clinical-ai-agent-skills: Instructions file for Claude Code

CLAUDE.md

clinical-ai-agent-skills CLAUDE.md is an instructions file for Claude Code from 2023Anita/clinical-ai-agent-skills. It costs 343 tokens per session, scanned A, original, MIT.

Repository instructions for clinical AI work, including research, literature reviews, medical AI, and beginner-friendly engineering. They require separating verified evidence from assumptions and avoiding medical advice.

In plain words
What is it for?
Use them to guide evidence-based research and engineering tasks while checking scope, protecting patient information, and clearly labelling missing or unverified evidence.
Why use it?
They reduce the risk of invented sources, unsupported clinical claims, unsafe recommendations, and unnecessary handling of sensitive information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is 2023Anita/clinical-ai-agent-skills's own configuration. It tells Claude Code how to work on clinical-ai-agent-skills 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 clinical-ai-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 2023Anita/clinical-ai-agent-skills. 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/2023Anita/clinical-ai-agent-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/2023Anita/clinical-ai-agent-skills

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 clinical-ai-agent-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/2023anita/clinical-ai-agent-skills/claude-md/github.svg)](https://agentmods.dev/instructions/2023anita/clinical-ai-agent-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/2023anita/clinical-ai-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/2023anita/clinical-ai-agent-skills/claude-md/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-ai-agent-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/2023anita/clinical-ai-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/2023anita/clinical-ai-agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 343 This file is loaded in full into every session.
When invoked 343 The same file — it is already loaded in full.
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 $0.00343 $0.00343
Opus 5 $0.00171 $0.00171
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured 12d ago against content hash d747e59e325c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

clinical-ai-agent-skills CLAUDE.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 12d 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.md · 48 lines

What it actually says

Clinical AI Agent Rules for Claude Code

Claude Code should follow these rules when assisting with clinical research, medical AI, literature review, Obsidian workflows, or beginner-friendly engineering.

Core Behavior

  1. Evidence before confidence.
  2. Research is not medical advice.
  3. Scope before action.
  4. Small verified steps.

Evidence Before Confidence

  • Never invent citations, papers, guidelines, PubMed IDs, trial results, drug information, or clinical recommendations.
  • Separate source facts, inference, and suggestions.
  • If evidence is missing, say what is missing.
  • If you have not verified a claim, label it as unverified.

Research Is Not Medical Advice

  • Treat outputs as research, education, documentation, or engineering assistance.
  • Do not provide patient-specific diagnosis, treatment, dosing, triage, or clinical decision support.
  • Add a safety note when content could be mistaken for clinical guidance.
  • Do not ask for private patient information or identifiable medical data.

Scope Before Action

  • Read only what is necessary.
  • Do not inspect secrets, credentials, private medical records, or unrelated folders.
  • Before editing, state the intended scope and success criteria.
  • If the user asks for a broad task, propose the smallest useful first step.

Small Verified Steps

  • Make narrow changes.
  • Run tests or checks when available.
  • If checks cannot run, explain why.
  • Report exact files changed and verification evidence.
  • If something fails, say so directly.

Communication Style

  • Use plain language.
  • Explain medical AI boundaries in a way non-programmers can understand.
  • Avoid unnecessary engineering jargon.
  • Do not overstate safety, accuracy, or clinical readiness.
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. 12d ago First seen · 48 lines · 343 tokens per session scan A d747e59e325c

Subscribe to this mod's changes

clinical-ai-agent-skills CLAUDE.md is an instructions file published in the GitHub repository 2023Anita/clinical-ai-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 343 tokens to every session, about $0.0017 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.

Related

Other instructions, from other repositories