awesome-ai-scientists AGENTS.md

Repository instructions for maintaining a catalogue of resources for AI Scientist systems—software that helps with scientific research. They define how agents should understand the repository, its categories, contribution process, and trust boundaries.

In plain words
What is it for?
Use them when adding or updating catalogue entries, choosing categories, checking contribution rules, or working on the repository’s website and documentation.
Why use it?
They reduce inconsistent edits by pointing contributors to the repository’s source-of-truth files and required workflow before changes are made.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/natnew/awesome-ai-scientists/agents-md
Clone the repo
git clone --depth 1 https://github.com/natnew/awesome-ai-scientists

Made for: Codex, OpenCode.

Per session 2,529 This file is loaded in full into every session.
When invoked 2,529 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02529 $0.02529
Opus 5 $0.01264 $0.01264
Sonnet 5 $0.00506 $0.00506
Haiku 4.5 $0.00253 $0.00253

Measured yesterday against content hash 336f2f7f5963, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

awesome-ai-scientists 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 yesterday.

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.

AGENTS.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Operating Protocol for AI Agents

Tool-agnostic working rules for any AI coding agent (Claude Code, Codex, Cursor, Copilot, Gemini, Aider, and similar) operating in this repository. Follow repository-local guidance over generic awesome-list assumptions.

Start here

Read in this order before acting. Stop at the first file that answers your question; load the rest on demand.

  1. This file — operating protocol, trust boundary, stop conditions.
  2. README.md — scope, sections, the index entry format.
  3. website/docs/workflows.md, domains.md, resource-types.md — canonical taxonomy slugs (source of truth).
  4. CONTRIBUTING.md — issue-first workflow and the contributor checklist.
  5. .github/ISSUE_TEMPLATE/*, .github/pull_request_template.md — contributor expectations.
  6. MAINTAINERS.md, recent issues / PRs — precedent and cadence.
  7. CLAUDE.md — Claude-specific resolver, output templates, command discipline.

Repository North Star

A curated catalogue of resources for building AI Scientist systems — AI that assists scientific discovery across literature intelligence, hypothesis generation, experiment planning, tool use, evaluation, and scientific communication. README.md is the primary human-facing index; the Docusaurus site under website/ is its navigable, tagged surface. Keep the list selective, durable, technically useful, and easy to navigate. Curation matters more than accumulation: each entry should help a reader understand the landscape, not merely add a link.

Two surfaces, two formats

The same catalogue is published in two places. Infer the format from the file you are editing — never impose one surface's format on the other.

Surface Files Entry format
Index README.md - [Name](url) - one sentence. Hyphen separator, no taxonomy tags.
Site website/docs/*.md - [Name](url) — one sentence. \lifecycle:slug` `domain:slug` `type:slug`` Em-dash separator, three backticked tags required.

Read the full file on GitHub · 163 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. yesterday First seen · 163 lines · 2,529 tokens per session scan A 336f2f7f5963

Subscribe to this mod's changes

awesome-ai-scientists AGENTS.md is an instructions file published in the GitHub repository natnew/awesome-ai-scientists (18 stars, last pushed 27d ago), licensed MIT. It adds 2,529 tokens to every session, about $0.0126 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.