query

A command for running SQL queries, which are instructions for reading or changing data in a database, with help understanding and improving the query. It uses PostgreSQL, a database system.

In plain words
What is it for?
Use it to read data, add or change records, inspect database structure, and review query performance with execution plans.
Why use it?
It helps turn plain-language requests into SQL, checks risky changes, and identifies queries that may run slowly before execution.

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/cyperx84/claude-code-plugin-examples/query
Clone the repo
git clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examples
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 1,491 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 $0.01491
Opus 5 $0.00004 $0.00745
Sonnet 5 $0.00002 $0.00298
Haiku 4.5 $0.00001 $0.00149

Measured yesterday against content hash 4dc972a7508b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

examples/04-real-world/database-plugin/commands/query.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Database Query

Execute query: $ARGUMENTS

Using PostgreSQL MCP

1. Query Understanding

Parse and analyze the query request:

  • Natural Language: "Show me all users who signed up last month"
  • SQL Query: SELECT * FROM users WHERE created_at > '2024-09-01'
  • Query Type: SELECT, INSERT, UPDATE, DELETE, CREATE, ALTER

2. Safety Checks

Before Execution:

Safety Analysis:
✅ READ query - Safe to execute
⚠️  UPDATE without WHERE - DANGEROUS! Add confirmation
⚠️  DELETE without WHERE - DANGEROUS! Require explicit confirmation
⚠️  DROP TABLE - CRITICAL! Require double confirmation
⚠️  TRUNCATE - WARNING! Data loss, confirm

Confirmations Required:

  • Any DELETE/UPDATE without WHERE clause
  • DROP/TRUNCATE operations
  • Schema changes (ALTER)
  • Production database operations

3. Query Optimization

EXPLAIN Analysis:

-- Auto-run EXPLAIN before executing
EXPLAIN ANALYZE
SELECT * FROM users WHERE email LIKE '%@gmail.com';

-- Show execution plan:
Seq Scan on users  (cost=0.00..1234.56 rows=5000 width=100)
  Filter: (email ~~ '%@gmail.com'::text)
  Rows Removed by Filter: 45000

⚠️  Warning: Sequential scan detected!
Recommendation: Add index on email column

Optimization Suggestions:

-- ❌ Inefficient:
SELECT * FROM users WHERE email LIKE '%@gmail.com';
-- Sequential scan, checks all 50,000 rows

-- ✅ Better:
CREATE INDEX idx_users_email ON users(email);
SELECT * FROM users WHERE email LIKE '@gmail.com%';
-- Index scan, faster lookup

-- ✅ Even Better (if exact match):
SELECT * FROM users WHERE email = '[email protected]';
-- Index seek, optimal

4. Execute Query

Via PostgreSQL MCP:

// Execute through MCP
const result = await postgres.query(optimizedQuery);

// Return results
{
  rows: [...],
  rowCount: 42,
  executionTime: "125ms",
  fromCache: false
}

5. Format Results

Table Format:

┌──────┬─────────────┬───────────────────────┬────────────────────┐
│ id   │ username    │ email                 │ created_at         │
├──────┼─────────────┼───────────────────────┼────────────────────┤
│ 1    │ alice       │ [email protected]     │ 2024-09-15 10:30   │
│ 2    │ bob         │ [email protected]       │ 2024-09-16 14:22   │
│ 3    │ charlie     │ [email protected]   │ 2024-09-17 09:15   │
└──────┴─────────────┴───────────────────────┴────────────────────┘

Showing 3 of 42 rows (limited for display)
Query executed in: 125ms

Read the full file on GitHub · 256 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 · 256 lines · 8 tokens per session scan A 4dc972a7508b

Subscribe to this mod's changes

query is a command published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,491 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.