environment

A set of project rules for coding on Windows, including which shells, script formats, line endings, and tools to use.

In plain words
What is it for?
Writing PowerShell helpers, keeping text files consistent across computers, using platform-neutral paths, and working with Git, Python, Node.js, Docker, and related tools.
Why use it?
It prevents agents from assuming a Unix-like system and producing scripts or file paths that do not work in the project.

Cursor rule for Codex

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 rules/ralfhuesing/computetoai/environment
Clone the repo
git clone --depth 1 https://github.com/RalfHuesing/ComputeToAi

Made for: Codex.

Per session 621 This file is loaded in full into every session.
When invoked 621 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 $0.00621 $0.00621
Opus 5 $0.00311 $0.00311
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured yesterday against content hash 5b7f16fc9cae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

environment 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 yesterday.

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/rules/environment.mdc · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Entwicklungsumgebung

Entwickelt wird auf Windows. Konkret bedeutet das:

  • Keine Bash als gegeben annehmen. Automatisierungs-/Hilfsskripte werden als PowerShell (.ps1) geschrieben, nicht als .sh. Ein Agent mit Bash-Zugriff darf Bash interaktiv nutzen, aber committete Skripte im Repo sind PowerShell.
  • Zeilenenden: .gitattributes im Repo-Root erzwingt eol=lf für Text-/Codedateien, unabhängig von der lokalen core.autocrlf-Einstellung des jeweiligen Rechners/Agenten. Neue Dateitypen, die spezielle Zeilenenden brauchen, werden dort ergänzt statt sich auf implizite Defaults zu verlassen.
  • Pfade in Doku/Skripten möglichst plattformneutral halten (pathlib in Python statt String-Konkatenation mit \).

Verfügbare Tools (Stand: 2026-07-18, geprüft in dieser Umgebung)

Tool Version Zweck
git 2.38.1 Versionskontrolle
PowerShell (pwsh) 7.6.3 primäre Shell
ripgrep (rg) 15.1.0 Codesuche
Python 3.13.14 Implementierungssprache (siehe Docs/02-Architektur-und-MCP.md)
Node.js 24.15.0 für Tooling/MCP-Clients bei Bedarf
GitHub CLI (gh) 2.92.0 PR-/Issue-Interaktion
Docker 28.4.0 bei Bedarf für isolierte Ausführung
winget 1.29.280 Paketinstallation unter Windows
uv 0.11.29 Paket-/Dependency-/Environment-Verwaltung (siehe Docs/11-Code-Standards-und-Projektstruktur.md)
ruff 0.15.22 Linting & Formatierung
pyright 1.1.411 Typprüfung

uv, ruff, pyright sind aktuell global installiert (Stand: 2026-07-18), damit sie in dieser Umgebung sofort nutzbar sind. Sobald in Meilenstein 1 (Docs/10-Roadmap.md, Epic 1.1) ein pyproject.toml entsteht, werden ruff und pyright zusätzlich als Dev-Dependencies dort eingetragen (uv add --dev ruff pyright), damit jede Umgebung, die das Repo klont, exakt dieselben Versionen bekommt – die globale Installation ist dann nur noch die Fallback-/Editor-Integration. pytest kommt ebenfalls erst als Dev-Dependency über uv, sobald das Projekt existiert.

Read the full file on GitHub · 31 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. yesterday First seen · 31 lines · 621 tokens per session scan A 5b7f16fc9cae

Subscribe to this mod's changes

environment is a cursor rule published in the GitHub repository RalfHuesing/ComputeToAi (0 stars, last pushed 1mo ago), licensed MIT. It adds 621 tokens to every session, about $0.0031 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 2026-08-31.