postgres-readonly-queries
Lets your agent safely read data from PostgreSQL databases. It ensures data isn't accidentally changed.
What it does
This agent lets you safely ask questions to PostgreSQL databases, only reading data. It connects to different databases you set up and ensures you don't accidentally change anything.
When to use it
- ✓When you need to view data in a PostgreSQL database without the risk of altering it.
- ✓When exploring the tables and columns of a database.
- ✓To check specific information in a database, like a list of customers or orders.
Example of what to ask your AI
“List the first 10 users from the production database.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You set up the connection details for your PostgreSQL databases in a file. Then, you can ask the agent to run SQL queries (commands to retrieve data) that are always read-only, ensuring safety.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill postgres-readonly-queriesOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/skills/postgres-readonly-queries/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
PostgreSQL Read-Only Query Skill
When to Use
- Use when querying PostgreSQL databases and access must stay strictly read-only
- Use when exploring schemas, tables, and data across multiple configured connections
- Use when you want defense-in-depth protection against accidental INSERT/UPDATE/DELETE or DDL
Execute safe, read-only queries against configured PostgreSQL databases.
Requirements
- Python 3.8+
- psycopg2-binary:
pip install -r requirements.txt
Setup
Create connections.json in the skill directory or ~/.config/claude/postgres-connections.json.
Security: Set file permissions to 600 since it contains credentials:
chmod 600 connections.json
{
"databases": [
{
"name": "production",
"description": "Main app database - users, orders, transactions",
"host": "db.example.com",
"port": 5432,
"database": "app_prod",
"user": "readonly_user",
"password": "your-password",
"sslmode": "require"
}
]
}
Config Fields
| Field | Required | Description |
|---|---|---|
| name | Yes | Identifier for the database (case-insensitive) |
| description | Yes | What data this database contains (used for auto-selection) |
| host | Yes | Database hostname |
| port | No | Port number (default: 5432) |
| database | Yes | Database name |
| user | Yes | Username |
| password | Yes | Password |
| sslmode | No | SSL mode: disable, allow, prefer (default), require, verify-ca, verify-full |
Usage
List configured databases
python3 scripts/query.py --list
Query a database
python3 scripts/query.py --db production --query "SELECT * FROM users LIMIT 10"
List tables
python3 scripts/query.py --db production --tables
Show schema
python3 scripts/query.py --db production --schema
Limit results
python3 scripts/query.py --db production --query "SELECT * FROM orders" --limit 100
Database Selection
Match user intent to database description:
| User asks about | Look for description containing |
|---|---|
| users, accounts | users, accounts, customers |
| orders, sales | orders, transactions, sales |
| analytics, metrics | analytics, metrics, reports |
| logs, events | logs, events, audit |
If unclear, run --list and ask user which database.
Safety Features
- Read-only session: Connection uses PostgreSQL
readonly=Truemode (primary protection) - Query validation: Only SELECT, SHOW, EXPLAIN, WITH queries allowed
- Single statement: Multiple statements per query rejected
- SSL support: Configurable SSL mode for encrypted connections
- Query timeout: 30-second statement timeout enforced
- Memory protection: Max 10,000 rows per query to prevent OOM
- Column width cap: 100 char max per column for readable output
- Credential sanitization: Error messages don't leak passwords
Troubleshooting
| Error | Solution |
|---|---|
| Config not found | Create connections.json in skill directory |
| Authentication failed | Check username/password in config |
| Connection timeout | Verify host/port, check firewall/VPN |
| SSL error | Try "sslmode": "disable" for local databases |
| Permission warning | Run chmod 600 connections.json |
Exit Codes
- 0: Success
- 1: Error (config missing, auth failed, invalid query, database error)
Workflow
- Run
--listto show available databases - Match user intent to database description
- Run
--tablesor--schemato explore structure - Execute query with appropriate LIMIT
Limitations
- Read-only protections reduce accidental writes but cannot override database-server policy, triggers, extensions, or an over-privileged account. Use a database role with read-only permissions as the primary control.
- Query results can contain personal, confidential, or regulated data. Confirm the intended database and avoid exporting or sharing results without explicit authorization.
- The script is not a replacement for backups, auditing, access reviews, or production change controls.
FAQ
What happens if I try to change data?
The agent is designed to prevent changes. It only allows read commands (like SELECT) and has extra protections to stop you from accidentally modifying or deleting data.
How does the agent know which database to connect to?
You can list the configured databases and choose one by name or description. The agent also tries to guess which database you want based on your question.
Is it safe to put my passwords in?
Yes, as long as you follow the security instructions. Passwords are in a special configuration file that should have restricted permissions (only you can read/write), and the agent doesn't show passwords in error messages.
Details
Original description by the author
Execute safe read-only SQL queries against PostgreSQL databases with multi-connection support and defense-in-depth write protection.
Popularity
- GitHub stars
- 48k
- Ranking position
- #4677
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
clickhouse-io
Helps your agent optimize queries and schemas in ClickHouse databases. It applies best practices for high-performance analytical workloads. Use when analytical queries are too slow.
affaan-m/ECC
scientific-db-pubmed-database
Helps your agent search for scientific articles in the biomedical field. It's useful for research needing specific medical information.
affaan-m/ECC
scientific-db-uspto-database
Allows the agent to look up official US patent and trademark data. It's useful for intellectual property research.
affaan-m/ECC