opus 5 $0.00044 $0.01523
Sonnet 5 $0.00018 $0.00609
Haiku 4.5 $0.00009 $0.00305

Measured 5d ago against content hash f6316b86b041, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dismech-references 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 5d 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.

.claude/skills/dismech-references/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Curate Evidence and References

Use this workflow whenever evidence or its cited source changes.

Non-negotiable rules

  • Quote an exact substring of the cited source. Do not paraphrase or fabricate a snippet.
  • Confirm that the quote substantively supports the precise claim. A matching string from the wrong paper, or an unrelated sentence from the right paper, is not evidence.
  • Prefer a result sentence from the abstract or authoritative source record. A paper title usually establishes only that a topic was studied.
  • Never create or hand-edit references_cache/*.md. Generate or regenerate a cache entry with just fetch-reference <ID>.
  • Never use fuzzy auto-repair to rewrite snippets. Read the source and copy the exact passage, choose another source, or remove the evidence.
  • Treat deep-research output as leads, not ground truth.

Evidence shape

evidence:
  - reference: PMID:12345678
    supports: SUPPORT
    evidence_source: HUMAN_CLINICAL
    snippet: "Exact text copied from the cited source."
    explanation: "How this passage supports the specific KB claim."

Use supports: SUPPORT, REFUTE, or the value allowed by the schema. Make the explanation connect the quote to the claim without adding conclusions the quote does not establish.

Classify evidence_source by the cited study, not by the curator or the claim:

  • HUMAN_CLINICAL: patients, cohorts, clinical observations, or trials
  • MODEL_ORGANISM: in vivo non-human animal or organism work
  • IN_VITRO: cells, organoids, explants, or biochemical assays
  • COMPUTATIONAL: modeling, simulation, or in-silico analysis
  • OTHER: evidence that does not fit the categories above

Inspect the schema and nearby current entries if a field or enum is uncertain.

Workflow

1. Screen deep-research sources

If evidence came from research/, first read the report's reference_validation, unresolved_references, needs_review, and off_topic_references results. Do not curate an unresolved identifier. An off-topic flag is a reason to inspect the paper, not an automatic rejection.

Read the full file on GitHub · 314 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. 5d ago Changed · +68 lines f6316b86b041
  2. 9d ago First seen · 246 lines · 88 tokens per session scan A 9d7bb927e645

Subscribe to this mod's changes

dismech-references is a skill published in the GitHub repository monarch-initiative/dismech (59 stars, last pushed today), licensed BSD-3-Clause. It adds 88 tokens to every session and 3,047 once invoked, about $0.0004 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 2026-08-30.

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

earth2studio-create-datasource

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.

NVIDIA/skills · 53 tokens