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.
npx agentmods add skills/open-metadata/openmetadata/code-reviewnpx skills add open-metadata/OpenMetadata --skill code-reviewgit clone --depth 1 https://github.com/open-metadata/OpenMetadataWhat 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 | $0.00036 | $0.01176 |
| Opus 5 | $0.00018 | $0.00588 |
| Sonnet 5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 153 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 diffto 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-schemafor UI forms
- Schema change (
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.
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.
- yesterday First seen · 153 lines · 36 tokens per session scan A 4c1ae9068a54
code-review is a skill published in the GitHub repository open-metadata/OpenMetadata (15,032 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,176 once invoked, about $0.0002 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.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate smoke tests and integration tests against established testing standards, identify issues, and provide actionable feedback.
conventional-commit-message
Generate high-quality Conventional Commit messages for repositories using conventional-changelog-conventionalcommits.
whodb
Query and explore databases via MCP. Use when the user asks to inspect schemas, run SQL, browse tables, analyze data quality, generate ER diagrams, or work with PostgreSQL, MySQL, MariaDB, TiDB, SQLite, MongoDB, Redis, ClickHouse, Elasticsearch, or DuckDB.
schema-designer
Help design database schemas, create tables, and plan data models. Activates when users ask to create tables, design schemas, or model data relationships.
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…
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…