parse-schema-for-dataset

parse-schema-for-dataset is a command for Claude Code from liam-hq/liam. It costs 13 tokens per session (228 once invoked), scanned A, original, Apache-2.0.

A command that converts a database schema file—such as SQL, Prisma, or Drizzle definitions—into a JSON dataset for benchmarks. A schema describes tables, fields, and relationships in a database.

In plain words
What is it for?
Use it to create named benchmark cases from SQL or supported schema files, with automatic or explicitly selected format detection.
Why use it?
It avoids manually rewriting schema files into the JSON structure expected by benchmark tests. It also records the source format and checks the generated structure.

Command for Claude Code

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 commands/liam-hq/liam/parse-schema-for-dataset
Clone the repo
git clone --depth 1 https://github.com/liam-hq/liam

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 parse-schema-for-dataset

README.md
[![agentmods](https://agentmods.dev/badge/commands/liam-hq/liam/parse-schema-for-dataset.svg)](https://agentmods.dev/commands/liam-hq/liam/parse-schema-for-dataset)
Your own site
<a href="https://agentmods.dev/commands/liam-hq/liam/parse-schema-for-dataset"><img src="https://agentmods.dev/badge/commands/liam-hq/liam/parse-schema-for-dataset.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 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 $0.00013 $0.00228
Opus 5 $0.00006 $0.00114
Sonnet 5 $0.00003 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured 4d ago against content hash a4a90b8a1dad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parse-schema-for-dataset 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.

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.

.claude/commands/parse-schema-for-dataset.md · 30 lines

What it actually says

Parse Schema for Dataset

Task

Parse the specified schema file (SQL, Prisma, Drizzle, etc.) to JSON format and save it to the benchmark reference directory at frontend/internal-packages/schema-bench/benchmark-workspace-default/execution/reference/.

Process

  1. Identify the input schema file format (postgres, prisma, drizzle, tbls, schemarb)
  2. Use the @liam-hq/schema parser to convert to JSON
  3. Save the output to an appropriately named case file in the benchmark reference directory
  4. Verify the generated JSON structure matches the expected format

Arguments

$ARGUMENTS

Expected arguments:

  • Input file path (SQL or schema file)
  • Output case name (e.g., "case-002", "case-003")
  • Format (optional - will auto-detect if not provided)

Example usage: /parse-schema-for-dataset schema.sql case-002 /parse-schema-for-dataset prisma/schema.prisma case-003 --format prisma

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 · 30 lines · 13 tokens per session scan A a4a90b8a1dad

Subscribe to this mod's changes

parse-schema-for-dataset is a command published in the GitHub repository liam-hq/liam (5,102 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 228 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 2026-08-30.