setup

An interactive setup command for a SQL development environment using sql-language-server, a tool that understands SQL code, plus sqlfluff for checking and formatting SQL.

In plain words
What is it for?
Use it to prepare a machine for SQL work by installing the language server and sqlfluff, checking their versions, and optionally creating a .sqlfluff configuration.
Why use it?
It verifies required runtimes, installs the SQL tools, and can create project settings such as the SQL dialect and style rules.

Command

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/zircote/sql-lsp/setup
Clone the repo
git clone --depth 1 https://github.com/zircote/sql-lsp
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 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 $0.00008 $0.00951
Opus 5 $0.00004 $0.00476
Sonnet 5 $0.00002 $0.00190
Haiku 4.5 $0.00001 $0.00095

Measured yesterday against content hash 261712bf623c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

commands/setup.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQL LSP Setup

This command will configure your SQL development environment with sql-language-server LSP and sqlfluff for linting and formatting.

Prerequisites Check

Verify you have Node.js and Python installed:

node --version
python --version || python3 --version

Installation Steps

1. Install sql-language-server (LSP)

npm install -g sql-language-server

Verify installation:

sql-language-server --version

2. Install sqlfluff (Linter & Formatter)

pip install sqlfluff

Or with pipx for isolated installation:

pipx install sqlfluff

Verify installation:

sqlfluff --version

3. Create Project Configuration (Optional)

Create a .sqlfluff configuration file in your project root:

cat > .sqlfluff << 'EOF'
[sqlfluff]
# Set your SQL dialect
dialect = postgres
# Options: postgres, mysql, sqlite, bigquery, redshift, snowflake, tsql, etc.

[sqlfluff:rules]
max_line_length = 120
indent_unit = space
tab_space_size = 4

[sqlfluff:rules:L010]
# Keywords should be upper case
capitalisation_policy = upper

[sqlfluff:rules:L030]
# Function names should be upper case
capitalisation_policy = upper

[sqlfluff:rules:L014]
# Unquoted identifiers should be lower case
capitalisation_policy = lower
EOF

4. Verify LSP Configuration

Check that .lsp.json exists and is properly configured:

cat .lsp.json

Expected configuration:

{
    "sql": {
        "command": "sql-language-server",
        "args": ["up", "--method", "stdio"],
        "extensionToLanguage": {
            ".sql": "sql"
        },
        "transport": "stdio"
    }
}

5. Test sqlfluff

Test sqlfluff on a sample SQL file:

# Create test file
cat > test.sql << 'EOF'
select * from users where id = 1;
EOF

# Lint the file
sqlfluff lint test.sql

# Format the file
sqlfluff format test.sql

# Clean up
rm test.sql

Supported SQL Dialects

sqlfluff supports multiple SQL dialects. Configure in .sqlfluff:

Read the full file on GitHub · 192 lines

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. yesterday First seen · 192 lines · 8 tokens per session scan A 261712bf623c

Subscribe to this mod's changes

setup is a command published in the GitHub repository zircote/sql-lsp (1 stars, last pushed 22d ago), licensed MIT. It adds 8 tokens to every session and 951 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 2026-08-31.