Data Formulator is an interactive workspace where AI agents connect to data sources, answer questions, and create visualizations. It is used to explore and analyze data while branching into related questions without losing the context of each investigative path.
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 microsoft/data-formulator --skill data-loadinggit clone --depth 1 https://github.com/microsoft/data-formulatorWrote 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/microsoft/data-formulator/data-loading)<a href="https://agentmods.dev/skills/microsoft/data-formulator/data-loading"><img src="https://agentmods.dev/badge/skills/microsoft/data-formulator/data-loading/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/microsoft/data-formulator/data-loading"><img src="https://agentmods.dev/badge/skills/microsoft/data-formulator/data-loading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01231 |
| Opus 5.5 | $0.00015 | $0.00492 |
| Sonnet 5.5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
data-loading 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- data-loading — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Data discovery
The workspace tables listed in your context are the data already loaded into the system, and the only data that can be read directly. Everything these tools return is not loaded yet — it lives in a connected source and only becomes usable after the user selects a loading option and the server materializes it.
Use these tools to determine whether connected sources contain data needed for the user's goal. They are read-only: discovering, describing, or probing a source does not add anything to the workspace analysis inputs.
Adding a connector
When the user wants to connect a new source, do not merely ask them to navigate to settings and do not attempt to connect on their behalf.
- Call
list_connectorsfirst because available built-ins and plugins vary by deployment. For a broad request such as "help me connect", summarize the concrete available types and ask which one they use. - Once the source type is known, call
describe_connectorwhen field or auth details are useful. - When the requested source type is known and available, you MUST call
propose_connectionin this same turn. Do not stop with text such as "I'll open the form", "you'll need to provide", or a list of required fields. Only the action opens the form. Include one or two helpful sentences alongside the action call explaining what the user should review or supply; this text appears above the chat while the form opens on the canvas. Passprefilledvalues the user already supplied, including values parsed from a connection string or config snippet. Never invent missing values. - The form is only a proposal. The user reviews it and clicks Connect; the action must never connect automatically.
Prefilled values may include credentials the user deliberately supplied. Do not repeat those values in prose or subsequent tool output. They are transient form seeds and are removed from persisted UI state.
Discovery sequence
- Use
find_datawhen the user names a business concept or table. Uselist_datawhen you need to browse available sources or hierarchy. - Use
describe_databefore relying on columns, types, row counts, or filter values. Pass the exactsource_idandtable_keyreturned by discovery. - Use
probe_dataonly when metadata is insufficient to choose a useful bounded result. Probes are limited, read-only, and may be approximate. - First reconcile discoveries with every table in
[PRIMARY TABLE(S)],[OTHER AVAILABLE TABLES], or[AVAILABLE TABLES]. If the needed data is already loaded, use or explain that workspace table instead of proposing it. - When there are genuinely missing useful alternatives, call
propose_data_operationwith one to three complete immutable plans. This pauses for the user's choice; it does not load data yet.
What ships with it
3 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.
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 · 109 lines · 37 tokens per session scan A d7cecaa0a45c
data-loading is a skill published in the GitHub repository microsoft/data-formulator (17,584 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,231 once invoked, about $0.0001 per session on Opus 5.5. 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
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.