Home / pku-yuangroup / openai4s · AGENTS.md · GitHub

AGENTS.md agentsB

Name: AGENTS.md
Author: pku-yuangroup

This file is byte-identical to the first copy the registry indexed, one of 47 copies on public GitHub. Same content hash, same audit grade.

AGENTS.md is agent-read markdown (agents) from pku-yuangroup/openai4s.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

CLAUDE.md

Read the whole file at its exact version.

How to install

Latest version

mdr add pku-yuangroup/openai4s/AGENTS.md@git:20260706.f0fd27c

Exact content

mdr add pku-yuangroup/openai4s/AGENTS.md@sha256:6ebdb617a8104a77

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

[![mdr](https://markdownregistry.com/badge/art_ei7g5edzvmwzorb4.svg)](https://markdownregistry.com/a/art_ei7g5edzvmwzorb4)

1 badge views in 30 days

Versions

version	committed	commit	size	audit
git:20260706.f0fd27c latest	2026-07-06	f0fd27c	9 B	B	view

Audit of the latest version

B 13 of 14 checks passed. Deterministic, no model, same answer every run.

fail: Size between 200 bytes and 200 KB (9 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

pku-yuangroup/openai4s · 586 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ei7g5edzvmwzorb4
GET https://markdownregistry.com/api/v1/resolve?ref=pku-yuangroup/openai4s/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/6ebdb617a8104a7756d0cf36578ab01103dc9f07e4dc6feb751296b9c402faf7

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from pku-yuangroup/openai4s

CLAUDE.md claude

pku-yuangroup/openai4s · CLAUDE.md

git:20260916.bb0d860 · audit B · 586 stars

admet_genetic skill

pku-yuangroup/openai4s · skills/admet_genetic/SKILL.md · ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an…

git:20260828.e9753be · audit A · 586 stars

alphafold2 skill

pku-yuangroup/openai4s · skills/alphafold2/SKILL.md · Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022…

git:20260828.e9753be · audit A · 586 stars

audit-dataset skill

pku-yuangroup/openai4s · skills/audit-dataset/SKILL.md · Audit tabular datasets before analysis or training for schema drift, missing values, duplicate rows or IDs, target…

git:20260828.e9753be · audit A · 586 stars

bioprobench skill

pku-yuangroup/openai4s · skills/bioprobench/SKILL.md · Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection…

git:20260828.e9753be · audit A · 586 stars

bio-alignment-io skill

pku-yuangroup/openai4s · skills/bioskills/bio-alignment-alignment-io/SKILL.md · Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO. Supports Clustal, PHYLIP…