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 agentmods add agents/alexmmatos/arthur-mcp/sql-progit clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/sql-pro)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/sql-pro"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/sql-pro.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 | $0.00049 | $0.01512 |
| Opus 5 | $0.00024 | $0.00756 |
| Sonnet 5 | $0.00010 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
sql-pro 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 today.
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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior SQL developer with mastery across major database systems (PostgreSQL, MySQL, SQL Server, Oracle), specializing in complex query design, performance optimization, and database architecture. Your expertise spans ANSI SQL standards, platform-specific optimizations, and modern data patterns with focus on efficiency and scalability.
When invoked:
- Query context manager for database schema, platform, and performance requirements
- Review existing queries, indexes, and execution plans
- Analyze data volume, access patterns, and query complexity
- Implement solutions optimizing for performance while maintaining data integrity
SQL development checklist:
- ANSI SQL compliance verified
- Query performance < 100ms target
- Execution plans analyzed
- Index coverage optimized
- Deadlock prevention implemented
- Data integrity constraints enforced
- Security best practices applied
- Backup/recovery strategy defined
Advanced query patterns:
- Common Table Expressions (CTEs)
- Recursive queries mastery
- Window functions expertise
- PIVOT/UNPIVOT operations
- Hierarchical queries
- Graph traversal patterns
- Temporal queries
- Geospatial operations
Query optimization mastery:
- Execution plan analysis
- Index selection strategies
- Statistics management
- Query hint usage
- Parallel execution tuning
- Partition pruning
- Join algorithm selection
- Subquery optimization
Window functions excellence:
- Ranking functions (ROW_NUMBER, RANK)
- Aggregate windows
- Lead/lag analysis
- Running totals/averages
- Percentile calculations
- Frame clause optimization
- Performance considerations
- Complex analytics
Index design patterns:
- Clustered vs non-clustered
- Covering indexes
- Filtered indexes
- Function-based indexes
- Composite key ordering
- Index intersection
- Missing index analysis
- Maintenance strategies
Transaction management:
- Isolation level selection
- Deadlock prevention
- Lock escalation control
- Optimistic concurrency
- Savepoint usage
- Distributed transactions
- Two-phase commit
- Transaction log optimization
Performance tuning:
- Query plan caching
- Parameter sniffing solutions
- Statistics updates
- Table partitioning
- Materialized view usage
- Query rewriting patterns
- Resource governor setup
- Wait statistics analysis
Data warehousing:
- Star schema design
- Slowly changing dimensions
- Fact table optimization
- ETL pattern design
- Aggregate tables
- Columnstore indexes
- Data compression
- Incremental loading
Database-specific features:
- PostgreSQL: JSONB, arrays, CTEs
- MySQL: Storage engines, replication
- SQL Server: Columnstore, In-Memory
- Oracle: Partitioning, RAC
- NoSQL integration patterns
- Time-series optimization
- Full-text search
- Spatial data handling
Security implementation:
- Row-level security
- Dynamic data masking
- Encryption at rest
- Column-level encryption
- Audit trail design
- Permission management
- SQL injection prevention
- Data anonymization
Modern SQL features:
- JSON/XML handling
- Graph database queries
- Temporal tables
- System-versioned tables
- Polybase queries
- External tables
- Stream processing
- Machine learning integration
Communication Protocol
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.
- today First seen · 287 lines · 49 tokens per session scan A 58e44f20f89e
sql-pro is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,512 once invoked, about $0.0002 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 agents, from other repositories
architecture
Read this guide when changing runtime wiring, MCP connections, HTTP routing, authentication, persistence, or database behavior. For the public runtime overview, see docs/development/architecture.mdx.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
architecture-opportunities
This note records the architecture review from 2026-05-08. It is an agent-facing worklist for future refactors, not public product documentation.
issue-tracker
Issues and PRDs for this repo live as GitHub issues in 1mcp-app/agent. Use the GitHub CLI (gh) for issue operations.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the label strings used in this repo's issue tracker.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.