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/test-locallyWrote 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/test-locally)<a href="https://agentmods.dev/skills/open-metadata/openmetadata/test-locally"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/test-locally/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/test-locally"><img src="https://agentmods.dev/badge/skills/open-metadata/openmetadata/test-locally.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 129 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.01395 |
| Opus 5.5 | $0.00015 | $0.00558 |
| Sonnet 5.5 | $0.00008 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
test-locally 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 1mo 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 -s -o /dev/null -w "%{http_code}" http://localhost:8585/api/v1/system/version How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Connector Locally
Build, deploy, and test a connector in a full local OpenMetadata stack with Docker.
When to Activate
When a user asks to "test locally", "start docker", "deploy locally", "test in the UI", "bring up the stack", or "run local docker".
Arguments
--skip-mavenor--fast: Skip the Maven build (use when only ingestion Python code changed)--rebuild: Tear down existing containers and rebuild--teardownor--down: Just stop and remove containers- No arguments: Auto-detect what changed and choose the optimal build strategy
Process
Step 0: Handle Teardown
If the user asked to tear down / stop:
cd docker/development && docker compose down -v
Report success and exit.
Step 1: Check Prerequisites
Verify the environment is ready:
# Check Docker is running
docker info > /dev/null 2>&1 || echo "Docker is not running"
# Check docker compose is available
docker compose version > /dev/null 2>&1 || echo "docker compose not found"
# Check we're in the repo root
test -f docker/run_local_docker.sh || echo "Not in OpenMetadata repo root"
If any check fails, tell the user what to fix and stop.
Step 2: Activate Environment
source env/bin/activate
Step 3: Run Code Generation
Always run code generation to ensure models are up to date:
make generate
If make generate fails, check if the venv is set up:
make install_dev generate
Step 4: Detect Build Strategy
Decide whether to skip the Maven build. Check what files changed:
# Check for Java/schema/UI changes since last build
git diff --name-only HEAD~5 | grep -E "^(openmetadata-spec|openmetadata-service|openmetadata-ui)" | head -5
Skip Maven if:
- User passed
--skip-mavenor--fast - Only files under
ingestion/changed (Python-only changes) - No changes to
openmetadata-spec/,openmetadata-service/, oropenmetadata-ui/
Full build if:
- JSON Schema files changed (
openmetadata-spec/) - Java service code changed (
openmetadata-service/) - UI code changed (
openmetadata-ui/) - First time running (no existing Docker images)
- User explicitly asked for full build
What ships with it
1 file 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.
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.
- 1mo ago First seen · 201 lines · 38 tokens per session scan A fe9b26629757
test-locally is a skill published in the GitHub repository open-metadata/OpenMetadata (15,542 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,395 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 2026-08-30.
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.
agent-sandbox
Agent skill for sandbox - invoke with $agent-sandbox.
verify
Build the computer-use-demo image and drive the Streamlit UI headlessly to verify changes end-to-end.
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…
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".
redamon-testing
How RedAmon tests actually run and how to author them: the per-file Docker gate, the unit/integration/live tiers, and the failure modes that make a green run a lie. Trigger: editing any test.py, .test.ts(x) or tests/.sh; a test that is red, skipped or xfailed; a request to "run the tests", "make it green" or check…