# query-clarifier

Checks a research request for ambiguity and scope, then decides whether the user should clarify it before research starts.

- subagent · `type=agent` · Claude Code · 782 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/query-clarifier.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/query-clarifier

## What it does

This subagent reviews a research request before work begins. It looks for vague wording, competing interpretations, missing scope, unclear goals, and topics that are too broad. It then chooses whether to proceed, refine the request, or ask the user for clarification.

Its response is a JSON object containing the decision, confidence score, short reasoning, clarification questions, a revised query, and focus areas. The configured tools are `Read`, `Write`, and `Edit`. That keeps `query-clarifier` focused on shaping the research request rather than conducting the research itself.

For Claude Code, setup uses `npx` and the file `.claude/agents/query-clarifier.md`. The repository entry also provides agent paths for Codex and Cursor.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent deep-research-team/query-clarifier
```

2. **Manually: put the files in place**
- File: `.claude/agents/query-clarifier.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/query-clarifier.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/query-clarifier.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/query-clarifier.md

## When to use it
- check a query before research
- spot vague research wording
- narrow an overly broad topic
- ask focused clarification questions
- return a structured query assessment

## Example prompts
- Review this research request and tell me whether clarification is needed: “Compare tools for data analysis.”
- Assess “Tell me about AI” and ask only the questions needed to make the research actionable.
- Return the query review as JSON using the subagent’s required structure.

## Similar
- [explore-code](https://affpapa.org/en/nevibecode/skills/explore-code.md) — skill · 336700 installs
- [firecrawl-research-index](https://affpapa.org/en/nevibecode/skills/firecrawl-research-index.md) — skill · 24400 installs
- [tavily-research](https://affpapa.org/en/nevibecode/skills/tavily-research.md) — skill · 22000 installs
- [parallel-deep-research](https://affpapa.org/en/nevibecode/skills/parallel-deep-research.md) — skill · 15600 installs
- [learn](https://affpapa.org/en/nevibecode/skills/learn.md) — skill · 13200 installs
- [tanstack-query-best-practices](https://affpapa.org/en/nevibecode/skills/tanstack-query-best-practices.md) — skill · 12800 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 495 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md