atlas: Instructions file for Claude Code

CLAUDE.md

atlas CLAUDE.md is an instructions file for Claude Code from AtlasDevHQ/atlas. It costs 5,345 tokens per session, scanned A, original, AGPL-3.0.

Repository instructions for Claude Code in the AtlasDevHQ/atlas project. They describe required practices, error handling, types, style, and product rules.

In plain words
What is it for?
They help guide code changes, error handling, type usage, formatting, and checks for product requirements.
Why use it?
They give Claude Code the project-specific constraints needed to make changes that fit the existing code and preserve important behavior.

Instructions file for Claude Code

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

This is AtlasDevHQ/atlas's own configuration. It tells Claude Code how to work on atlas 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 atlas configures →

Reuse

Borrowing it

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

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 atlas CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/atlasdevhq/atlas/claude-md"><img src="https://agentmods.dev/badge/instructions/atlasdevhq/atlas/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,345 This file is loaded in full into every session.
When invoked 5,345 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 unknown 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 $0.05345 $0.05345
Opus 5.5 $0.02138 $0.02138
Sonnet 5.5 $0.01069 $0.01069
Haiku 4.5 $0.00534 $0.00534

Measured 1mo ago against content hash 12bb44567095, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atlas 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 1mo 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 · 183 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 1mo ago Changed · -47 tokens per session 12bb44567095
  2. 2mo ago Changed · +4 lines · +110 tokens per session 22525e5a1cff
  3. 2mo ago Changed · +2 lines · +176 tokens per session afa3564b944b
  4. 2mo ago First seen · 177 lines · 5,106 tokens per session scan A c5f50f61f50f

Subscribe to this mod's changes

atlas CLAUDE.md is an instructions file published in the GitHub repository AtlasDevHQ/atlas (1 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 5,345 tokens to every session, about $0.0214 per session on Opus 5.5. 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 2026-08-31.

Related

atlas CLAUDE.md compared with instructions from other repositories

atlas CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
atlas CLAUDE.mdAtlasDevHQ/atlasInstructions file11mo agoAGPL-3.0A5,345Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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