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.
curl -O https://raw.githubusercontent.com/2023Anita/clinical-ai-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/2023Anita/clinical-ai-agent-skillsWrote 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/instructions/2023anita/clinical-ai-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/2023anita/clinical-ai-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/2023anita/clinical-ai-agent-skills/agents-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.
<a href="https://agentmods.dev/instructions/2023anita/clinical-ai-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/2023anita/clinical-ai-agent-skills/agents-md.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 | $0.00467 | $0.00467 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
clinical-ai-agent-skills AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical AI Agent Rules
Use these rules when working on clinical research, medical AI, literature review, Obsidian knowledge workflows, or beginner-friendly engineering tasks.
1. Evidence Before Confidence
- Do not 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 evidence is missing.
- When using external sources, name the source and distinguish direct evidence from interpretation.
- If a claim could affect health decisions, mark it as requiring human clinical review.
2. 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 the user to paste private patient data, hospital records, credentials, or identifiable medical information.
3. Scope Before Action
- Read only the files needed for the task.
- Do not access private medical records, credentials, secrets, or unrelated folders.
- Before editing, state the intended scope and success criteria.
- If the task is ambiguous, ask a focused clarification before making changes.
- Do not broaden the task into unrelated cleanup, refactoring, publishing, or automation.
4. Small Verified Steps
- Prefer small changes with visible verification.
- For code, run tests or explain why tests cannot run.
- For research, cite real source names or mark claims as unverified.
- For files, summarize what changed and which files were touched.
- If verification fails, report the actual failure instead of claiming success.
Clinical Safety Defaults
- Use plain language so clinicians can inspect the output.
- Avoid unsupported certainty. Prefer "the available evidence suggests" only when evidence is actually available.
- Keep medical uncertainty visible.
- Do not convert population-level research into patient-level advice.
- Do not handle emergency, urgent, or patient-specific scenarios as an AI agent task.
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.
- 12d ago First seen · 52 lines · 467 tokens per session scan A 80cef2e69518
clinical-ai-agent-skills AGENTS.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 467 tokens to every session, about $0.0023 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).