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.
git clone --depth 1 https://github.com/RalfHuesing/ComputeToAiWrote 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.
[](https://agentmods.dev/rules/ralfhuesing/computetoai/environment)<a href="https://agentmods.dev/rules/ralfhuesing/computetoai/environment"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/environment/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.
<a href="https://agentmods.dev/rules/ralfhuesing/computetoai/environment"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/environment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00621 | $0.00621 |
| Opus 5.5 | $0.00248 | $0.00248 |
| Sonnet 5.5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
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 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.
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:
.gitattributesim Repo-Root erzwingteol=lffür Text-/Codedateien, unabhängig von der lokalencore.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 (
pathlibin 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.
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.
- 1mo ago First seen · 31 lines · 621 tokens per session scan A 5b7f16fc9cae
environment is a cursor rule published in the GitHub repository RalfHuesing/ComputeToAi (0 stars, last pushed 2mo ago), licensed MIT. It adds 621 tokens to every session, about $0.0025 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).