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 skills add j4flmao/agent-skills --skill relational-databasegit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/skills/j4flmao/agent-skills/relational-database)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/relational-database"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/relational-database.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 5.1 | $0.00148 | $0.06073 |
| Opus 5 | $0.00074 | $0.03037 |
| Sonnet 5 | $0.00030 | $0.01215 |
| Haiku 4.5 | $0.00015 | $0.00607 |
Grade A, and why
data-relational-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Relational Database
Purpose
Design relational database schemas with proper indexing, partitioning, replication, connection pooling, and query optimization strategies.
Agent Protocol
Trigger
Exact user phrases: "PostgreSQL", "MySQL", "relational database", "partitioning", "replication", "indexing", "vacuum", "connection pooling", "query optimization", "EXPLAIN", "CTE", "window function", "transaction isolation", "migration", "PgBouncer", "MVCC", "WAL", "B-tree", "GiST", "GIN", "BRIN".
Input Context
Before activating, verify:
- Database platform (PostgreSQL, MySQL, MariaDB, SQLite)
- Data volume (rows, growth rate, total size in GB/TB)
- Query workload (OLTP, OLAP, mixed)
- Current schema and migration tool (Alembic, Sqitch, Flyway, Liquibase)
- Existing indexing strategy and planner statistics
- Replication needs (read replicas, disaster recovery, logical replication)
- Connection pooling requirements (client count, max connections)
Output Artifact
Database schema with indexes, partition configuration, replication setup, and query optimization plan as SQL and YAML.
Response Format
-- Table DDL with partitioning
-- Index creation statements
-- Replication configuration
-- Migration statements
# Connection pool config
# Replication setup
# Vacuum settings
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Normalized schema with appropriate constraints (PK, FK, CHECK, UNIQUE)
- Indexing strategy covering slow queries (EXPLAIN ANALYZE output reviewed)
- Partitioning scheme configured for large tables
- Replication setup (streaming for HA, logical for data distribution)
- Connection pool configured (PgBouncer transaction mode default)
- Vacuum and autovacuum settings tuned
- Transaction isolation levels chosen per workload
- Migration plan with rollback strategy
Max Response Length
300 lines of SQL and configuration.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/cockroachdb-yugabyte.md 3.8 KB
- references/database-indexing.md 3.2 KB
- references/database-migration-strategies.md 3.5 KB
- references/distributed-sql-databases.md 4.0 KB
- references/postgres-advanced.md 3.6 KB
- references/query-optimization.md 3.3 KB
- references/relational-database-high-availability.md 14 KB
- references/relational-database-query-optimization.md 16 KB
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.
- 3d ago First seen · 511 lines · 148 tokens per session scan A 7ca68752bdb6
data-relational-database is a skill published in the GitHub repository j4flmao/agent-skills (21 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 6,073 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
database
Query and manage SQLite, PostgreSQL, and MySQL databases from the command line. Use when the user asks to run SQL queries, inspect database schemas, create or alter tables, import or export data, manage indexes, analyze query performance with EXPLAIN, back up or restore databases, or perform CRUD operations via…
postgresql-expert
Expert-level PostgreSQL database administration, advanced queries, performance tuning, and production operations. Use when the user mentions database, SQL, or performance, or when the task involves Advanced Data Types, Full-Text Search, Advanced Indexes, or Advanced Queries.
sql-executor
Write and execute PostgreSQL or Supabase SQL queries from natural-language requests. Use when the user wants to inspect schema, run read queries, validate data, or safely perform confirmed database changes.
wren-connection-info
Reference guide for Wren Engine connection info — explains required fields for all 18 supported data sources (PostgreSQL, MySQL, BigQuery, Snowflake, ClickHouse, Trino, DuckDB, Databricks, Spark, Athena, Redshift, Oracle, SQL Server, Apache Doris, S3, GCS, MinIO, local files). Covers sensitive field handling, Docker…
sql-analyst
SQL query expert for optimization, schema design, and data analysis.
postgres-expert
PostgreSQL expert for query optimization, indexing, extensions, and database administration.