ask-me-questions

ask-me-questions is a command for Claude Code from glittercowboy/taches-cc-resources. It costs 9 tokens per session (760 once invoked), scanned A, original, MIT.

A command that asks adaptive questions to collect the requirements for a task before work begins. It examines what is already known and asks only about important gaps.

In plain words
What is it for?
Use it before writing, building, researching, or analyzing when the request needs clarification.
Why use it?
Starting with incomplete context can lead to the wrong output or unnecessary rework. This creates a clearer shared understanding of the task, audience, purpose, approach, and timing.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the taches-cc-resources plugin — 12 skills, 19 commands, 3 agents shipped together

Good fit Use it before writing, building, researching, or analyzing when the request needs clarification.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/glittercowboy/taches-cc-resources/ask-me-questions
About the project

TÂCHES Claude Code Resources is a collection of custom commands, skills, and agents that structure Claude Code workflows such as planning, debugging, automation, and subagent creation. It is intended for developers who use Claude Code for real software projects. The catalogue entries are examples of the resources included in the collection.

glittercowboy/taches-cc-resources · 1,976 stars · on GitHub · youtube.com

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.

Clone the repo
git clone --depth 1 https://github.com/glittercowboy/taches-cc-resources

Made for: Claude Code.

Or install taches-cc-resources, the plugin that ships this one along with the rest of its 12 skills, 19 commands, 3 agents.

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 ask-me-questions

README.md
[![agentmods](https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/ask-me-questions/github.svg)](https://agentmods.dev/commands/glittercowboy/taches-cc-resources/ask-me-questions)
Your own site
<a href="https://agentmods.dev/commands/glittercowboy/taches-cc-resources/ask-me-questions"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/ask-me-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.

agentmods 80×15 button for ask-me-questions

Your own site · 80×15
<a href="https://agentmods.dev/commands/glittercowboy/taches-cc-resources/ask-me-questions"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/ask-me-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00009 $0.00760
Opus 5 $0.00005 $0.00380
Sonnet 5 $0.00002 $0.00152
Haiku 4.5 $0.00001 $0.00076

Measured 12d ago against content hash 465dfbed1238, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ask-me-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.

commands/ask-me-questions.md · 94 lines

What it actually says

This prevents premature execution, captures nuance, and creates a collaborative context-building flow where you maintain control over when work begins.

<intake_gate>

<no_context_handler> IF $ARGUMENTS is empty or vague: → IMMEDIATELY use AskUserQuestion with:

  • header: "Task"
  • question: "What would you like help with?"
  • options:
    • "Write something" - Create a document, email, post, or other written content
    • "Build something" - Create code, a feature, system, or technical artifact
    • "Figure something out" - Research, analyze, or help me think through a problem
    • "Other" - Something else entirely

Then proceed to context_analysis with their response.

IF $ARGUMENTS provides clear context: → Skip to context_analysis </no_context_handler>

<context_analysis> Analyze $ARGUMENTS (or conversation context) to extract what's already provided:

  • What: The task, deliverable, or outcome requested
  • Who: Target audience, recipient, or stakeholders
  • Why: Purpose, goal, or motivation
  • How: Approach, constraints, or requirements
  • When: Timeline, urgency, or dependencies

Only ask about genuine gaps - don't re-ask what's already stated. </context_analysis>

<initial_questions> Use AskUserQuestion to ask 2-4 questions based on actual gaps:

If "what" is unclear:

  • "What specifically do you want?" with domain-appropriate options

If "who" is unclear:

  • "Who is this for?" with options: Myself, My team, External stakeholders, Public audience, Other

If "why" is unclear:

  • "What's the goal?" with options relevant to the task type

If "how" is unclear:

  • "Any constraints or preferences?" with domain-appropriate options

Skip questions where the context already provides the answer. </initial_questions>

<decision_gate> After receiving answers, use AskUserQuestion:

Question: "Ready to proceed, or would you like me to ask more questions?"

Options:

  1. Start working - I have enough context, proceed with the task
  2. Ask more questions - There are details I want to clarify
  3. Let me add context - I want to provide additional information

If "Ask more questions" → generate 2-3 contextual follow-ups based on accumulated context, then present decision gate again If "Let me add context" → receive input, then present decision gate again If "Start working" → proceed to execution </decision_gate>

</intake_gate>

<success_criteria>

  • No questions asked about information already provided
  • User maintains control over when execution begins
  • Context accumulates through multiple rounds if needed
  • All AskUserQuestion calls use structured options (not plain text questions)
  • Task executes only after user explicitly chooses to proceed </success_criteria>
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. 12d ago First seen · 94 lines · 9 tokens per session scan A 465dfbed1238

Subscribe to this mod's changes

ask-me-questions is a command published in the GitHub repository glittercowboy/taches-cc-resources (1,976 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 760 once invoked, about $0.0000 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.