warehouse-sql

warehouse-sql is a skill for Claude Code from HybridAIOne/hybridclaw. It costs 27 tokens per session (1,736 once invoked), scanned A, original, MIT.

A tool for asking questions about warehouse data in plain language and turning them into SQL, the language used to query databases. It supports several database systems and checks queries before running them.

In plain words
What is it for?
Use it to inspect schemas, review generated SQL, answer reporting questions, and run safe read-only warehouse queries.
Why use it?
It reduces the risk of misunderstanding the database structure or accidentally changing data. Queries run in read-only mode unless a specific write permission is granted.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/skill-creator/scripts/quick_validate.py skills/warehouse-sql.

Good fit Use it to inspect schemas, review generated SQL, answer reporting questions, and run safe read-only warehouse queries.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HybridAIOne/hybridclaw
agentmods
npx agentmods add skills/hybridaione/hybridclaw/warehouse-sql

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.

agentmods badge for warehouse-sql

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/warehouse-sql.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/warehouse-sql)
Your own site
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/warehouse-sql"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/warehouse-sql.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,736 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 3
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00027 $0.01736
Opus 5 $0.00014 $0.00868
Sonnet 5 $0.00005 $0.00347
Haiku 4.5 $0.00003 $0.00174

Measured 4d ago against content hash 6f4b27c85b6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

warehouse-sql 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (evals/tpch_eval_planner.py, scripts/warehouse_sql.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/warehouse-sql/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warehouse SQL

Use this skill when the user asks natural-language questions of a data warehouse, analytics database, or TPC-H-style reporting dataset.

Scope

  • schema introspection for SQLite eval databases and pluggable Postgres, ClickHouse, BigQuery, and Snowflake backends
  • cached schema summaries with explicit refresh commands for scheduled runs
  • reproducible TPC-H-style evaluation cases for generated SQL
  • deterministic SQL safety review before execution
  • read-only execution by default
  • write detection and explicit per-skill grant checks before any mutation

Default Workflow

  1. Refresh or read cached schema before asking the model to draft SQL:
    python3 skills/warehouse-sql/scripts/warehouse_sql.py --format json schema --backend sqlite --database ./warehouse.db
    
  2. Have the model draft SQL using the cached schema, then review it before execution:
    python3 skills/warehouse-sql/scripts/warehouse_sql.py --format json review "SELECT c_name FROM customer LIMIT 10"
    
    For review-only commands, pass --model-review with the original question to invoke HybridClaw's OpenAI-compatible gateway for the business-meaning review:
    python3 skills/warehouse-sql/scripts/warehouse_sql.py --format json review --model-review --question "Show the first 10 customers" "SELECT c_name FROM customer LIMIT 10"
    
  3. Return the SQL to the user before execution when the user asks for review, when the query is broad, or when the result could expose sensitive business data.
  4. Execute only after the SQL review passes and include the original question:
    python3 skills/warehouse-sql/scripts/warehouse_sql.py --format json query --backend sqlite --database ./warehouse.db --execute --question "Show the first 10 customers" "SELECT c_name FROM customer LIMIT 10"
    
    query --execute always invokes model review before running SQL. Configure model review with HYBRIDCLAW_GATEWAY_URL / GATEWAY_BASE_URL and HYBRIDCLAW_WAREHOUSE_SQL_MODEL_REVIEW_TOKEN, HYBRIDCLAW_GATEWAY_TOKEN, or GATEWAY_API_TOKEN. Execution requires --question so the model can check whether the SQL answers the user's request.

Read the full file on GitHub · 181 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 181 lines · 27 tokens per session scan A 6f4b27c85b6b

Subscribe to this mod's changes

warehouse-sql is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,736 once invoked, about $0.0001 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 2026-09-03.