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 instructions/tkmawarire/sql-sentinel/claude-mdgit clone --depth 1 https://github.com/tkmawarire/sql-sentinelWrote 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/instructions/tkmawarire/sql-sentinel/claude-md)<a href="https://agentmods.dev/instructions/tkmawarire/sql-sentinel/claude-md"><img src="https://agentmods.dev/badge/instructions/tkmawarire/sql-sentinel/claude-md.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 | $0.00944 | $0.00944 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
sql-sentinel CLAUDE.md 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
SQL Sentinel MCP Server (v2.3.0) - a .NET 9 MCP (Model Context Protocol) server for SQL Server monitoring, diagnostics, and database operations using Extended Events and DMVs. Provides query profiling, deadlock detection, blocking analysis, wait stats, intelligent diagnostics, and CRUD database tools. Uses Microsoft.Data.SqlClient for native SQL Server connectivity (no ODBC drivers required).
Build Commands
# Restore and build
dotnet restore
dotnet build
# Run the server
dotnet run
# Publish single executable (pick your platform)
dotnet publish -c Release -r win-x64 --self-contained
dotnet publish -c Release -r linux-x64 --self-contained
dotnet publish -c Release -r osx-x64 --self-contained
dotnet publish -c Release -r osx-arm64 --self-contained
Output location: bin/Release/net9.0/{runtime}/publish/
Architecture
Program.cs # Entry point, DI setup, MCP server config
├── Services/
│ ├── ProfilerService.cs # Core Extended Events logic (IProfilerService)
│ ├── QueryFingerprintService.cs # SQL normalization & fingerprinting (IQueryFingerprintService)
│ ├── WaitStatsService.cs # DMV-based wait stats analysis (IWaitStatsService)
│ └── SessionConfigStore.cs # In-memory session config storage
├── Models/
│ ├── ProfilerModels.cs # Records, enums (SessionConfig, ProfilerEvent, DeadlockEvent, etc.)
│ └── DbOperationResult.cs # Result model for CRUD database operations
├── Utilities/
│ └── SqlInputValidator.cs # SQL input validation & escaping (shared across tools)
└── Tools/
├── SessionManagementTools.cs # MCP tools: create/start/stop/drop/list/quick_capture
├── EventRetrievalTools.cs # MCP tools: get_events/get_stats/analyze_sequence/get_connection_info
├── DiagnosticTools.cs # MCP tools: get_deadlocks/get_blocking/get_wait_stats/health_check
├── PermissionTools.cs # MCP tools: check_permissions/grant_permissions
└── DatabaseTools.cs # MCP tools: list_tables/describe_table/create_table/read_data/insert_data/update_data/drop_table
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 · 83 lines · 944 tokens per session scan A 9fb35ff31afc
sql-sentinel CLAUDE.md is an instructions file published in the GitHub repository tkmawarire/sql-sentinel (5 stars, last pushed 5mo ago), licensed MIT. It adds 944 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
mcp-mssql CLAUDE.md
Instructions for alyiox/mcp-mssql, a project described as: A read-only MCP server for Microsoft SQL Server that supports metadata discovery, parameterized queries, and query analysis.
dbhub copilot-instructions.md
Copilot instructions for bytebase/dbhub: This project provides an MCP server (DBHub) for secure SQL access to the development database.
trace-mcp CLAUDE.md
Instructions for nikolai-vysotskyi/trace-mcp, covering trace-mcp development guide, what this project is, agent behavior — read before every task, no flattery, no filler and disagree when the premise is wrong.
MCP-PostgreSQL-Ops copilot-instructions.md
Instructions for call518/MCP-PostgreSQL-Ops, covering architecture overview, core components, key patterns, in functions.py and development workflows.
NyxID CLAUDE.md
Instructions for ChronoAIProject/NyxID, covering project overview, critical rules, 1. mongodb model conventions, 2. layer architecture and 3. error handling.
FalkorDB-MCPServer AGENTS.md
Instructions for FalkorDB/FalkorDB-MCPServer, covering project guidelines, build & install, development, testing and pre-commit checks.