AtomisticSkills: Instructions file for Claude Code

CLAUDE.md

AtomisticSkills CLAUDE.md is an instructions file for Claude Code from learningmatter-mit/AtomisticSkills. It costs 820 tokens per session, scanned A, original, MIT.

A set of instructions for using Claude Code with the AtomisticSkills research framework. It links to project rules and explains the framework's tools, skills, and workflows.

In plain words
What is it for?
Use it as the main guidance file when Claude Code is working on AtomisticSkills projects involving atomistic simulations or machine-learning research.
Why use it?
It gives Claude Code the project context needed to follow the repository's research, coding, and environment conventions. This reduces guesswork when running or extending research tasks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is learningmatter-mit/AtomisticSkills's own configuration. It tells Claude Code how to work on AtomisticSkills 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 AtomisticSkills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to learningmatter-mit/AtomisticSkills. 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/learningmatter-mit/AtomisticSkills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills

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 AtomisticSkills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/learningmatter-mit/atomisticskills/claude-md.svg)](https://agentmods.dev/instructions/learningmatter-mit/atomisticskills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/learningmatter-mit/atomisticskills/claude-md"><img src="https://agentmods.dev/badge/instructions/learningmatter-mit/atomisticskills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 820 This file is loaded in full into every session.
When invoked 820 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 $0.00820 $0.00820
Opus 5 $0.00410 $0.00410
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 3d ago against content hash 0e380696e77e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

AtomisticSkills 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 3d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AtomisticSkills Agent Instructions

You are an atomistic research agent with access to literature, Skills, and MCP tools.

Project Rules

Read these rules files at the start of every conversation (imported below via @):

  • .agents/rules/research-standards.md — research protocol, intent classification, plan workflow
  • .agents/rules/coding-standards.md — coding rules, environment management, MCP stability
  • .agents/rules/mcp-environments.md — conda environment to MCP server mapping

@.agents/rules/coding-standards.md @.agents/rules/mcp-environments.md @.agents/rules/research-standards.md

Read these on demand when the task requires it:

  • .agents/rules/skill-standards.md — for creating or editing a skill
  • .agents/rules/workflow-standards.md — for creating or editing a workflow
  • .agents/rules/plot-standards.md — for creating or editing a plotting script
  • .agents/rules/release-standards.md — for preparing a release tag

Framework Overview

This project decomposes complex research tasks into three levels:

  • Tools (src/mcp_server/): Low-level operations exposed via MCP (relax structure, run MD, query databases). Strict typed I/O.
  • Skills (.agents/skills/): Mid-level tutorials combining tools and scripts to solve focused tasks. Each has a SKILL.md with step-by-step instructions.
  • Workflows (.agents/workflows/): High-level research campaigns that chain multiple skills.

When a user asks a research question, check workflows first for end-to-end protocols, then find the relevant skill(s).

Skill Discovery

Skills are at .agents/skills/. In Claude Code they are registered as native project skills, so each one is listed by name and description and can be invoked directly with the Skill tool — no searching needed.

If the skills are not listed, they have not been configured yet. Run:

python configure_mcp.py --agent claude

This symlinks every .agents/skills/<name> into .claude/skills/<name>, which Claude Code discovers automatically. .claude/ is gitignored, so this is a per-checkout setup step; re-run it after cloning or after a skill is added or removed. .agents/skills/ stays the single source of truth — the symlinks are never copies.

Read the full file on GitHub · 90 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. 3d ago First seen · 90 lines · 820 tokens per session scan A 0e380696e77e

Subscribe to this mod's changes

AtomisticSkills CLAUDE.md is an instructions file published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 820 tokens to every session, about $0.0041 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 2026-09-03.

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 · 5,182 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

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.

github/spec-kit · 7,104 tokens