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.
npx agentmods add commands/liam-hq/liam/parse-schema-for-datasetgit 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/parse-schema-for-dataset)<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>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 | $0.00013 | $0.00228 |
| Opus 5 | $0.00006 | $0.00114 |
| Sonnet 5 | $0.00003 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
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.
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
- Identify the input schema file format (postgres, prisma, drizzle, tbls, schemarb)
- Use the @liam-hq/schema parser to convert to JSON
- Save the output to an appropriately named case file in the benchmark reference directory
- 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
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.
- 4d ago First seen · 30 lines · 13 tokens per session scan A a4a90b8a1dad
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.
Other commands, from other repositories
k8s-dev
Manage a production-like Lightdash deployment on AWS EKS. Args: (none) = show status, up = idempotently provision + deploy, deploy = build this branch → ECR → roll the deployment, logs = tail backend/scheduler, psql = shell into the bundled postgres, down = tear everything down to stop spend.
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
adr-supersede
Create a new ADR that supersedes an existing one.
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
install
This page explains how the livewiki install CLI command detects installed coding agents and safely configures the livewiki MCP server entry, hook templates, shared skills, and optional pointer files.