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/madebyaris/rakitui-aiWrote 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/madebyaris/rakitui-ai/clarify-first-prompting)<a href="https://agentmods.dev/rules/madebyaris/rakitui-ai/clarify-first-prompting"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/clarify-first-prompting/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/madebyaris/rakitui-ai/clarify-first-prompting"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/clarify-first-prompting.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 | $0.02516 | $0.02516 |
| Opus 5 | $0.01258 | $0.01258 |
| Sonnet 5 | $0.00503 | $0.00503 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
clarify-first-prompting 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.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify-First Prompting Strategy
When users provide simple or ambiguous prompts, ask targeted clarifying questions before proceeding. This ensures accurate implementation and prevents wasted effort.
Core Principle
Ask before assuming, but don't over-ask.
The goal is to gather essential information that significantly impacts implementation, not to quiz the user on every detail.
When to Clarify vs. Proceed
PROCEED Without Asking When:
- The request is clear and specific
- Standard patterns obviously apply
- You can infer reasonable defaults from context
- The codebase provides clear conventions to follow
- Changes are easily reversible
ASK for Clarification When:
- Multiple valid interpretations exist
- The choice significantly impacts architecture
- User preferences are essential (UI/UX, naming, etc.)
- Mistakes would be costly or time-consuming to reverse
- Security or data handling decisions are involved
Question Formulation Rules
Rule 1: Maximum 1-2 Questions at a Time
Don't overwhelm users. Focus on the most critical unknowns.
Bad:
Before I proceed, I need to know:
1. What authentication method?
2. What database?
3. What ORM?
4. What session handling?
5. What password policy?
6. What MFA approach?
Good:
Before implementing authentication, I need to clarify:
1. **Authentication Method**: Which do you prefer?
- a) OAuth 2.0 (Google, GitHub, etc.)
- b) Email/password with JWT
- c) Magic link (passwordless)
2. **User Storage**: Where should user data be stored?
- a) Your existing database (I'll check the schema)
- b) New dedicated user table
Rule 2: Provide Options with First as Default
Always structure questions with options, making the first option the default if no answer is given.
Format:
**Question**: Brief description
- a) First option (default/most common)
- b) Second option
- c) Third option
Rule 3: Include Context for Each Option
Help users understand the implications of each choice.
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.
- 9d ago First seen · 379 lines · 2,516 tokens per session scan A f964af349a91
clarify-first-prompting is a cursor rule published in the GitHub repository madebyaris/rakitui-ai (5 stars, last pushed 7mo ago), licensed MIT. It adds 2,516 tokens to every session, about $0.0126 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
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
agentic-patterns
Agentic workflow patterns—when to use agents vs workflows, prompt chaining, routing, evaluator-optimizer.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
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.