What is databid CLAUDE.md?

Repository instructions for DataBid, a company-intelligence platform where AI agents can obtain structured information about businesses through an API.

Use them when running the app, building or linting it, working with Prisma, or changing DataBid's company-context and agent-facing features.

They explain the product, current development stage, required Node.js version, local commands, and database workflow before code changes begin.

How indiano881/databid configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to indiano881/databid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/indiano881/databid/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/indiano881/databid

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/indiano881/databid/claude-md/github.svg)](https://agentmods.dev/instructions/indiano881/databid/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/indiano881/databid/claude-md"><img src="https://agentmods.dev/badge/instructions/indiano881/databid/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/indiano881/databid/claude-md"><img src="https://agentmods.dev/badge/instructions/indiano881/databid/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,772 This file is loaded in full into every session.

When invoked 1,772 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01772	$0.01772
Opus 5.5	$0.00709	$0.00709
Sonnet 5.5	$0.00354	$0.00354
Haiku 4.5	$0.00177	$0.00177

Measured 2mo ago against content hash baa3ae231b4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

databid 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 2mo 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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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

Context on Call (running on DataBid infrastructure at databid.io) is an agent-native company intelligence platform. AI agents buy structured, verified company context (capabilities, certifications, capacity, standards) on demand via API. Companies list themselves to get discovered by agents worldwide — "SEO for the agent era."

Current phase: Validation. Seeding first 100 company contexts in manufacturing/supply chain vertical. 13 companies live (3 seeded, 10 scraped). No paying customers yet. See ACTION_PLAN.md for milestones.

Future product: A Context Constructor — guided flow that asks companies the right questions and generates standardized, token-efficient context packs (chunked files + navigation index) sized for agent context windows.

Commands

Requires Node 20+.

# Dev server
npm run dev          # Start dev server (http://localhost:3000)
npm run build        # Production build (runs prisma generate automatically)
npm run lint         # ESLint (flat config, v9)

# Prisma
npx prisma generate                   # Regenerate client after schema changes
npx prisma migrate dev --name <name>  # Create and apply a migration (local dev)
npx prisma db push                    # Push schema to Neon (no advisory lock issues)

# Company scraper (requires ANTHROPIC_API_KEY in .env)
npx tsx scripts/scrape-company.ts "Company Name" "https://example.com"

# List all companies in DB
npx tsx scripts/list-companies.ts

# Seed test companies (3 hardcoded)
npx tsx prisma/seed-companies.ts

No test framework is set up. No test runner commands exist.

Architecture

Framework: Next.js 16 (App Router) with TypeScript and Tailwind CSS v4. next.config.ts sets output: "standalone" for Docker/containerized deployments. Check node_modules/next/dist/docs/ for breaking changes vs older Next.js.
Database: PostgreSQL via Prisma ORM v7 (requires @prisma/adapter-pg)
Auth: NextAuth.js with credentials + Google OAuth, JWT sessions
Styling: Tailwind v4 CSS-first config (@import "tailwindcss" in globals.css, no tailwind.config.js). Zinc/emerald color palette.
No component library: src/components/ui/ exists but is empty. All UI is plain Tailwind.
No middleware: Auth is checked per-route via getServerSession(authOptions), not via Next.js middleware.
Schema validation: Zod used in MCP tool definitions; API routes use manual if checks.

Read the full file on GitHub · 127 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.

2mo ago First seen · 127 lines · 1,772 tokens per session scan A baa3ae231b4c

Subscribe to this mod's changes

databid CLAUDE.md is an instructions file published in the GitHub repository indiano881/databid (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,772 tokens to every session, about $0.0071 per session on Opus 5.5. 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.

databid CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
databid CLAUDE.mdindiano881/databid	Instructions file	0	7mo ago	MIT	A	1,772	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

databid: Instructions file for Claude Code