sql-query

sql-query is a skill for Claude Code, Codex from TeamDzX/myllm-skills. It costs 31 tokens per session (261 once invoked), scanned A, original, MIT.

A skill that turns a plain-English data request and table schema into a SQL query.

In plain words
What is it for?
Use it to write, explain, or fix standard SQL queries when you provide the relevant tables and columns.
Why use it?
It helps produce a readable query with explicit joins and safe parameter placeholders, while exposing missing schema assumptions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/teamdzx/myllm-skills/sql-query
Any agent
npx skills add TeamDzX/myllm-skills --skill sql-query
Clone the repo
git clone --depth 1 https://github.com/TeamDzX/myllm-skills

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 sql-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/teamdzx/myllm-skills/sql-query.svg)](https://agentmods.dev/skills/teamdzx/myllm-skills/sql-query)
Your own site
<a href="https://agentmods.dev/skills/teamdzx/myllm-skills/sql-query"><img src="https://agentmods.dev/badge/skills/teamdzx/myllm-skills/sql-query.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00261
Opus 5 $0.00015 $0.00130
Sonnet 5 $0.00006 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 5d ago against content hash de8c93f850f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sql-query 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 5d 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.

skills/sql-query/SKILL.md · 26 lines

What it actually says

SQL query

Translate the user's request into a correct SQL query.

  1. Work from the schema the user provides. If the relevant tables/columns aren't given, ask for them (or state the assumptions you're making).

  2. Output:

    -- one clear query
    

    Then two lines explaining what it does and any assumption (e.g. dialect).

Rules:

  • Assume standard SQL unless the user names a dialect (Postgres, MySQL, SQLite, …); say which you assumed.
  • Use explicit column lists and JOIN ... ON, not implicit joins. Alias tables for readability.
  • For user-supplied values, use parameter placeholders (? / :name) and note it — never concatenate raw input.
  • Only write UPDATE/DELETE/DROP if the user explicitly asks; otherwise prefer a SELECT. For destructive statements, add a one-line warning and suggest a SELECT to preview affected rows first.
  • If asked to fix a query, show the corrected version and name the bug.
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. 5d ago First seen · 26 lines · 31 tokens per session scan A de8c93f850f7

Subscribe to this mod's changes

sql-query is a skill published in the GitHub repository TeamDzX/myllm-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 261 once invoked, about $0.0002 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.