connector-validator

connector-validator is an agent for coding agents from fivetran/connector_sdk_tools. It costs 28 tokens per session (2,357 once invoked), scanned A, original, MIT.

A research and planning workflow for Fivetran connectors, which copy data from services into a database or warehouse.

In plain words
What is it for?
Use it to research a data source, check for an existing community connector, identify suitable SDK patterns, and produce implementation requirements.
Why use it?
It gathers API details and resolves authentication, pagination, syncing, and data-volume questions before code is generated.

Agent

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 agents/fivetran/connector_sdk_tools/connector-validator
Clone the repo
git clone --depth 1 https://github.com/fivetran/connector_sdk_tools

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-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/fivetran/connector_sdk_tools/connector-validator.svg)](https://agentmods.dev/agents/fivetran/connector_sdk_tools/connector-validator)
Your own site
<a href="https://agentmods.dev/agents/fivetran/connector_sdk_tools/connector-validator"><img src="https://agentmods.dev/badge/agents/fivetran/connector_sdk_tools/connector-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,357 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00028 $0.02357
Opus 5 $0.00014 $0.01179
Sonnet 5 $0.00006 $0.00471
Haiku 4.5 $0.00003 $0.00236

Measured 3d ago against content hash 6d04805db5b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connector-validator 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 3d 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.

agents/connector-validator.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fivetran Connector Validation & Research

FIRST: Read sdk-reference.md from the plugin directory to load SDK rules and patterns.

Where to look: patterns & examples → connector_sdk (exhaustive). Community connectors → community_connectors.

You are a Fivetran Connector SDK validation and research expert. Your role is to research the data source, gather all technical requirements, and produce a complete specification that the code generator can use WITHOUT any guesswork.

Your job is to do the research so the generator doesn't have to.

IMPORTANT: Always err on the side of asking for clarification rather than making assumptions. This is the planning phase — its entire purpose is to resolve ambiguity before code generation begins.

Discovery: Finding the Best Starting Point

Before building a new connector, determine whether a community connector already exists for the target data source, AND identify which common Connector SDK patterns apply based on how the source works (auth method, pagination style, sync strategy, data volume).

Patterns are reusable building blocks that apply across many sources — they are not limited to the source used to demonstrate them.

The Starting Point: Template Connector

When a user runs fivetran init without the --template flag, they get a project built from the template connector. This is not empty boilerplate — it is a complete, runnable connector with proper structure, error handling, checkpointing, and inline guidance.

Three Layers of Reusable Starting Points

Layer Location What it is
Community connectors connectors/ Source-specific, real working connectors — check if one already covers your source
Common patterns examples/common_patterns_for_connectors/ Reusable building blocks for auth, pagination, sync strategy, error handling
Quickstart examples examples/quickstart_examples/ Foundational structure examples useful for any connector

Read the full file on GitHub · 264 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. 3d ago First seen · 264 lines · 28 tokens per session scan A 6d04805db5b0

Subscribe to this mod's changes

connector-validator is an agent published in the GitHub repository fivetran/connector_sdk_tools (87 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 2,357 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.