agentmods.dev

OpenAI4S: Instructions file for Claude Code

CLAUDE.md

OpenAI4S CLAUDE.md is an instructions file for Claude Code from PKU-YuanGroup/OpenAI4S. It costs 8,225 tokens per session, scanned A, original, MIT.

A set of shared instructions for CLAUDE.md and AGENTS.md files, which give coding agents guidance about a project. It documents the OpenAI4S research agent, its commands, architecture, and repository conventions.

In plain words
What is it for?
Use it when working on OpenAI4S, especially when setting it up, changing its Python or R execution environments, or following its platform-neutral project guidance.
Why use it?
It gives agents and developers one place to find project rules and understand where important parts of the code live. This reduces confusion when changing the repository.

Instructions file for Claude Code

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

This is PKU-YuanGroup/OpenAI4S's own configuration. It tells Claude Code how to work on OpenAI4S 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 OpenAI4S configures →

not rated 662repo +5 changed 14d ago A scan 8,225 tokens original MIT
View source ↗ PKU-YuanGroup/OpenAI4S arxiv.org
Reuse

Borrowing it

Nothing to install: this file belongs to PKU-YuanGroup/OpenAI4S. 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/PKU-YuanGroup/OpenAI4S/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S

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 OpenAI4S CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pku-yuangroup/openai4s/claude-md/github.svg)](https://agentmods.dev/instructions/pku-yuangroup/openai4s/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pku-yuangroup/openai4s/claude-md"><img src="https://agentmods.dev/badge/instructions/pku-yuangroup/openai4s/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 OpenAI4S CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pku-yuangroup/openai4s/claude-md"><img src="https://agentmods.dev/badge/instructions/pku-yuangroup/openai4s/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,225 This file is loaded in full into every session.
When invoked 8,225 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.08225 $0.08225
Opus 5.5 $0.03290 $0.03290
Sonnet 5.5 $0.01645 $0.01645
Haiku 4.5 $0.00822 $0.00822

Measured 14d ago against content hash c8a06a5d3246, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OpenAI4S CLAUDE.md scanned grade A with 1 finding 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 14d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Core is zero-dependency by design.** The engine, the LLM client (over `urllib`), and the web server (`http.server` + a hand-rolled WebSocket) use only the Python standard library. This is a hard constraint — see conven
CLAUDE.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md / AGENTS.md

This file provides shared guidance to both Claude Code (CLAUDE.md) and Codex (AGENTS.md, symlinked to this file) when working with code in this repository.

Keep future guidance platform-neutral unless a section explicitly calls out a Claude Code- or Codex-specific workflow.

What this is

OpenAI4S is a pure-stdlib hybrid scientific research agent: provider-native JSON Tool calls form the orchestration/permission control plane, while persistent Python/R Code-as-Action kernels form the scientific execution plane. Python can call the in-kernel host singleton synchronously mid-cell; R is an independent analysis channel.

Core is zero-dependency by design. The engine, the LLM client (over urllib), and the web server (http.server + a hand-rolled WebSocket) use only the Python standard library. This is a hard constraint — see conventions below.

Commands

./setup.sh                          # one-time: locked lightweight .venv + pre-commit hook
./setup.sh --with-kernel-envs       # also create comprehensive Python + R envs
./setup.sh --update-kernel-envs     # sync existing Python + R envs, without pruning
./start.sh                          # launch daemon + web UI at http://127.0.0.1:8760/
uv run pytest                       # full offline test suite (LLM is mocked — no network, no keys)
uv run pytest -n auto --maxprocesses=4 --dist loadfile   # the same suite, the way CI runs it (~7min vs ~20min)
uv run pytest tests/test_agent.py::test_max_turns_stop   # a single test
uv run pytest tests/test_kernel.py -k background         # tests matching a pattern
uv run mypy                         # strict agent/Host + orchestration contracts
uv run pre-commit run --all-files   # format + lint + mypy (black · isort --profile black · ruff)
uv run openai4s run "…" -v          # run one Code-as-Action task in-process, no daemon
openai4s setup --profile standard   # build Python + R from envs/*.yml
openai4s setup                      # build all 4 envs (--dry-run to preview)

Read the full file on GitHub · 201 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. 14d ago Changed c8a06a5d3246
  2. 20d ago Changed 404d7a818d07
  3. 25d ago Changed · +64 lines · +565 tokens per session 0e2b3947f2fb
  4. 1mo ago Changed · +5 tokens per session 82b16a919a0e
  5. 1mo ago Changed · +66 tokens per session 161e29eff23c
  6. 1mo ago Changed 3d4e6036932d
  7. 1mo ago Changed · +64 tokens per session 5e23e0bf4c9e
  8. 2mo ago Changed · +1 lines · +22 tokens per session d1c96665990b
  9. 2mo ago Changed · +6 lines · +456 tokens per session f6419c38c495
  10. 2mo ago First seen · 130 lines · 7,047 tokens per session scan A 0e9159dbe31f

Subscribe to this mod's changes

OpenAI4S CLAUDE.md is an instructions file published in the GitHub repository PKU-YuanGroup/OpenAI4S (662 stars, last pushed 3d ago), licensed MIT. It adds 8,225 tokens to every session, about $0.0329 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agentai4scienceclaude-sciencemit-licenseopen-sourcescience-research
Related

OpenAI4S CLAUDE.md compared with instructions from other repositories

OpenAI4S CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
OpenAI4S CLAUDE.mdPKU-YuanGroup/OpenAI4SInstructions file6623d agoMITA8,225Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode