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/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/yes-no-questions)<a href="https://agentmods.dev/rules/paulbaranowski/wild-horses/yes-no-questions"><img src="https://agentmods.dev/badge/rules/paulbaranowski/wild-horses/yes-no-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.
<a href="https://agentmods.dev/rules/paulbaranowski/wild-horses/yes-no-questions"><img src="https://agentmods.dev/badge/rules/paulbaranowski/wild-horses/yes-no-questions.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 | $0.00327 | $0.00327 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
yes-no-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 12d 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
When asking the user a question with discrete choices, ask it as numbered yes/no questions (1./2./3.), one per line, no bullet glyphs. Collapse every either/or into a single yes/no phrased around one branch, where "no" means the other — e.g. "1. Should I include the script rewrite in this PR? (no = separate cleanup PR)". Never write a question with an embedded "or" offering two courses of action, and never list the two branches as pick-one options. This applies to approval and confirmation gates too: "Does this look right?" / "Ready to proceed?" becomes a yes/no — e.g. "1. Approve as-is? (no = tell me what to change)". Only when a choice has 3+ genuinely mutually-exclusive branches that can't reduce to yes/no, list them as numbered pick-one options or use AskQuestion. Exception — list-already-shown: if the immediately preceding text in your response already enumerates the candidates as a numbered list (i.e. each numbered item is a distinct thing to pick from, not a branch of a binary decision — e.g. "1. plan-A.md 2. plan-B.md"), the list IS the question. Don't restate it as N yes/no questions ("1. Pick plan A? 2. Pick plan B?") — that's redundant. Don't append a follow-up prompt either; the user will reply with the item number on their own.
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.
- 12d ago First seen · 7 lines · 327 tokens per session scan A 8157a6e89704
yes-no-questions is a cursor rule published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 24d ago), licensed MIT. It adds 327 tokens to every session, about $0.0016 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 2026-08-30.
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.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.