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/openmetadata-workflownpx skills add open-metadata/OpenMetadata --skill openmetadata-workflowgit 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 | $0.00035 | $0.01211 |
| Opus 5 | $0.00017 | $0.00606 |
| Sonnet 5 | $0.00007 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
openmetadata-workflow 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenMetadata Development Workflow
This skill is loaded automatically at session start. It ensures you follow the right workflow for every task.
Before Starting Any Task
Check which skills apply to your task and use them. This is not optional — if a skill applies, you must follow it.
Skill Selection Guide
| Task type | Required skill(s) |
|---|---|
| New feature (multi-file) | /planning then /tdd then /test-enforcement then /verification |
| Bug fix | /systematic-debugging then /tdd (write regression test) then /verification |
| New API endpoint | /planning then /tdd then /test-enforcement (must include integration test) |
| New connector | /connector-standards then /connector-building then /test-enforcement |
| UI component | Read openmetadata-ui/src/main/resources/ui/DEVELOPER_HANDBOOK.md first (folder structure + file naming for any new file), then /ui-core-components + /react-best-practices + /composition-patterns before writing, then /tdd, then /web-design-guidelines after, then /test-enforcement (must include Jest + Playwright if user-facing) |
| UI a11y / UX / design audit | /web-design-guidelines |
| React perf work (re-renders, waterfalls, bundle) | /react-best-practices |
| Code review / PR review | /code-review then /test-enforcement |
| Opening / finalizing a PR | /test-enforcement then /verification then /pr-checklist |
| Connector review | /connector-review |
| E2E test creation | /playwright |
| Finishing implementation | /test-enforcement then /verification |
Note: Connector skills (
/connector-standards,/connector-building,/connector-review) and/playwrightare part of the OpenMetadata Skills plugin and ship together with this workflow skill. They are defined in theskills/directory alongside this file.
Why the UI row names skills explicitly: a skill only loads when it is invoked, and the model decides that from the skill's own
description./composition-patternsdescribes itself as being for refactoring prop proliferation and building component libraries, and/web-design-guidelinesdescribes itself as being for "review my UI" / "check accessibility" — so neither reliably fires on "build me a component". Naming them here is what makes them part of the workflow instead of a coin flip. Invoke/web-design-guidelinesafter the component exists: it is an audit, and running it first works against its own trigger.
/react-best-practices,/composition-patternsand/web-design-guidelinesare vendored from vercel-labs/agent-skills (MIT) underskills/vendor/. They are authoring aids, not gates — enforcement isui-checkstyle, seedocs/ui-code-quality-gate.md.
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.
- 3d ago First seen · 82 lines · 35 tokens per session scan A aa98fd9d8d83
openmetadata-workflow is a skill published in the GitHub repository open-metadata/OpenMetadata (15,059 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,211 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.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
mcporter
List, auth, and call MCP servers/tools from the terminal.
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".
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).