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/agentxp/connect-datanpx skills add ai-analyst-lab/agentxp --skill connect-datagit clone --depth 1 https://github.com/ai-analyst-lab/agentxpWhat 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 | $0.00044 | $0.00702 |
| Opus 5 | $0.00022 | $0.00351 |
| Sonnet 5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade B, and why
connect-data scanned grade B 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
description: Wire a warehouse profile via an interactive wizard. Supports DuckDB, Snowflake, BigQuery, Databricks. Writes ~/.agentxp/credentials/<dialect>/<profile>.yaml at chmod 600. How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: /connect-data
Purpose
Wire a warehouse profile so the design and analyze verbs can probe_data against it. The wizard walks the user through the connection fields for their chosen dialect, tests the connection, and writes the credentials file.
When to invoke
Direct:
/connect-data <dialect>— start the wizard for one dialect/connect-data— ask the user which dialect first
Supported dialects: duckdb, snowflake, bigquery, databricks.
Plain-English routing:
| Phrase | What to do |
|---|---|
| "Connect to my Snowflake warehouse" | /connect-data snowflake |
| "Wire up the demo DuckDB" | /connect-data duckdb |
| "I need to set up BigQuery" | /connect-data bigquery |
| "Hook up Databricks" | /connect-data databricks |
Procedure
1. Pick the dialect
If the user did not supply one, ask. Then:
from agentxp.workflows.connect import run_wizard
out_path = run_wizard(dialect)
The wizard prompts for each field per the dialect schema. Fields with defaults can be left blank; required fields prompt until non-empty. The wizard writes ~/.agentxp/credentials/<dialect>/<profile>.yaml at chmod 600.
2. Test the connection
After the wizard returns, attempt a minimal query (e.g., SELECT 1) through the safety pipeline:
from agentxp.orchestrator.tools import probe_data
result = probe_data("SELECT 1", mode="analyze", dialect=dialect)
If the query fails: surface the error to the user and offer to re-run the wizard.
3. Confirm + print next step
Profile written to ~/.agentxp/credentials/<dialect>/<profile>.yaml
Next: /design --data <path-or-profile> to begin an experiment.
Tools you call
run_wizardfromagentxp.workflows.connectprobe_data(mode="analyze")fromagentxp.orchestrator.toolsfor the connection test
Rules cited
- R10 — credential file shape is a Pydantic-validated schema (no ad-hoc fields)
- R11 — once wired, design queries against this warehouse run in
mode="design"and refuse outcome columns
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.
- 3d ago First seen · 85 lines · 44 tokens per session scan B b1ca4e0db46a
connect-data is a skill published in the GitHub repository ai-analyst-lab/agentxp (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 44 tokens to every session and 702 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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)…
bigquery-ai-ml
Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).
cocoindex
This skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change…
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
fabriciq-ontology-cli
Manages Fabric IQ Ontology items, including entity and relationship types, data bindings, and definition updates, plus schema, lineage, grounding, and graph-walk exploration. Use for ontology modelling and traversal. For natural-language questions over a Power BI report use fabriciq.
lineage-diff
Compare column-level lineage between two versions of a SQL query to show added, removed, and changed data flow edges.