surface-dont-guess

surface-dont-guess is a cursor rule for Cursor from arango-solutions/arango-sparql-py. It costs 413 tokens per session, scanned A, original, MIT.

A rule for handling uncertainty during coding work. It tells the agent to ask the user when requirements, design choices, scope, or missing context are unclear.

In plain words
What is it for?
Checking the codebase and documentation briefly, then asking focused questions about requirements, architecture, breaking changes, or unclear scope before proceeding.
Why use it?
It prevents the agent from silently choosing an approach that may not match the user's needs or could break existing code.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

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/arango-solutions/arango-sparql-py/surface-dont-guess
Clone the repo
git clone --depth 1 https://github.com/arango-solutions/arango-sparql-py

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 surface-dont-guess

README.md
[![agentmods](https://agentmods.dev/badge/rules/arango-solutions/arango-sparql-py/surface-dont-guess.svg)](https://agentmods.dev/rules/arango-solutions/arango-sparql-py/surface-dont-guess)
Your own site
<a href="https://agentmods.dev/rules/arango-solutions/arango-sparql-py/surface-dont-guess"><img src="https://agentmods.dev/badge/rules/arango-solutions/arango-sparql-py/surface-dont-guess.svg" alt="Measured on agentmods" height="20"></a>
Per session 413 This file is loaded in full into every session.
When invoked 413 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 5.1 $0.00413 $0.00413
Opus 5 $0.00206 $0.00206
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00041 $0.00041

Measured 5d ago against content hash 5e64db3b185f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

surface-dont-guess 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 5d 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/surface-dont-guess.mdc · 57 lines

What it actually says

Surface Don't Guess

"When unsure, ask—don't bet the codebase."

A wrong guess implemented is worse than an honest question asked.

When You MUST Ask

Situation Why
Ambiguous requirements "Add caching" — Cache what? Where? How long?
Multiple valid approaches Sync or async? REST or gRPC?
Breaking changes Will this affect existing callers?
Architectural decisions New service or extend existing?
Unclear scope Is this feature supposed to include X?
Missing context Why does this code exist?

The Uncertainty Protocol

  1. Attempt Self-Resolution (60 seconds max) — Search codebase, check docs, look at tests
  2. If Still Uncertain → ASK — State what you understand, what's unclear, and options with tradeoffs
  3. WAIT — Do NOT proceed with a guess

Good vs. Bad

# BAD: Silent Guessing
User: "Add retry logic"
Agent: *implements exponential backoff with 5 retries, 1s delay, max 30s*
User: "Why 30 seconds? I wanted 3 quick retries."

# GOOD: Surfacing Uncertainty
User: "Add retry logic"
Agent: "Before I implement:
1. Max retries: 3? 5?
2. Backoff: fixed? exponential? jitter?
3. Which errors trigger retry?
4. Max total timeout?"

Cost of Guessing

Guess Cost
Wrong architecture Days of refactoring
Wrong behavior User-facing bugs
Wrong scope Wasted effort

Cost of asking: 30 seconds of the user's time.

Your confidence is not a substitute for their knowledge. Ask.

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. 5d ago First seen · 57 lines · 413 tokens per session scan A 5e64db3b185f

Subscribe to this mod's changes

surface-dont-guess is a cursor rule published in the GitHub repository arango-solutions/arango-sparql-py (2 stars, last pushed 19d ago), licensed MIT. It adds 413 tokens to every session, about $0.0021 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.