database

A command-line tool for working with SQLite, PostgreSQL, and MySQL databases. It supports running SQL, inspecting database structure, and managing stored data.

In plain words
What is it for?
Use it to connect to databases, query or change records, create or alter tables, inspect schemas, manage indexes, examine query performance, and back up or restore data.
Why use it?
It keeps database work in the terminal and provides one reference for common tasks across three database systems.

Skill for Claude CodeCodex

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 skills/bug-ops/zeph/database
Any agent
npx skills add bug-ops/zeph --skill database
Clone the repo
git clone --depth 1 https://github.com/bug-ops/zeph

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,132 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 $0.00076 $0.03132
Opus 5 $0.00038 $0.01566
Sonnet 5 $0.00015 $0.00626
Haiku 4.5 $0.00008 $0.00313

Measured 2d ago against content hash e5c147a312ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

database 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 2d 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.

.zeph/skills/database/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database CLI Operations

Quick Reference

Action SQLite PostgreSQL MySQL
Connect sqlite3 db.sqlite psql -U user -d dbname mysql -u user -p dbname
List databases .databases \l SHOW DATABASES;
List tables .tables \dt SHOW TABLES;
Describe table .schema tablename \d tablename DESCRIBE tablename;
Quit .quit \q \q or exit
Run file .read file.sql \i file.sql source file.sql

SQLite (sqlite3)

Connection and Configuration

# Open or create a database
sqlite3 mydb.sqlite

# Open read-only
sqlite3 -readonly mydb.sqlite

# Execute SQL directly (non-interactive)
sqlite3 mydb.sqlite "SELECT * FROM users;"

# Execute SQL from file
sqlite3 mydb.sqlite < queries.sql
sqlite3 mydb.sqlite ".read queries.sql"

# Output modes
sqlite3 mydb.sqlite -header -column "SELECT * FROM users;"
sqlite3 mydb.sqlite -json "SELECT * FROM users;"
sqlite3 mydb.sqlite -csv "SELECT * FROM users;"
sqlite3 mydb.sqlite -markdown "SELECT * FROM users;"

Dot Commands

.help                    # List all dot commands
.tables                  # List all tables
.tables %user%           # List tables matching pattern
.schema                  # Show CREATE statements for all tables
.schema users            # Show CREATE statement for specific table
.indexes                 # List all indexes
.indexes users           # List indexes for specific table
.headers on              # Show column headers
.mode column             # Columnar output (also: csv, json, markdown, table, line)
.width 20 10 30          # Set column widths
.timer on                # Show query execution time
.dbinfo                  # Show database metadata
.dump                    # Dump entire database as SQL
.dump users              # Dump specific table
.import file.csv users   # Import CSV into table
.output result.txt       # Redirect output to file
.output stdout           # Reset output to terminal
.changes on              # Show number of rows changed
.eqp on                  # Show query plan automatically

Read the full file on GitHub · 461 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. 2d ago First seen · 461 lines · 76 tokens per session scan A e5c147a312ec

Subscribe to this mod's changes

database is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 3,132 once invoked, about $0.0004 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.