medsci-skills: Instructions file for Claude Code

CLAUDE.md

medsci-skills CLAUDE.md is an instructions file for Claude Code from Aperivue/medsci-skills. It costs 508 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on Aperivue’s medsci-skills repository, which handles published medical-science papers.

In plain words
What is it for?
Use it when changing or testing the repository’s paper-detection tools and deciding which files, scans, or results may be used as evidence.
Why use it?
It protects a reserved collection of papers used for unbiased testing, so development work does not accidentally contaminate those results.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Aperivue/medsci-skills's own configuration. It tells Claude Code how to work on medsci-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 medsci-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Aperivue/medsci-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/Aperivue/medsci-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Aperivue/medsci-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 medsci-skills CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aperivue/medsci-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/aperivue/medsci-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 508 This file is loaded in full into every session.
When invoked 508 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 $0.00508 $0.00508
Opus 5 $0.00254 $0.00254
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 9d ago against content hash 2684675c960a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

medsci-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 9d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in this repository

_corpus/heldout/ — do not read, do not run anything against it

This is the one instruction in this file that cannot be recovered from if you get it wrong.

_corpus/heldout/ holds a frozen set of real published papers whose entire purpose is to be material no detector was written knowing about. Its protocol (reverse_engineer/HELDOUT.md) states the spend rule directly:

set role spent by
challenge-card fixtures train authored with the detector
the current corpus validation acting on a fire
a fresh frozen corpus test — one unbiased number reading it

Reading is not a neutral act here. A fire rate measured on these papers asserts "no detector was written knowing this paper"; reading one in order to author or justify a change is exactly how a detector comes to know it. The protocol's own instruction is "Never open them again except to label a fire."

So, when working anywhere in this repository:

  • Do not open _corpus/heldout/*.md.
  • Do not run a detector, a grep, or a scan across _corpus/.
  • Do not cite a number derived from it as evidence for changing a detector.
  • If a task seems to require it, stop and ask. It almost certainly does not.

_corpus/ is gitignored, so git status will never show a change there and a clone will not carry it. Neither fact protects it: anything scanning the working tree sees it. That is not hypothetical — on 2026-07-31 an audit was launched against "the repository", three of its agents reached _corpus/heldout/, and one ran a detector across the corpus and opened two of the papers. The finding it produced was quarantined and not acted on, and the corpus in place was already spent, so nothing measurable was lost. The next corpus is the one that reading destroys, and this file exists because the fence was in a prompt instead of in the repository.

Everything else

CONTRIBUTING.md is the entry point: how to run the gate mirror before pushing, the worktree discipline, and what a change is expected to ship with.

Read the full file on GitHub · 41 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. 9d ago First seen · 41 lines · 508 tokens per session scan A 2684675c960a

Subscribe to this mod's changes

medsci-skills CLAUDE.md is an instructions file published in the GitHub repository Aperivue/medsci-skills (290 stars, last pushed 2d ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 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 instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens