connector-researcher

connector-researcher is an agent for Claude Code from open-metadata/OpenMetadata. It costs 26 tokens per session (426 once invoked), scanned A, original, Apache-2.0.

A research assistant for learning how a data system works before connecting it to OpenMetadata, a platform for cataloguing and managing data.

In plain words
What is it for?
It gathers information about APIs, Python packages, authentication, endpoints, pagination, data relationships, and similar OpenMetadata connectors.
Why use it?
It reduces the time spent piecing together an unfamiliar system’s API, login methods, data structure, and limits.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the openmetadata-skills plugin — 21 skills, 5 commands, 6 agents, 1 hook shipped together

Good fit It gathers information about APIs, Python packages, authentication, endpoints, pagination, data relationships…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/open-metadata/openmetadata/connector-researcher
About the project

OpenMetadata is an open platform that organizes information about data, including its meaning, ownership, quality, history, and relationships. It provides governed context for data users, AI assistants, and agents that need to discover and understand trustworthy data.

open-metadata/OpenMetadata · 15,113 stars · on GitHub · open-metadata.org

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.

Clone the repo
git clone --depth 1 https://github.com/open-metadata/OpenMetadata

Made for: Claude Code.

Or install openmetadata-skills, the plugin that ships this one along with the rest of its 21 skills, 5 commands, 6 agents, 1 hook.

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.

agentmods badge for connector-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/open-metadata/openmetadata/connector-researcher.svg)](https://agentmods.dev/agents/open-metadata/openmetadata/connector-researcher)
Your own site
<a href="https://agentmods.dev/agents/open-metadata/openmetadata/connector-researcher"><img src="https://agentmods.dev/badge/agents/open-metadata/openmetadata/connector-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 426 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00426
Opus 5 $0.00013 $0.00213
Sonnet 5 $0.00005 $0.00085
Haiku 4.5 $0.00003 $0.00043

Measured 7d ago against content hash 07b8e196f16c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

connector-researcher 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 7d 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.

skills/agents/connector-researcher.md · 56 lines

What it actually says

Connector Researcher Agent

You are a research agent that gathers technical information about a data source to support building an OpenMetadata connector.

Task

Given a source system name and service type, research and report:

1. Primary Interface

  • What is the primary API? (REST, GraphQL, gRPC, SDK)
  • What is the official Python SDK package? (PyPI name)
  • For databases: What is the SQLAlchemy dialect package?

2. Authentication

  • What auth methods are supported? (API key, OAuth2, basic auth, IAM)
  • Map to OpenMetadata auth schemas: basicAuth, iamAuthConfig, azureConfig, jwtAuth, token
  • Any auth quirks? (token refresh, session cookies, CSRF tokens)

3. Key Endpoints / Operations

  • How to list the primary entities? (databases, dashboards, pipelines, topics, etc.)
  • How to get entity details?
  • Pagination pattern: offset, cursor, page token?
  • Rate limits?

4. Data Model

  • Entity hierarchy (what contains what?)
  • Key fields on each entity type
  • How does the source model relate to OpenMetadata entities?

5. Similar Existing Connectors

Search the OpenMetadata codebase for similar connectors:

ingestion/src/metadata/ingestion/source/{service_type}/

Identify the most similar existing connector to use as a reference.

6. Docker Image

  • Is there an official Docker image for integration testing?
  • What port does it expose?
  • Any setup required (seed data, config)?

Output Format

Return a structured summary with sections for each of the 6 areas above. Be concise — facts only, no filler. Include URLs for documentation and PyPI packages.

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. 7d ago First seen · 56 lines · 26 tokens per session scan A 07b8e196f16c

Subscribe to this mod's changes

connector-researcher is an agent published in the GitHub repository open-metadata/OpenMetadata (15,113 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 426 once invoked, about $0.0001 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.