What is nosia AGENTS.md?

A project guide for an AI coding assistant working on a specific Ruby on Rails application. It records the app’s technology choices, code structure, design principles, and common commands.

Following the app’s Rails conventions, choosing the right testing and authentication approach, understanding where code belongs, and using the documented development and deployment commands.

It gives the assistant the project’s rules in one place, reducing guesses and changes that conflict with the existing codebase.

How dilolabs/nosia configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to dilolabs/nosia. 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/dilolabs/nosia/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dilolabs/nosia

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dilolabs/nosia/agents-md/github.svg)](https://agentmods.dev/instructions/dilolabs/nosia/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dilolabs/nosia/agents-md"><img src="https://agentmods.dev/badge/instructions/dilolabs/nosia/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dilolabs/nosia/agents-md"><img src="https://agentmods.dev/badge/instructions/dilolabs/nosia/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,549 This file is loaded in full into every session.

When invoked 7,549 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.

Model	Per session	Once invoked
Fable 5.1	$0.07549	$0.07549
Opus 5.5	$0.03020	$0.03020
Sonnet 5.5	$0.01510	$0.01510
Haiku 4.5	$0.00755	$0.00755

Measured 2mo ago against content hash 06059c86c0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nosia 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 2mo 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.

AGENTS.md · 940 lines

How it starts

The opening of the file, as written. The whole thing — 940 lines — stays where its author put it; the contents beside it link to each section on GitHub.

37signals Rails Configuration

Tech Stack

Ruby 3.3, Rails 8.2 (edge), MySQL (SaaS) / SQLite (OSS)
Frontend: Hotwire (Turbo 8 + Stimulus 3.2), Importmap (no Node.js)
Testing: Minitest + Fixtures (not RSpec, not FactoryBot)
Auth: Custom passwordless: passkeys (WebAuthn) + magic links (no Devise), has_secure_password optional
Background Jobs: Solid Queue (database-backed, no Redis)
Caching: Solid Cache | WebSockets: Solid Cable
IDs: UUIDv7 everywhere (base36-encoded, 25-char strings)
Assets: Propshaft + Import Maps (no Node.js, no Webpack)
Deployment: Kamal 2 + Thruster

Architecture

app/
  controllers/     # Thin. Only 7 REST actions. New resource for each state change.
  models/          # Rich. Business logic, concerns, associations, validations.
  models/concerns/ # Horizontal behavior: Closeable, Assignable, Searchable.
  views/           # ERB + Turbo Frames/Streams. No JS frameworks.
  jobs/            # Shallow. Call model methods, don't contain logic.
  mailers/         # Minimal. Bundle notifications, plain-text first.
  channels/        # ActionCable channels for real-time.

No app/services/, app/queries/, app/policies/, app/forms/ directories. Business logic lives in models. Authorization via roles on User model + controller concerns. Complex forms use standard Rails nested attributes.

Core Philosophy

Vanilla Rails: Rich domain models, thin controllers, avoid service objects (acceptable when justified, but not as default architecture), no Devise, no Pundit
Everything is CRUD: State changes = new resources (Closure, Publication, Archival)
State as records: No boolean flags for business state -- use has_one state records
Rich models over services: Business logic lives in models, organized via concerns
Concerns for organization: Models compose behavior via focused concerns (Closeable, Assignable)
No foreign key constraints: Application enforces referential integrity
Multi-tenancy: URL path-based (/:account_id/...), account_id on every table
Current for context: Current.user, Current.account, Current.session
Shallow jobs: _later/_now pattern; job calls model method, logic stays in model

Read the full file on GitHub · 940 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.

2mo ago First seen · 940 lines · 7,549 tokens per session scan A 06059c86c0a3

Subscribe to this mod's changes

nosia AGENTS.md is an instructions file published in the GitHub repository dilolabs/nosia (211 stars, last pushed 3d ago), licensed MIT. It adds 7,549 tokens to every session, about $0.0302 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 2026-08-30.

Backend and APIs LLM Languages RAG and vectors Ruby ai all-in-one docker

nosia AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nosia AGENTS.mddilolabs/nosia	Instructions file	211	3d ago	MIT	A	7,549	Codex, OpenCode
graftcode graftcode-ruby.instructions.mdgrft-dev/graftcode	Instructions file	967	1mo ago	none	A	4,609	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

nosia: Instructions file for Codex