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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/open-metadata/OpenMetadatanpx agentmods add skills/open-metadata/openmetadata/ui-pr-recordingWrote 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.
[](https://agentmods.dev/skills/open-metadata/openmetadata/ui-pr-recording)<a href="https://agentmods.dev/skills/open-metadata/openmetadata/ui-pr-recording"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/ui-pr-recording/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.
<a href="https://agentmods.dev/skills/open-metadata/openmetadata/ui-pr-recording"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/ui-pr-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.01991 |
| Opus 5.5 | $0.00024 | $0.00796 |
| Sonnet 5.5 | $0.00012 | $0.00398 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
ui-pr-recording 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --fail --silent --show-error http://localhost:8585/api/v1/system/version How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI PR recording
Produce evidence of the feature running against a real local OpenMetadata stack as part of pr-checklist when creating its PR. The requirement is recorded in ADR:2026-10-10-ui-prs-require-docker-screen-recordings.
Scope and completion
Inspect the task/linked issue and the diff against the PR's base. This requirement applies when
creating a PR that implements or extends a UI feature, including a task or subtask of that feature
with UI impact. Standalone bug fixes, refactors, styling, localization, docs, tests and backend-only
work may use Not applicable — <reason> in the recording section. Classify by the task and its
behavior, not just changed paths or labels. A styling task that delivers part of a UI feature
still qualifies.
Run this step during PR creation, not automatically during implementation or a standalone review. A user can still explicitly request a recording for any change. For a qualifying PR, prepare a description containing a playable GitHub-hosted video, the recorded commit, Docker startup/health evidence, sample-data setup, and the steps and outcomes shown. Screenshots supplement the video; a local path, test trace, terminal recording, mock-only UI or TODO does not satisfy the requirement. Required automated tests remain separate checks.
When invoked from pr-checklist Step 5, complete sections 1–3 only and return the verified local
video path and evidence for the PR body. Section 4 runs at pr-checklist Step 7, after Step 6 has
prepared the complete body for review; capture must not create or edit a PR.
1. Run the PR build in Docker
Use test-locally for prerequisites and the existing build workflow.
Build the committed PR code, including the UI, and record git rev-parse HEAD. Do not use a
released image or skip the build unless the existing artifact is verified to contain that code.
Inspect docker ps and the Compose configuration first. The local runner stops both default dev
stacks even with -r false; its default -r true deletes database files. If another task owns
those services, use an isolated Compose stack with distinct container names, host ports, network
and volumes. A different project name alone is insufficient: the base Compose file pins names,
ports, a subnet and a database bind mount. Do not stop another task's stack or delete its data.
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.
- 5d ago First seen · 143 lines · 60 tokens per session scan A eee785bae703
ui-pr-recording is a skill published in the GitHub repository open-metadata/OpenMetadata (15,490 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 1,991 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
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.
project-index
Kite's project registry — a structured JSON index of all active projects.
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".
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.