satus AGENTS.md

The main engineering rulebook for a Satus web application built with Next.js, React, TypeScript, Tailwind CSS, and Bun. It includes rules that automated checks enforce before code can pass.

In plain words
What is it for?
It helps agents understand the application stack, use the required tools, follow TypeScript and styling rules, and avoid changing managed documentation blocks that the development tools control.
Why use it?
It gives coding agents one reliable source for the project's technology choices and restrictions. Following it helps avoid changes that fail continuous integration, the automated build and test checks run for proposed code.

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/darkroomengineering/satus/agents-md
Clone the repo
git clone --depth 1 https://github.com/darkroomengineering/satus

Made for: Codex, OpenCode.

Per session 6,160 This file is loaded in full into every session.
When invoked 6,160 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 $0.06160 $0.06160
Opus 5 $0.03080 $0.03080
Sonnet 5 $0.01232 $0.01232
Haiku 4.5 $0.00616 $0.00616

Measured 2d ago against content hash 0c8e6e2b66fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

satus 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 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.

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 · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Satus Engineering Standards

This is the single source of truth for engineering standards in this repo. Claude Code, Cursor, and all other AI tools read this file. The other docs (CLAUDE.md, .cursor/rules/) are thin pointers back here.

This file changes only by deliberate review. next dev appends a managed block here (an HTML comment fencing nextjs-agent-rules) when it detects an AI coding agent; there is no config opt-out. Revert that block on sight, never commit it. This sentence must never contain the block's literal opening marker: Next locates the block by searching for that exact string, and a prose match makes the next next dev run truncate everything below it.


Stack

Layer Technology
Framework Next.js 16 (App Router, Cache Components, proxy.ts)
UI React 19.2 (React Compiler ON, no manual memoization)
Language TypeScript 7, strict: true
Styling Tailwind v4 (CSS-first) + CSS Modules
Runtime Bun
Linter / Formatter oxlint + oxfmt
Validation Zod
Animation Lenis, GSAP, Tempus
3D (optional) React Three Fiber, @react-three/drei

Enforced Rules (CI fails without these)

These are non-negotiable. Each is enforced by oxlint or TypeScript; bun run check and CI fail on violation; the pre-commit hook runs oxlint and tsc, and the two type-aware rules run only in lint:types, check, and CI (next build does not typecheck: ignoreBuildErrors is on).

oxlint rules

Rule What it catches Enforcer
typescript/no-explicit-any any types oxlint typescript
typescript/consistent-type-imports Missing import type for type-only imports oxlint typescript (.ts/.tsx)
typescript/consistent-type-exports Missing export type for type-only re-exports oxlint typescript, type-aware
nextjs/no-img-element Raw <img> tags (use @/components/ui/image) oxlint nextjs
react/forbid-elements Raw <a> tags (use @/components/ui/link) oxlint react
eslint/no-restricted-imports ../../ deep relative imports (use @/ aliases) and forwardRef imports (React 19 ref-as-prop) oxlint eslint
eslint/no-unused-vars Unused imports, variables and parameters oxlint eslint
react/jsx-key Missing key in list renders oxlint react (.tsx/.jsx)
jsx-a11y/alt-text Missing alt on images (incl. next/image) oxlint jsx-a11y
react/button-has-type <button> missing type attribute oxlint react
react/no-danger-with-children XSS risk oxlint react
import/first Imports not at top of file oxlint import
react/rules-of-hooks Hooks called conditionally / outside components oxlint react
typescript/no-floating-promises Un-awaited promises oxlint typescript, type-aware
typescript/no-misused-promises Async function passed where void expected oxlint typescript, type-aware

Read the full file on GitHub · 378 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. 2d ago First seen · 378 lines · 6,160 tokens per session scan A 0c8e6e2b66fe

Subscribe to this mod's changes

satus AGENTS.md is an instructions file published in the GitHub repository darkroomengineering/satus (982 stars, last pushed 4d ago), licensed MIT. It adds 6,160 tokens to every session, about $0.0308 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.