A two-stage code-review assistant for OpenMetadata changes: first checking whether the requirements are met, then checking code quality.

It reviews uncommitted changes, staged changes, branches, files, or pull requests for missing requirements, unrelated changes, and quality issues.

It separates “does this solve the requested problem?” from “is the implementation safe and maintainable?”

code-review — Skill for Claude Code by open-metadata/OpenMetadata

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 · 15,490 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.

Any agent

npx skills add open-metadata/OpenMetadata --skill code-review

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 23 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/open-metadata/openmetadata/code-review/github.svg)](https://agentmods.dev/skills/open-metadata/openmetadata/code-review)

Your own site

<a href="https://agentmods.dev/skills/open-metadata/openmetadata/code-review"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/code-review/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/skills/open-metadata/openmetadata/code-review"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,259 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00036	$0.01259
Opus 5.5	$0.00014	$0.00504
Sonnet 5.5	$0.00007	$0.00252
Haiku 4.5	$0.00004	$0.00126

Measured 6d ago against content hash b52b7db886ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-review 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.

skills/code-review/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review for OpenMetadata

Two-stage review process: requirements compliance first, then code quality.

When to Use

Before creating a PR
Reviewing someone else's PR
Self-checking your own changes before requesting review

Usage

/code-review                    # Review uncommitted changes
/code-review feature-branch     # Review branch diff against main
/code-review #1234              # Review GitHub PR
/code-review path/to/file.java  # Review specific files

Stage 1: Spec Compliance Review

Verify the changes do what they're supposed to do — no more, no less.

Steps

Understand the goal. Read the PR description, issue, or ask the user what the change is supposed to accomplish.

Read all changed files. Use git diff to see the full scope:

git diff main...HEAD          # Branch diff
git diff --staged             # Staged changes
gh pr diff <number>           # PR diff

Check completeness against requirements:
- Does every stated requirement have a corresponding code change?
- Are there missing pieces? (e.g., backend change without migration, API change without UI update)
Check for scope creep:
- Are there changes unrelated to the stated goal?
- Was code "improved" that didn't need to change?
Check the cross-layer contract:
- Schema change (openmetadata-spec/) + model regeneration (make generate)
- Backend API change + frontend API client update
- New entity field + database migration (bootstrap/sql/)
- New connection config + yarn parse-schema for UI forms

Report Format (Stage 1)

## Spec Compliance: [PASS / FAIL / PARTIAL]

### Requirements Met
- [x] Requirement A — implemented in file.java:42
- [ ] Requirement B — MISSING: no migration for new field

### Scope Issues
- file.java:100-120 — unrelated refactor, consider separate PR

### Cross-Layer Gaps
- Schema updated but `make generate` not run (models out of sync)

If Stage 1 fails, stop here. Fix compliance issues before reviewing quality.

Read the full file on GitHub · 157 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 Changed · +4 lines b52b7db886ad
1mo ago First seen · 153 lines · 36 tokens per session scan A 4c1ae9068a54

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository open-metadata/OpenMetadata (15,490 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 1,259 once invoked, about $0.0001 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 2026-08-30.

Code review data-catalog data-profiling datadiscovery dataquality metadata metadata-management

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

pr-review

Review of a PR, branch, or your own uncommitted work across eight dimensions — security, correctness, test coverage, API/compatibility, usability, documentation, code quality, performance. Sizes the diff, reviews inline or fans out reviewers off a shared brief, verifies findings against code, reports a grouped list…

apache/tika · 108 tokens

pr-verify

Verify a Docglow change actually works before submitting or merging a PR. Runs the conformance suite, then a behavioral verification pass (flag matrix, artifact-join spot checks, pipeline contract sweep, payload budget). Use when reviewing a PR, self-reviewing a branch before opening a PR, or when asked to "verify…

docglow/docglow · 79 tokens

code-review