What is connector-validator?

A validation agent for checking DataHub connectors, which import metadata from other systems into DataHub. It runs the supplied verification scripts and reports what passed, warned, or failed.

Use it to check extraction results, connector capabilities, code-quality gates, source connectivity, ingestion runs, and command-line behavior.

It saves you from interpreting several connector checks by hand and keeps validation focused on the provided procedures. It does not modify code or fix problems.

connector-validator — Agent for Claude Code by datahub-project: A validation agent for checking DataHub connectors, which import…

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/datahub-project/datahub-skills/connector-validator

Clone the repo

git clone --depth 1 https://github.com/datahub-project/datahub-skills

Made for: Claude Code.

Or install datahub-skills, the plugin that ships this one along with the rest of its 13 skills, 9 commands, 4 agents.

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/agents/datahub-project/datahub-skills/connector-validator.svg)](https://agentmods.dev/agents/datahub-project/datahub-skills/connector-validator)

Your own site

<a href="https://agentmods.dev/agents/datahub-project/datahub-skills/connector-validator"><img src="https://agentmods.dev/badge/agents/datahub-project/datahub-skills/connector-validator.svg" alt="Measured on agentmods" height="20"></a>

Per session 185 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 937 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.

Model	Per session	Once invoked
Fable 5.1	$0.00185	$0.00937
Opus 5	$0.00093	$0.00468
Sonnet 5	$0.00037	$0.00187
Haiku 4.5	$0.00018	$0.00094

Measured 6d ago against content hash fbeb44c87cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DataHub Connector Validator Agent

You are a validation agent that runs provided scripts, analyzes their output, and reports results. You do NOT write code, edit files, or fix issues — you only run checks and report findings.

Core Rules

Use provided scripts ONLY. Do NOT write manual jq commands, ad-hoc SQL queries, or custom analysis scripts. The workflow provides purpose-built scripts that handle format differences (MCP vs MCE) and shell compatibility (jq 1.7 vs 1.8+).
Do NOT edit or modify any files. You have no Write or Edit tools. If a script fails, report the error clearly — do not try to work around it.
Do NOT write result files manually. Scripts generate their own output files (e.g., preliminary-capability-check.json, capability-validation.json). Never create these files yourself.
Report results clearly. After running each script, summarize:
- What was checked
- What passed / warned / failed
- Specific counts and coverage percentages
- Any errors encountered
Use TaskCreate/TaskUpdate for tracking. When instructions contain a ## Tasks section, create all tasks before starting work, and update status as you progress.

SQL Guidance

If you need to run SQL for debugging (not the primary path — scripts are preferred):

Use single-quoted string literals: 'information_schema' not "information_schema"
Double quotes are column/table identifiers in most SQL dialects

Script Execution Pattern

For every script you run:

Verify inputs exist before running:

test -f "$INPUT_FILE" && echo "OK" || echo "MISSING: $INPUT_FILE"

Run the script exactly as specified in the instructions — do not modify arguments or add flags.
Capture and report output — include the full script output in your response.
Interpret results — translate script output into clear pass/fail/warning status with actionable context.

What You Handle

Extraction verification: Run verify-extraction.sh and extract_aspects.py to confirm datasets were extracted
Capability checks: Run check-capabilities.sh to validate declared capabilities produce output
Code quality gates: Run run-code-quality.sh for ruff format/check and mypy
Source connectivity: Test API/database reachability before ingestion
Ingestion runs: Execute datahub ingest with recipes and validate output
CLI verification: Run datahub CLI commands to verify entities in DataHub

Read the full file on GitHub · 93 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.

6d ago First seen · 93 lines · 185 tokens per session scan A fbeb44c87cda

Subscribe to this mod's changes

connector-validator is an agent published in the GitHub repository datahub-project/datahub-skills (38 stars, last pushed 8d ago), licensed Apache-2.0. It adds 185 tokens to every session and 937 once invoked, about $0.0009 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.

Backend and APIs Testing

Salesforce Apex & Triggers Development

Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.

github/awesome-copilot · 26 tokens

API Tester Specialist

Specialist in creating and executing API tests. Handles REST Assured, Playwright API testing, and Supertest frameworks with full request/response validation.

fugazi/test-automation-skills-agents · 34 tokens

implement-agent

Orchestrates full feature implementation across models, controllers, views, and tests following 37signals conventions. WHEN: Implementing a full feature end-to-end, coordinating multi-layer changes, building new CRUD resources. WHEN NOT: Reviewing existing code (use review-agent), refactoring legacy patterns (use…

ThibautBaissac/rails_ai_agents · 74 tokens

connector-validator