Liam ERD is a tool that turns database schemas into interactive entity-relationship diagrams, visual maps showing tables and their relationships. It helps people understand and document database structures, including complex schemas.
Borrowing it
Nothing to install: this file belongs to liam-hq/liam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liam-hq/liam/main/.claude/commands/deparse-dataset-to-schema.mdgit clone --depth 1 https://github.com/liam-hq/liamWrote 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.
[](https://agentmods.dev/commands/liam-hq/liam/deparse-dataset-to-schema)<a href="https://agentmods.dev/commands/liam-hq/liam/deparse-dataset-to-schema"><img src="https://agentmods.dev/badge/commands/liam-hq/liam/deparse-dataset-to-schema/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.
<a href="https://agentmods.dev/commands/liam-hq/liam/deparse-dataset-to-schema"><img src="https://agentmods.dev/badge/commands/liam-hq/liam/deparse-dataset-to-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.00236 |
| Opus 5 | $0.00004 | $0.00118 |
| Sonnet 5 | $0.00002 | $0.00047 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
deparse-dataset-to-schema 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.
What it actually says
Deparse Dataset to Schema
Task
Convert a JSON schema dataset to a schema file in the specified format using @liam-hq/schema deparser functionality.
Process
- Read the JSON dataset from the specified input path
- Use @liam-hq/schema's
postgresqlSchemaDeparserfunction to convert JSON to SQL DDL - Save the generated schema file to the specified output path
- Verify the generated schema is valid and properly formatted
Arguments
$ARGUMENTS
Expected arguments:
- Input JSON file path - path to the JSON schema dataset to convert
- Output file path - where to save the generated schema file
- Format (optional - currently supports postgres, defaults to postgres)
Example usage:
/deparse-dataset-to-schema frontend/internal-packages/schema-bench/benchmark-workspace-default/execution/reference/case-001.json schema.sql
/deparse-dataset-to-schema data/case-002.json output/schema.sql --format postgres
/deparse-dataset-to-schema ./my-schema.json generated-schema.sql
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.
- 9d ago First seen · 32 lines · 8 tokens per session scan A 20b72b2be178
deparse-dataset-to-schema is a command published in the GitHub repository liam-hq/liam (5,105 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 236 once invoked, about $0.0000 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.
Other commands, from other repositories
data
Invoke the Data Engineer for ETL/ELT, dbt, warehouses, streaming, orchestration, and data quality.
vector.batch_exists
Check existence for multiple vector keys.
vector.batch_upsert
Upsert multiple vectors in one itemwise batch.
vector.collection.stats
Read facts for one vector collection.
ai-rag-setup
Set up RAG (Retrieval-Augmented Generation) system.
fix
System prompt for /fix slash command.