1-ask

A conversational requirements-discovery command that asks questions to clarify a feature idea before writing a specification.

In plain words
What is it for?
Use it at the start of feature work when you need to clarify what should be built. It is intended to ask questions and not create specification files during this stage.
Why use it?
It reduces missing or misunderstood requirements by exploring the problem, users, scope, integrations, constraints, and technical needs first.

Command for Claude Code

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 commands/clchinkc/document-mcp/1-ask
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00757
Opus 5 $0.00000 $0.00378
Sonnet 5 $0.00000 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 2d ago against content hash 1117be960b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

1-ask 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.

.claude/commands/1-ask.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Discovery and Clarification

Workflow Stage: Requirements Discovery

Engage with the user to understand their feature idea through targeted questions and discussion, building context for subsequent specification generation.

This workflow focuses on exploring and clarifying the user's needs through conversational inquiry rather than formal documentation.

Constraints:

  • The model MUST engage in a conversational exploration of the user's feature idea or problem
  • The model MUST ask targeted, relevant questions based on the initial description
  • The model SHOULD focus on understanding:
    • The core problem or need being addressed
    • Who will use the feature (target users/roles)
    • The expected scale and scope
    • Integration requirements with existing systems
    • Key functional requirements
    • Non-functional requirements (performance, security, scalability)
    • Any specific constraints or dependencies
  • The model MUST adapt its questions based on the user's responses
  • The model SHOULD identify gaps in understanding and probe deeper when necessary
  • The model MUST NOT create any specification files during this phase
  • The model MUST maintain context from all responses for future reference
  • The model SHOULD summarize key findings periodically to confirm understanding
  • The model MAY suggest considerations the user might not have thought of
  • The model SHOULD explore edge cases and potential challenges
  • The model MUST prepare the groundwork for formal specification generation

Question Categories

Initial Understanding

  • What is the main problem you're trying to solve?
  • Who are the primary users of this feature/system?
  • What is the expected scale (number of users, data volume, etc.)?
  • What are the key outcomes you want to achieve?

Functional Requirements

  • What are the core functionalities needed?
  • How do users currently handle this task (if applicable)?
  • What are the must-have vs nice-to-have features?
  • Are there any specific workflows or processes to support?

Read the full file on GitHub · 86 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 · 86 lines · 0 tokens per session scan A 1117be960b38

Subscribe to this mod's changes

1-ask is a command published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 757 tokens. 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.