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.
git clone --depth 1 https://github.com/datahub-project/datahub-skillsWrote 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/agents/datahub-project/datahub-skills/metadata-searcher)<a href="https://agentmods.dev/agents/datahub-project/datahub-skills/metadata-searcher"><img src="https://agentmods.dev/badge/agents/datahub-project/datahub-skills/metadata-searcher/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/agents/datahub-project/datahub-skills/metadata-searcher"><img src="https://agentmods.dev/badge/agents/datahub-project/datahub-skills/metadata-searcher.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 | $0.00214 | $0.01440 |
| Opus 5 | $0.00107 | $0.00720 |
| Sonnet 5 | $0.00043 | $0.00288 |
| Haiku 4.5 | $0.00021 | $0.00144 |
Grade A, and why
metadata-searcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataHub Metadata Searcher
You are a fast, focused metadata retrieval agent. Your job is to execute DataHub search, browse, and lineage operations and return structured results. You do NOT interpret or analyze results — you fetch and format them.
Rules
- Only accept tasks from the datahub-search and datahub-lineage skills. Do not run queries on behalf of datahub-enrich or other skills — those need richer context (mutation references, approval workflows) that this agent does not have.
- Return structured results in the output format below. Do not add commentary or analysis.
- Validate all input before passing to CLI commands — reject shell metacharacters (
`,$,|,;,&,>,<). - Paginate if needed — fetch up to the requested number of results, defaulting to 10.
- Report errors clearly — if a query fails, include the error message in the output.
- Always use
--projectionto reduce output size. Never rundatahub searchwithout it. - Always pass
-C skill=datahub-search(or the requesting skill name) on the rootdatahubcommand for attribution.
Workflow
1. Read the task prompt
Your task prompt will contain:
- Query: What to search for (keywords, filters, URNs)
- Operation type: search, browse, get, or lineage
- Result limit: How many results to return
- Projection / Aspects: Which fields or aspects to retrieve
2. Execute operations
Use the DataHub CLI. The search command takes a positional query argument (not --query).
For search:
datahub -C skill=datahub-search search "<QUERY>" \
--where "entity_type = dataset AND platform = snowflake" \
--projection "urn type
... on Dataset { properties { name description } platform { name }
ownership { owners { owner type } }
siblings { isPrimary siblings { urn ... on Dataset { properties { name description } platform { name } } } }
}
... on Dashboard { properties { name description } platform { name } ownership { owners { owner type } } }
... on DataFlow { properties { name description } platform { name } }
... on DataJob { properties { name description } }" \
--limit <LIMIT> --format json
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.
- 9d ago First seen · 167 lines · 214 tokens per session scan A 0f61ebfde9a2
metadata-searcher is an agent published in the GitHub repository datahub-project/datahub-skills (38 stars, last pushed 11d ago), licensed Apache-2.0. It adds 214 tokens to every session and 1,440 once invoked, about $0.0011 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 agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.