agentmods.dev

dbhub CLAUDE.md

Project-specific instructions for DBHub, a lightweight server that connects AI tools to different databases through the Model Context Protocol. They cover development commands, architecture, configuration, and its Claude Code plugin.

In plain words
What is it for?
Use them when developing DBHub, working on database connectors or configuration, or validating and testing its Claude Code plugin.
Why use it?
They provide the repository rules and setup details needed to build, run, test, and modify DBHub safely.

Instructions file

3.4k today C scan 3,646 tokens original MIT
View the source file bytebase/dbhub
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/bytebase/dbhub/claude-md
Clone the repo
git clone --depth 1 https://github.com/bytebase/dbhub
Per session 3,646 This file is loaded in full into every session.
When invoked 3,646 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.03646 $0.03646
Opus 5 $0.01823 $0.01823
Sonnet 5 $0.00729 $0.00729
Haiku 4.5 $0.00365 $0.00365

Measured 2d ago against content hash b1697fa1ee0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

dbhub CLAUDE.md scanned grade C with 1 finding 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Default SSH key detection (tries `~/.ssh/id_rsa`, `~/.ssh/id_ed25519`, etc.)
CLAUDE.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 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.

DBHub Development Guidelines

DBHub is a zero-dependency, token efficient database MCP server implementing the Model Context Protocol (MCP) server interface. This lightweight server bridges MCP-compatible clients (Claude Desktop, Claude Code, Cursor) with various database systems.

Commands

  • Build: pnpm run build - Compiles TypeScript to JavaScript using tsup
  • Start: pnpm run start - Runs the compiled server
  • Dev: pnpm run dev - Runs server with tsx (no compilation needed)
  • Test: pnpm test - Run all tests
  • Test Watch: pnpm test:watch - Run tests in watch mode
  • Integration Tests: pnpm test:integration - Run database integration tests (requires Docker)
  • Claude Code Plugin: plugin/ packages DBHub as a Claude Code plugin — .mcp.json launches npx @bytebase/dbhub (pinned to the plugin version) against the bundled read-only plugin/dbhub.toml (DSN prompted via userConfig in plugin/.claude-plugin/plugin.json, passed as DBHUB_DSN), plus /dbhub:setup and /dbhub:explore skills. Validate with claude plugin validate ./plugin; test with claude --plugin-dir ./plugin.
  • Versioning: package.json is the single source of truth. pnpm version <bump> bumps it and auto-runs scripts/sync-version.mjs, which propagates the version into plugin/.claude-plugin/plugin.json, plugin/.mcp.json, and server.json (files that can't be stamped at build time — the plugin is read straight from git with no build step, and server.json's own version is what the npm publish workflow (.github/workflows/npm-publish.yml) checks against the MCP Registry before republishing — the registry publish runs as a post-step of that same workflow, after the npm publish succeeds). mcpb/manifest.json needs no sync — scripts/build-mcpb.mjs stamps it from package.json at build time. src/__tests__/plugin-consistency.test.ts fails CI if any of these drift from package.json, or if plugin/dbhub.toml diverges from mcpb/dbhub.toml.
  • MCP Bundle: pnpm run build:mcpb - Package DBHub as an .mcpb bundle for MCPB-compatible clients (Claude Desktop, Claude Code, MCP for Windows; see mcpb/ and scripts/build-mcpb.mjs); pnpm run test:mcpb smoke-tests the packed bundle over stdio. Published to GitHub releases by .github/workflows/mcpb-release.yml. The bundle is read-only by design (mcpb/dbhub.toml), with the DSN supplied via the DBHUB_DSN env var declared in mcpb/manifest.json (TOML ${ENV_VAR} interpolation).

Read the full file on GitHub · 222 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 · 222 lines · 3,646 tokens per session scan C b1697fa1ee0d

Subscribe to this mod's changes

dbhub CLAUDE.md is an instructions file published in the GitHub repository bytebase/dbhub (3,439 stars, last pushed today), licensed MIT. It adds 3,646 tokens to every session, about $0.0182 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DatabasesPlanningaianthropicclaudemcpmcp-server
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens