atom CLAUDE.md

An instruction set for the Atom project, described as an AI-powered business-automation platform. It covers project decisions, architecture, and a rule not to commit changes.

In plain words
What is it for?
Working on the Atom codebase while following its architecture guidance, decision standards, and no-commit rule.
Why use it?
It gives an agent project-specific boundaries and background before it fixes or designs anything.

Instructions file

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/rush86999/atom/claude-md
Clone the repo
git clone --depth 1 https://github.com/rush86999/atom
Per session 18,447 This file is loaded in full into every session.
When invoked 18,447 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
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 $0.18447 $0.18447
Opus 5 $0.09224 $0.09224
Sonnet 5 $0.03689 $0.03689
Haiku 4.5 $0.01845 $0.01845

Measured 2d ago against content hash 98dbf11020e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

atom CLAUDE.md scanned grade B with 2 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 2d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST "/api/v1/graph/search/local" -d '{"query": "Project Alpha", "depth": 2}'

Makes network callslowCapability

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

curl -X POST http://localhost:8000/api/auth/login -H "Content-Type: application/json" \
CLAUDE.md · 503 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. 2d ago First seen · 503 lines · 18,447 tokens per session scan B 98dbf11020e3

Subscribe to this mod's changes

atom CLAUDE.md is an instructions file published in the GitHub repository rush86999/atom (878 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 18,447 tokens to every session, about $0.0922 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.