What is define-questions.eval?

A document-analysis command that finds unanswered questions, “to be decided” items, unclear statements, and missing information, then saves them in a structured JSON file.

Use it on product requirements or other planning documents to prepare questions for review and later answer them with a question-and-answer session.

It makes hidden gaps in a draft visible and creates a consistent list for follow-up decisions.

define-questions.eval — Command for Claude Code by davistroy

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/davistroy/claude-marketplace

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/define-questions.eval/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/define-questions.eval)

Your own site

<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/define-questions.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/define-questions.eval/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/define-questions.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/define-questions.eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 872 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00872
Opus 5	$0.00000	$0.00436
Sonnet 5	$0.00000	$0.00174
Haiku 4.5	$0.00000	$0.00087

Measured 10d ago against content hash af18fc7b0765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

define-questions.eval 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 10d 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.

evals/commands/define-questions.eval.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval: /define-questions

Purpose

Analyzes a document and extracts all open questions, TBDs, ambiguities, and gaps into a structured JSON file. Good output: a valid JSON file compatible with the questions schema, containing every actionable open item from the document.

Fixtures

Fixture	Purpose
`docs/draft-prd.md`	PRD with 6 explicit open questions + multiple TBDs embedded in text
`docs/sample-prd.md`	Complete PRD with "None" open questions — tests the no-questions case

Test Scenarios

S1: Happy path — document with open questions

Invocation: /define-questions fixtures/docs/draft-prd.md

Must:

Creates reference/questions-draft-prd-*.json (timestamped)
Output is valid JSON
JSON contains questions array with at least 5 questions (doc has 6 explicit + implicit gaps)
JSON contains metadata object with source_document, total_questions, generated_date
Each question has id, question, context, priority fields
Schema validation PASSED is reported

Should:

Captures the 6 questions from Section 7 "Open Questions"
Also captures the TBD items embedded in Sections 1.2, 3.1, 3.2, 4.1 (implicit questions)
Priority assignments are reasonable (time zone handling = high, data retention = medium)
Questions are deduplicated (same question not listed twice)

Must NOT:

Invent questions not derivable from the document
Miss the explicit "TBD" markers

S2: Document with no open questions

Invocation: /define-questions fixtures/docs/sample-prd.md

Must:

Either: reports "No questions, open items, or TBDs found" (document appears complete)
Or: produces a JSON with 0 questions and a note
Does not generate a file with fabricated questions for a complete document

Should:

Suggests running /assess-document for a quality check

S3: CSV format

Invocation: /define-questions fixtures/docs/draft-prd.md --format csv

Read the full file on GitHub · 112 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.

10d ago First seen · 112 lines · 0 tokens per session scan A af18fc7b0765

Subscribe to this mod's changes

define-questions.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 872 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.

Documents

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens

prose-review-docs

Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…

ihudak/ihudak-claude-plugins · 67 tokens

define-questions.eval