connector-audit

connector-audit is a skill for Claude Code, Codex from open-metadata/OpenMetadata. It costs 35 tokens per session (2,019 once invoked), scanned A, original, Apache-2.0.

A deep review process for checking the reliability of OpenMetadata connectors across areas such as metadata, errors, authentication, lineage, and scale. Lineage describes how data moves between systems.

In plain words
What is it for?
Use it to run a full or selected reliability audit for a named connector, including follow-up implementation guidance. Existing audit-result files must be reviewed before the audit continues.
Why use it?
It helps find reliability problems that a normal code review may miss by investigating several parts of a connector and combining the findings.

Skill for Claude CodeCodex

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

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 · 15,109 stars · on GitHub

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 skills/open-metadata/openmetadata/connector-audit
Any agent
npx skills add open-metadata/OpenMetadata --skill connector-audit
Clone the repo
git clone --depth 1 https://github.com/open-metadata/OpenMetadata

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-metadata/openmetadata/connector-audit.svg)](https://agentmods.dev/skills/open-metadata/openmetadata/connector-audit)
Your own site
<a href="https://agentmods.dev/skills/open-metadata/openmetadata/connector-audit"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/connector-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00035 $0.02019
Opus 5 $0.00017 $0.01009
Sonnet 5 $0.00007 $0.00404
Haiku 4.5 $0.00003 $0.00202

Measured 5d ago against content hash e124a8da6875, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connector-audit scanned grade A 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 5d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. **Setup**: Ask user for connector name (if not provided), find source directory, write `.claude/connector-audit.json`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/connector-audit/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenMetadata Connector Reliability Audit

When to Activate

When a user asks to audit a connector, run a reliability audit, or investigate connector quality in depth.

STEP 1 — DO THIS FIRST, BEFORE ANYTHING ELSE

When this skill is invoked, your VERY FIRST action — before responding to the user, before summarizing anything, before checking any state — is:

  1. List all files in .claude/audit-results/ (if the directory exists)
  2. List .claude/connector-audit.json (if it exists)
  3. Present the file list to the user and ask: "These files exist from a previous audit. Which should I keep and which should I delete?"
  4. Wait for the user's answer. Do NOT proceed until they respond.

If no files exist, skip to Step 2.

NEVER summarize existing results, say "the audit is complete", or suggest the user doesn't need to run anything. The user invoked the skill — execute it.

Arguments

  • Connector name (e.g., mysql, snowflake, tableau): Full 7-prompt audit
  • --prompt N (e.g., --prompt 3): Run a single prompt (1-7) — useful for re-running after fixes
  • --prompts N,M (e.g., --prompts 1,4): Run specific prompts only
  • --from N (e.g., --from 6): Run prompts N through 7 — useful for continuing after P1-P5
  • --setup-only: Run setup only (writes connector-audit.json)
  • --dry-run: When used with P7, produce a detailed implementation plan (before/after diffs, tests, risk flags) without actually writing code — for review before execution

Relationship to connector-review

connector-audit connector-review
Purpose Deep reliability investigation Breadth check for PRs
Depth 7 focused prompts, hours of analysis 5 parallel agents, minutes
Output .claude/audit-results/ (7 reports) PR comment or local report
When Before major work on a connector During PR review
Scope Full connector + base classes + shared code Changed files only

Workflow Overview

Read the full file on GitHub · 170 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 170 lines · 35 tokens per session scan A e124a8da6875

Subscribe to this mod's changes

connector-audit is a skill published in the GitHub repository open-metadata/OpenMetadata (15,109 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 2,019 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

test-review

You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.

datahub-project/datahub · 0 tokens

conventional-commit-message

Generate high-quality Conventional Commit messages for repositories using conventional-changelog-conventionalcommits.

conventional-changelog/conventional-changelog · 23 tokens

oss-fuzz

Run Tika's OSS-Fuzz Jazzer targets locally against a working-tree checkout — build the image, build fuzzers from local source, fuzz a target, run a corpus as a regression pass, reproduce a crash, and add seeds. Use for "fuzz the OneNote parser", "run OneNoteParserFuzzer against these files", "reproduce an OSS-Fuzz…

apache/tika · 90 tokens

update-site-for-release

Update/publish the Apache Tika website (tika-site SVN repo) for a release — step 17 of the Release Process. Handles the 4.x track (Changes page + aggregate javadoc + Antora docs branch) vs the 3.x maintenance track (full per-version apt docs + javadoc). Use for "update the site", "publish the site for X.Y.Z", "the…

apache/tika · 92 tokens

file-to-markdown

Turn almost any file into Markdown plus metadata — PDF, Office, HTML, email, archives, images, audio/video, 1000+ formats — powered by Apache Tika, either via the tika-app CLI (zero setup, one file) or a running tika-server (curl, warm process, many calls). Leads with rmeta (structured, embedded-item-aware output) as…

apache/tika · 147 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens