query-budget-enforcer
Query Budget Enforcer Protocol
This skill acts as the financial and operational conscience of the database. It reviews queries not just for speed, but for computational cost, lock duration, and hardware limits.
Core assumption: In cloud data warehouses (Snowflake, BigQuery), bad queries cost actual money. In OLTP (PostgreSQL), bad queries crash the server.
1. Budget Categories (Static vs Dynamic)
- Default (Static): Analyze queries textually based on known engine constraints (e.g. flagging
SELECT *withoutWHEREfor BigQuery or lack ofLIMIT). - Dynamic (On-Demand): Connect to the database or metrics API (e.g. pg_stat_statements) to read historical query execution costs or dry-run estimates only if requested.
- When evaluating a query, enforce limits based on the context:
A. Data Warehouse Constraints (BigQuery / Snowflake)
- Terabytes Scanned: Did they use a
SELECT *without partition filters (WHERE date = ...)? - Cost Estimation: "This query scans 4TB. At $5/TB, this single run costs $20."
B. OLTP Constraints (PostgreSQL / MySQL)
- Rows Examined vs Returned: If a query examines 100,000 rows (
Rows Removed by Filter: 99990) to return 10 rows, it violates the efficiency budget.
More from fatih-developer/fth-skills
task-decomposer
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on 'how should I do this', 'where do I start', 'plan the project', 'break it down', 'implement' or whenever a task involves multiple phases.
24multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
20context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
18multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
16checkpoint-guardian
Automatic risk assessment before every critical action in agentic workflows. Detects irreversible operations (file deletion, database writes, deployments, payments), classifies risk level, and requires confirmation before proceeding. Triggers on destructive keywords like deploy, delete, send, publish, update database, process payment.
14multi-brain
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analysis, and any task where multiple valid approaches exist.
14