proactive-questions

proactive-questions is a cursor rule for Cursor from RalfHuesing/ComputeToAi. It costs 421 tokens per session, scanned A, original, MIT.

Rules for asking the user before making a genuine implementation or scope decision.

In plain words
What is it for?
They guide how to present a recommended option, alternatives, trade-offs, and grouped questions before starting non-trivial work.
Why use it?
They prevent the coding agent from silently choosing between several reasonable approaches when the project does not provide a clear answer.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: installed under .agents/ (shared by several agents).

Good fit They guide how to present a recommended option, alternatives, trade-offs, and grouped questions before starting non-trivial work.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/ralfhuesing/computetoai/proactive-questions
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.

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

Made for: Cursor.

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.

agentmods badge for proactive-questions

README.md
[![agentmods](https://agentmods.dev/badge/rules/ralfhuesing/computetoai/proactive-questions/github.svg)](https://agentmods.dev/rules/ralfhuesing/computetoai/proactive-questions)
Your own site
<a href="https://agentmods.dev/rules/ralfhuesing/computetoai/proactive-questions"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/proactive-questions/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.

agentmods 80×15 button for proactive-questions

Your own site · 80×15
<a href="https://agentmods.dev/rules/ralfhuesing/computetoai/proactive-questions"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/proactive-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 421 This file is loaded in full into every session.
When invoked 421 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00421 $0.00421
Opus 5.5 $0.00168 $0.00168
Sonnet 5.5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 1mo ago against content hash 7f038bfa380f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proactive-questions 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.

.agents/rules/proactive-questions.mdc · 23 lines

What it actually says

Proaktiv nachfragen statt eigenmächtig loslegen

Stößt ein Agent auf eine echte Entscheidung – mehrere sinnvolle Umsetzungswege, unklarer Scope/Umfang einer Aufgabe, eine Grundsatzfrage, die nicht eindeutig aus Docs/ oder .agents/rules/ folgt – wird nicht stillschweigend eine Annahme getroffen und direkt losgelegt. Stattdessen wird interaktiv beim Nutzer nachgefragt, bevor mit der Umsetzung begonnen wird.

Wie gefragt wird

  • Nicht offen ("Was soll ich tun?", "Wie möchtest du das haben?"), sondern mit einer konkreten Handlungsempfehlung: eigener Vorschlag inkl. kurzer Begründung, plus die relevanten Alternativen mit ihren Trade-offs. Der Nutzer soll auswählen/bestätigen können, nicht das Problem von null durchdenken müssen.
  • Wenn das genutzte Agent-Tool ein interaktives Rückfrage-Werkzeug anbietet (z. B. eine strukturierte Auswahlfrage), wird das genutzt; ansonsten wird die Frage im Chat mit klar benannten Optionen gestellt.
  • Mehrere offene Entscheidungen zu einer Aufgabe werden nach Möglichkeit gebündelt gefragt, nicht nacheinander in Einzel-Runden.

Wann NICHT gefragt wird

Bei trivialen, reversiblen Schritten, deren Umsetzung eindeutig aus Docs/ oder .agents/rules/ folgt (z. B. ein offensichtlicher Tippfehler, eine Formatierungskorrektur, ein Schritt, der exakt so in einer bereits abgestimmten Roadmap/Aufgabe steht) – hier bremst eine Rückfrage nur die Zusammenarbeit, ohne echten Erkenntnisgewinn zu bringen.

Beispiel

Vor der Festlegung der Commit-Granularität und Branch-Strategie in git-workflow.mdc wurde genau so nachgefragt: zwei konkrete Optionen mit Empfehlung statt einer offenen Frage, gebündelt in einer Runde.

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. 1mo ago First seen · 23 lines · 421 tokens per session scan A 7f038bfa380f

Subscribe to this mod's changes

proactive-questions is a cursor rule published in the GitHub repository RalfHuesing/ComputeToAi (0 stars, last pushed 2mo ago), licensed MIT. It adds 421 tokens to every session, about $0.0017 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.