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 skills add preset-io/agent-skills --skill preset-datasetsgit clone --depth 1 https://github.com/preset-io/agent-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/skills/preset-io/agent-skills/preset-datasets)<a href="https://agentmods.dev/skills/preset-io/agent-skills/preset-datasets"><img src="https://agentmods.dev/badge/skills/preset-io/agent-skills/preset-datasets/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/preset-io/agent-skills/preset-datasets"><img src="https://agentmods.dev/badge/skills/preset-io/agent-skills/preset-datasets.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 | $0.00048 | $0.00565 |
| Opus 5 | $0.00024 | $0.00282 |
| Sonnet 5 | $0.00010 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
preset-datasets 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preset-datasets
Use for dataset and database metadata inspection in a resolved Preset workspace.
Always
- Auth and conventions come from
preset-api(JWT exchange, base URLs, Rison); resolve the workspace hostname through the Management API when it is not already known. Consultpreset-supersetonly when version drift matters. - Run schema, table, dataset, column, and metric metadata reads directly.
- Run samples, distinct values, and datasource values directly when the user asked in their own message with an explicit table/column target: row/value limit as a request parameter (default 100, hard cap 1000 without explicit confirmation), output summarized — no raw row dumps.
- Connection configuration stays confirmation-gated; route credential-bearing database connection work to
preset-database-connections. - Require confirmation before dataset/database mutations, uploads, cache changes, imports, exports, validation, or SQL execution.
- Do not create, update, delete, duplicate, import, refresh schemas, upload files, test databases, validate SQL, or run SQL Lab queries from this skill without confirmation and focused routing.
Decision Rules
- Treat schema, table, dataset, column, and metric inspection as read-only metadata.
- Distinguish metadata inspection from data-returning reads.
- Use database identity from discovered environment facts or API results.
- Avoid credential-bearing connection fields; route those to
preset-database-connections.
Workflow Order
- Resolve database connection.
- Inspect schemas, tables, datasets, columns, and metrics metadata.
- Fetch explicitly requested samples or distinct values with parameterized limits and summarized output.
- Confirm before exports, mutations, uploads, cache changes, imports, validation, SQL execution, or credential-bearing connection work.
Retrieve
- Database list/detail and available database metadata: references/database-metadata.md
- Dataset list/detail, columns, metrics, related objects: references/dataset-metadata.md
- Catalogs, schemas, tables, table metadata, functions: references/table-and-schema-metadata.md
- Samples, distinct values, datasource values: references/data-returning-reads.md
- Connection configuration routing: references/connection-configuration.md
- Dataset/database mutations and routing: references/dataset-database-mutations.md
What ships with it
7 files 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.
- examples/table_and_schema_metadata.py 514 B runs code
- references/connection-configuration.md 1.2 KB
- references/data-returning-reads.md 1.2 KB
- references/database-metadata.md 1.6 KB
- references/dataset-database-mutations.md 1.2 KB
- references/dataset-metadata.md 2.3 KB
- references/table-and-schema-metadata.md 1.1 KB
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.
- 12d ago First seen · 41 lines · 48 tokens per session scan A ffea75046490
preset-datasets is a skill published in the GitHub repository preset-io/agent-skills (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 565 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
business-intelligence-expert
Build comprehensive business intelligence solutions including data warehouses, ETL pipelines, interactive dashboards, and analytical reporting systems. Use when the user mentions BI, data warehousing, star or snowflake schemas, OLAP cubes, ETL/ELT pipelines, dashboards, KPIs, or analytical reporting.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Quick reference for common patterns, index types, data types, and anti-pattern detection. Based on Supabase best practices.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.