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/davistroy/claude-marketplaceWrote 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/commands/davistroy/claude-marketplace/ask-questions)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/ask-questions"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/ask-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.
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/ask-questions"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/ask-questions.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 | $0.00008 | $0.04195 |
| Opus 5 | $0.00004 | $0.02098 |
| Sonnet 5 | $0.00002 | $0.00839 |
| Haiku 4.5 | $0.00001 | $0.00419 |
Grade A, and why
ask-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 11d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Questions Command
Interactively walk the user through answering questions from a JSON file produced by the /define-questions command.
Pipeline component: This command walks through a JSON question file interactively. For the combined extract → answer → update workflow, use
/finish-document.
Input Validation
Required Arguments:
<questions-file>- Path to the JSON file created by/define-questions
Optional Arguments:
--force- Proceed even if input or output schema validation fails (not recommended)
Validation: If the questions file path is missing, display:
Usage: /ask-questions <questions-file> [--force]
Example: /ask-questions questions-PRD-20260110-143052.json
Example: /ask-questions reference/questions-requirements-20260114.json
Input
The user will provide a JSON file path after the slash command (e.g., /ask-questions questions-PRD-20260110.json). This file must follow the structure created by /define-questions.
Instructions
1. Load and Validate
- Read the specified JSON file
- Validate it conforms to the questions schema structure (see validation rules below)
- Verify it contains the required
questionsarray andmetadata - Load the original source document referenced in
metadata.source_document - Check for existing answer file (resume support - see below)
- Report the total number of questions to the user
1.1 Resume Support
Before starting the Q&A session, check for an incomplete previous session:
-
Use the Glob tool to find existing
answers-[source-document]-*.jsonfiles in the same directory as the questions file -
If found, read the file and check
metadata.status. If status is"in_progress": Report the session state as prose — previous file, progress (15 of 47 answered (32%)), and last activity — then ask withAskUserQuestion, exactly as specified inreferences/patterns/workflow.md:{ "questions": [ { "question": "How would you like to proceed with the interrupted session?", "header": "Resume", "multiSelect": false, "options": [ { "label": "Resume (Recommended)", "description": "Continue from question 16 with all previous answers preserved" }, { "label": "Start Fresh", "description": "Begin a new session; previous answers are backed up to a .bak file first" }, { "label": "Abort", "description": "Exit without making changes" } ] } ] } -
On resume: Load existing answers and continue from
metadata.last_question_answered + 1. Each answer entry has ananswered: true/falsefield to identify which questions have responses. -
On start fresh: Backup existing file (rename with
.baksuffix) and start from question 1
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.
- 11d ago First seen · 487 lines · 8 tokens per session scan A 027a983ce926
ask-questions is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 8 tokens to every session and 4,195 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.