clinical-research-tools

clinical-research-tools is a skill for Claude Code, Codex from DrugClaw/DrugClaw. It costs 74 tokens per session (945 once invoked), scanned A, original, Apache-2.0.

A guide for planning and evaluating research involving groups of people, such as clinical trials or observational studies. It covers study design, outcomes, evidence quality, statistics, and reporting rules.

In plain words
What is it for?
Use it to design or review protocols, statistical analysis plans, clinical study reports, and evidence summaries. It helps choose study types, define outcomes and eligibility rules, assess bias and missing data, and select reporting guidelines.
Why use it?
It helps avoid weak study plans, unclear outcomes, biased comparisons, and reports that miss required information. It also keeps research planning separate from medical advice for individual patients.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design or review protocols, statistical analysis plans, clinical study reports, and evidence summaries. It helps choose study types, define outcomes and eligibility rules, assess bias and missing data, and select reporting guidelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/drugclaw/drugclaw/clinical-research-tools
Install

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.

Any agent
npx skills add DrugClaw/DrugClaw --skill clinical-research-tools
Clone the repo
git clone --depth 1 https://github.com/DrugClaw/DrugClaw

Made for: Claude Code, Codex.

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 clinical-research-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/drugclaw/drugclaw/clinical-research-tools/github.svg)](https://agentmods.dev/skills/drugclaw/drugclaw/clinical-research-tools)
Your own site
<a href="https://agentmods.dev/skills/drugclaw/drugclaw/clinical-research-tools"><img src="https://agentmods.dev/badge/skills/drugclaw/drugclaw/clinical-research-tools/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 clinical-research-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/drugclaw/drugclaw/clinical-research-tools"><img src="https://agentmods.dev/badge/skills/drugclaw/drugclaw/clinical-research-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 945 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.
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 $0.00074 $0.00945
Opus 5 $0.00037 $0.00473
Sonnet 5 $0.00015 $0.00189
Haiku 4.5 $0.00007 $0.00094

Measured 13d ago against content hash 7029fa57e841, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

clinical-research-tools 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 13d 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.

skills/medical/clinical-research-tools/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clinical Research Tools

Use this skill for group-level human research work, not bedside care.

Typical triggers:

  • choose between RCT, cohort, case-control, cross-sectional, diagnostic, or single-arm designs
  • define primary and secondary endpoints, estimands, eligibility criteria, or subgroup analyses
  • select the right reporting guideline such as CONSORT, STROBE, PRISMA, STARD, TRIPOD, SPIRIT, or CARE
  • draft protocol, SAP, CSR, or evidence-summary outlines
  • review bias, confounding, missing data, and sample-size assumptions
  • prepare trial or real-world-evidence summaries for drug-discovery programs

Working Rules

  1. Keep the task at the study or cohort level.
  2. Separate confirmed study facts from proposed design choices.
  3. State assumptions behind endpoint, power, and statistical-model choices.
  4. Call out data leakage, immortal-time bias, selection bias, and confounding whenever relevant.
  5. Do not present DrugClaw as giving medical advice, treatment recommendations, or diagnostic decisions.

Study Design Map

Use this quick routing:

  • RCT: intervention efficacy, causal inference, registration-ready protocols
  • Prospective cohort: prognosis, exposure-outcome tracking, real-world evidence
  • Retrospective cohort: registry or EHR analyses with explicit confounding control
  • Case-control: rare outcomes or exploratory risk-factor work
  • Cross-sectional: prevalence, survey snapshots, baseline association work
  • Diagnostic accuracy: sensitivity, specificity, ROC, calibration, decision curves
  • Prediction model: risk scores, survival models, treatment-response models with external validation plans

Reporting Guideline Map

Choose and state the governing framework early:

  • CONSORT: randomized trials
  • SPIRIT: trial protocols
  • STROBE: observational studies
  • PRISMA: systematic reviews and meta-analysis
  • STARD: diagnostic accuracy studies
  • TRIPOD: prediction models
  • CARE: case reports
  • ICH E3: clinical study reports

Protocol Workflow

Read the full file on GitHub · 98 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. 13d ago First seen · 98 lines · 74 tokens per session scan A 7029fa57e841

Subscribe to this mod's changes

clinical-research-tools is a skill published in the GitHub repository DrugClaw/DrugClaw (125 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 945 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.