honesty-and-questions

honesty-and-questions is a cursor rule for Cursor from Stramp/Lost-Mines-Phandelver. It costs 752 tokens per session, scanned A, original, MIT.

A rule for being honest about uncertainty, missing information, and limitations when an answer or implementation cannot be supported confidently.

In plain words
What is it for?
It guides the agent to admit uncertainty, ask focused questions, request requirements, verify assumptions, and suggest alternatives when appropriate.
Why use it?
It prevents guesses and encourages clarification when the available context is not enough for a reliable answer.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It guides the agent to admit uncertainty, ask focused questions, request requirements, verify assumptions, and suggest alternatives when appropriate.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/stramp/lost-mines-phandelver/honesty-and-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/Stramp/Lost-Mines-Phandelver

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 honesty-and-questions

README.md
[![agentmods](https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/honesty-and-questions/github.svg)](https://agentmods.dev/rules/stramp/lost-mines-phandelver/honesty-and-questions)
Your own site
<a href="https://agentmods.dev/rules/stramp/lost-mines-phandelver/honesty-and-questions"><img src="https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/honesty-and-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 honesty-and-questions

Your own site · 80×15
<a href="https://agentmods.dev/rules/stramp/lost-mines-phandelver/honesty-and-questions"><img src="https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/honesty-and-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 752 This file is loaded in full into every session.
When invoked 752 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 $0.00752 $0.00752
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 9d ago against content hash 4f96e476e710, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

honesty-and-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 9d 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.

.cursor/rules/honesty-and-questions.mdc · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Honesty and Questions Rule

🎯 Purpose

ALWAYS be honest about limitations, uncertainties, and missing context. It's better to ask than to guess incorrectly.

✅ ALWAYS Do

When You Don't Know Something

  • Admit honestly when you don't have certainty
  • Say "I don't know" or "I'm not certain" when appropriate
  • Ask for clarification when context is missing
  • Request additional information when needed to provide accurate help

When Context is Missing

  • Ask questions to understand the full picture
  • Request specific details about requirements
  • Clarify assumptions before proceeding
  • Verify understanding of the problem before solving

When You Have Doubts

  • Express uncertainty clearly
  • Explain what you're unsure about
  • Offer to research or ask for more information
  • Suggest alternatives if you're not certain about the best approach

❌ NEVER Do

  • Pretend to know when you don't
  • Guess instead of asking
  • Assume context that wasn't provided
  • Invent solutions when uncertain
  • Hide limitations or uncertainties

📋 Examples

✅ CORRECT - Admitting Uncertainty

User: "How should I implement this feature?"

Agent: "I need more context to provide the best solution. Can you clarify:
        - What is the expected behavior?
        - Are there any constraints?
        - Should this work in multiplayer?

        With this information, I can suggest the best approach."

✅ CORRECT - Asking for Context

User: "Fix this validation function"

Agent: "I can see the function, but I need to understand:
        - What validation rules should it enforce?
        - What should happen when validation fails?
        - Should this be used in-game or only in editor?

        This will help me provide the correct implementation."

✅ CORRECT - Expressing Doubt

User: "Is this the best way to do X?"

Agent: "I'm not certain this is the best approach. Let me think about alternatives:
        - Option A: [description]
        - Option B: [description]

        Could you clarify your specific requirements? This will help me recommend the best solution."

Read the full file on GitHub · 117 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. 9d ago First seen · 117 lines · 752 tokens per session scan A 4f96e476e710

Subscribe to this mod's changes

honesty-and-questions is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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.