ask-me

A questioning rule for clarifying underspecified requests before implementation begins.

In plain words
What is it for?
Asking one focused question at a time, including a best-guess answer, until the request is specific enough to implement safely.
Why use it?
It prevents work from being based on hidden guesses about the user's goal, audience, definition of success, or constraints.

Cursor rule for 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/brainy-builds/ts-inspect-cli/ask-me
Clone the repo
git clone --depth 1 https://github.com/Brainy-Builds/ts-inspect-cli

Made for: Cursor.

Per session 2,128 This file is loaded in full into every session.
When invoked 2,128 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 $0.02128 $0.02128
Opus 5 $0.01064 $0.01064
Sonnet 5 $0.00426 $0.00426
Haiku 4.5 $0.00213 $0.00213

Measured 2d ago against content hash bd89e5b45f0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ask-me 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 2d 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/ask-me.mdc · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask Me

Purpose

What people ask for and what they actually want are often different things. This rule closes that gap before any code exists. Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).

When to Use

Apply this when:

  • The ask is missing at least one of: who the user is, why they want it, what success looks like, what the binding constraint is.
  • The request is conventional rather than specific ("build me a dashboard", "make it faster") and you cannot unpack the convention without guessing.
  • You are tempted to start with assumptions you have not surfaced.
  • The user explicitly says: "interview me", "grill me", "before we start, are we sure?", "stress-test my thinking".

Do NOT use when:

  • The ask is unambiguous and self-contained ("rename this variable", "fix this typo").
  • The user explicitly asks for speed over verification.
  • Pure information requests ("how does X work?", "what does this code do?").
  • Mechanical operations (renames, formats, file moves).
  • You already have >= 9/10 confidence.

Non-interactive constraint: This rule needs a live, responsive user. Do not invoke in CI pipelines, scheduled runs, or autonomous loops. If the ask is underspecified in a non-interactive context, flag it as a blocker instead of guessing.

Core Process

Step 1: Detect underspecification

Treat a request as underspecified if any of these are unclear:

  • Objective - what should change vs stay the same.
  • Done - acceptance criteria, examples, edge cases.
  • Scope - which files, components, or users are in/out.
  • Constraints - compatibility, performance, style, deps, time.
  • Environment - language/runtime versions, OS, build/test runner.
  • Safety - data migration, rollout/rollback, risk.

If multiple plausible interpretations exist, assume it is underspecified.

Read the full file on GitHub · 175 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. 2d ago First seen · 175 lines · 2,128 tokens per session scan A bd89e5b45f0e

Subscribe to this mod's changes

ask-me is a cursor rule published in the GitHub repository Brainy-Builds/ts-inspect-cli (2 stars, last pushed 13d ago), licensed MIT. It adds 2,128 tokens to every session, about $0.0106 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.