askdb CLAUDE.md

A concise map of important files and coding rules for AskDB, an application built with Express, React, TypeScript, Drizzle, SQLite, authentication, Docker, and MCP tools. It identifies the server, database schema, synchronisation code, dashboard, and MCP entry points.

In plain words
What is it for?
Use it when locating AskDB's core files or making changes to its server, database schema, synchronisation scheduler, adapters, dashboard, or MCP tools.
Why use it?
It helps an agent quickly find the right files and follow constraints such as additive schema changes, encrypted connection strings, and routing AI queries through MCP.

Instructions file

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/mgorabbani/askdb/claude-md
Clone the repo
git clone --depth 1 https://github.com/mgorabbani/askdb
Per session 200 This file is loaded in full into every session.
When invoked 200 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 $0.00200 $0.00200
Opus 5 $0.00100 $0.00100
Sonnet 5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured 2d ago against content hash 869281895064, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

askdb 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 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.

CLAUDE.md · 25 lines

What it actually says

@AGENTS.md

Key Paths

What Where
Server entry server/src/index.ts
DB schema packages/shared/src/db/schema.ts
Sync scheduler packages/shared/src/adapters/mongodb/scheduler.ts
Sync logic packages/shared/src/adapters/sync.ts
DB adapters packages/shared/src/adapters/{mongodb,postgresql}/
Dashboard pages ui/src/pages/dashboard/
MCP tools packages/mcp-server/src/index.ts

Tech Stack

Express, React, TypeScript, Drizzle ORM (SQLite), Better Auth, Docker API

Rules

  • SQLite via Drizzle — no migrations framework, schema changes are additive with safe defaults
  • Connection strings and passwords are AES-256-GCM encrypted
  • Sandbox containers are managed via Docker socket proxy
  • All AI queries go through MCP — never expose raw DB access
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 · 25 lines · 200 tokens per session scan A 869281895064

Subscribe to this mod's changes

askdb CLAUDE.md is an instructions file published in the GitHub repository mgorabbani/askdb (73 stars, last pushed 2mo ago), licensed MIT. It adds 200 tokens to every session, about $0.0010 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.