db-mcp copilot-instructions.md

Project guidance for db-mcp, a TypeScript server that lets AI agents work with SQLite databases through the Model Context Protocol. It covers code review context, project structure, coding rules, and session handoffs.

In plain words
What is it for?
Reviewing db-mcp code, following its TypeScript and naming conventions, checking recent project work, and working with its tests and SQLite integrations.
Why use it?
It gives an agent the project-specific background and review rules it needs before changing or reviewing code. It also points to recent development notes and uses the current GitHub Copilot command.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/neverinfamous/db-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/neverinfamous/db-mcp

Made for: GitHub Copilot.

Per session 1,088 This file is loaded in full into every session.
When invoked 1,088 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01088 $0.01088
Opus 5 $0.00544 $0.00544
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 2d ago against content hash 5a800e532954, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

db-mcp copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

db-mcp — Copilot Code Review Context

Project Overview

db-mcp is a TypeScript MCP (Model Context Protocol) server for SQLite database integration. It offers 181 Native / 154 WASM tools with dual backends — native (better-sqlite3) for full performance and WASM (sql.js) for zero-dependency portability. Features include Code Mode (sandboxed JS execution), HTTP/SSE transport, OAuth 2.1, Tool Filtering, and Audit/Token Logging.

Stack: TypeScript, Vitest, Playwright (E2E), Zod schemas, better-sqlite3 (native), sql.js (WASM), Commander (CLI).

Note: For any CLI interactions involving Copilot, you must reference gh copilot and NEVER the deprecated github-copilot-cli.

Session Context

Before starting work on this project, read memory://briefing/db-mcp from the memory-journal-mcp server for real-time context:

  • Recent journal entries — what was just worked on by the development agent
  • GitHub status — open issues, PRs, CI status, milestones
  • Workflow runs — recent CI/CD results
  • Copilot review summaries — your own recent review findings

For detailed session handoff context, search for entries tagged session-summary — these contain end-of-session notes from the development agent.

If you find issues during code review, use create_entry with tag copilot-finding to record them for the development agent to see in their next session briefing.

Coding Standards

Naming

  • Files and folders: Always kebab-case (database-adapter.ts, tool-filter.ts)
  • Never PascalCase or camelCase for filenames

Modularity

  • File size limit: Source files stay under ~500 lines
  • Split pattern: foo.tsfoo/ directory with sub-modules + foo/index.ts barrel re-export
  • Logical grouping: Split by functional cohesion, not arbitrary line counts

Type Safety

  • Strict TypeScripttsconfig.json enforces strict mode
  • Never use eslint-disable to evade standards
  • Never use any — use unknown and narrow with type guards
  • Never use as type assertions — use satisfies operator or strict type guards
  • Never use @ts-ignore or @ts-expect-error — fix the underlying type issue
  • Zod schemas for all tool input validation at system boundaries
  • Union types over enums — use type Status = "active" | "inactive" instead of enum

Read the full file on GitHub · 104 lines

Changes

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.

  1. 2d ago First seen · 104 lines · 1,088 tokens per session scan A 5a800e532954

Subscribe to this mod's changes

db-mcp copilot-instructions.md is an instructions file published in the GitHub repository neverinfamous/db-mcp (11 stars, last pushed 5d ago), licensed MIT. It adds 1,088 tokens to every session, about $0.0054 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 2026-08-30.