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.
npx agentmods add rules/arango-solutions/arango-sparql-py/surface-dont-guessgit clone --depth 1 https://github.com/arango-solutions/arango-sparql-pyWrote 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/arango-solutions/arango-sparql-py/surface-dont-guess)<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>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 | $0.00413 | $0.00413 |
| Opus 5 | $0.00206 | $0.00206 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
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.
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
- Attempt Self-Resolution (60 seconds max) — Search codebase, check docs, look at tests
- If Still Uncertain → ASK — State what you understand, what's unclear, and options with tradeoffs
- 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.
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.
- 5d ago First seen · 57 lines · 413 tokens per session scan A 5e64db3b185f
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.
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.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.