ask-a-data-question

ask-a-data-question is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 65 tokens per session (1,563 once invoked), scanned A, original, MIT.

A plain-English way to ask questions about data stored in a data warehouse such as Postgres, BigQuery, Snowflake, or Redshift. It turns the question into read-only SQL, runs it, and returns the result with cautions about possible problems.

In plain words
What is it for?
Use it to ask questions such as how many users signed up, which items sell most, how a metric changed over time, or how two groups compare.
Why use it?
It removes the need to write SQL for routine questions while reducing the risk of running an expensive query or trusting a misleading number. It also saves queries so they can be reused.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to ask questions such as how many users signed up, which items sell most, how a metric changed over time, or how two groups compare.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/ask-a-data-question
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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill ask-a-data-question
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

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-a-data-question

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/ask-a-data-question/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/ask-a-data-question)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/ask-a-data-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/ask-a-data-question/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-a-data-question

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/ask-a-data-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/ask-a-data-question.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,563 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 $0.00065 $0.01563
Opus 5 $0.00032 $0.00781
Sonnet 5 $0.00013 $0.00313
Haiku 4.5 $0.00006 $0.00156

Measured 9d ago against content hash 89f55a35f685, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ask-a-data-question 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 9d 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.

store/agents/operations/.agents/skills/ask-a-data-question/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask A Data Question

When to use

User asked data question. Anything phrased "how many," "what's," "top N by," "trend of," "compare X to Y," "why did Z change." Translate to SQL, run safely, return result with citations.

Connections I need

I run external work through Composio. Before this skill runs I check the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

  • Warehouse / data source (Postgres, BigQuery, Snowflake, Redshift) - Required. I run read-only SQL here. No warehouse means no answer.

If no warehouse is connected I stop and ask you to connect your warehouse first.

Information I need

I read your operations context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

  • Where the data lives - Required. Why I need it: I need to know which warehouse to query and the SQL dialect. If missing I ask: "Where does this data live? Best is to connect your warehouse from the Integrations tab and tell me which one to use."
  • Cost ceilings - Optional. Why I need it: I warn before running anything that would scan more than your ceiling. If you don't have it I keep going with TBD and use a conservative default of 100 GB scanned.
  • Table schemas - Optional. Why I need it: lets me draft accurate SQL without guessing column names. If you don't have it I introspect the warehouse on the fly.
  • Operating context doc - Required. Why I need it: anchors what "this number looks weird" means against your priorities. If missing I ask: "Want me to set up your operating context first? Helps me catch suspicious results."

Hard rules

  • Read-only. Any proposed query containing INSERT, UPDATE, DELETE, MERGE, DROP, CREATE, ALTER, TRUNCATE, GRANT, or REVOKE refused immediately.
  • Warn before executing potentially expensive query. Use warehouse explain / dry-run tool (discover via composio search warehouse explain or provider equivalent) to estimate scanned bytes + runtime. Compare against config/data-sources.jsoncostCeilingScannedGb and costCeilingSeconds for target source. If exceeded, state estimate, wait for explicit approval.
  • Every result ships with: exact SQL, run timestamp, row count, any data-quality caveats.

Read the full file on GitHub · 139 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. 9d ago First seen · 139 lines · 65 tokens per session scan A 89f55a35f685

Subscribe to this mod's changes

ask-a-data-question is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,563 once invoked, about $0.0003 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.