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/ai-analyst-lab/ai-analyst-plugin/connect-datanpx skills add ai-analyst-lab/ai-analyst-plugin --skill connect-datagit clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-pluginWrote 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/ai-analyst-lab/ai-analyst-plugin/connect-data)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/connect-data"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/connect-data.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.01437 |
| Opus 5 | $0.00051 | $0.00718 |
| Sonnet 5 | $0.00021 | $0.00287 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade A, and why
connect-data 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Connect Data
Purpose
This is an interactive setup wizard, not a documentation generator. Guide the user through the actual connection process by executing each step: finding the data, testing that it reads, profiling the schema, and registering the dataset in the .knowledge/ context store. Do not just explain what would happen. Make it happen.
When to Use
- User says
/connect-data, "connect my data", or "add a new dataset" - A first analysis request arrives and no dataset is registered in
.knowledge/datasets/ - The user drops new files into the working folder and wants to analyze them
The three connection paths
Path 1: Files in the working folder (first-class path)
CSV and Excel files in the mounted working folder are the primary way to connect data in Cowork. No configuration is needed: the files are already accessible.
- Find the files. List the working folder for
.csv,.xlsx,.xls,.parquet, and.jsonfiles (including subfolders likedata/). Show what you found and ask the user to confirm which files belong to this dataset. - If the user mentions files that are not there, ask them to add the files to the working folder (or share them into the session) and re-run this step.
- Read each file with pandas (
pd.read_csv/pd.read_excel) and confirm it parses: row count, column names, obvious encoding or delimiter problems. Fix read options until every file loads cleanly.
Each file becomes one table, named after the file (without extension).
Path 2: Local DuckDB files
A .duckdb file in the working folder works in the sandbox.
- Ask for the path to the
.duckdbfile (relative to the working folder) and verify it exists. - Connect read-only with the
duckdbpackage and runSELECT 1to confirm the file opens. - Enumerate tables with
SHOW TABLESand confirm with the user.
Path 3: Cloud warehouses via Cowork connectors (Snowflake, BigQuery, and similar)
Cloud warehouses connect through Cowork connectors, which the user sets up in Customize (not through anything this skill configures).
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.
- 5d ago First seen · 86 lines · 103 tokens per session scan A eb794cad7866
connect-data is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 9d ago), licensed MIT. It adds 103 tokens to every session and 1,437 once invoked, about $0.0005 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
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.
cognee-community
Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify)…
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…