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 neo4j-contrib/gds-agent --skill neo4j-graph-data-scientistgit clone --depth 1 https://github.com/neo4j-contrib/gds-agentWrote 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/neo4j-contrib/gds-agent/neo4j-graph-data-scientist)<a href="https://agentmods.dev/skills/neo4j-contrib/gds-agent/neo4j-graph-data-scientist"><img src="https://agentmods.dev/badge/skills/neo4j-contrib/gds-agent/neo4j-graph-data-scientist/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/neo4j-contrib/gds-agent/neo4j-graph-data-scientist"><img src="https://agentmods.dev/badge/skills/neo4j-contrib/gds-agent/neo4j-graph-data-scientist.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 | $0.00023 | $0.00487 |
| Opus 5 | $0.00012 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
neo4j-graph-data-scientist 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 11d 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.
What it actually says
Workflow
- Inspect the database schema first. Never guess labels, types, or property names.
- Project a graph. Plugin and session mode have different projection syntax and parameters. Check the graph projection tool description and parameters. For session mode, you need to first create sessions to project graphs onto.
- Clean up.
drop_graphwhen a projection is no longer needed.delete_sessionwhen a session is no longer needed, and this will automatically drop all graphs projected to this session. - When you see errors, inspect the message and make necessary corrections. If you cannot fix it, consult the detailed references/troubleshooting.md guide.
Best Practices
- Large graphs. When the graph in the DB is large, you might want to consider projecting subgraphs at the start for analysis.
When the projected graph is large, consider
mode: "mutate"to store the computed results in the projected graph and then usestream_node_propertiesorstream_relationship_propertiesto inspect the data. - Long running tools. Certain algorithms (or Cypher queries) are long running. For exploratory work, consider trying them out on smaller projected graphs before executing them on a desirable large projected graph.
- Follow general data science best practice. Understand if the task is transductive (over the fixed data) or inductive. For predictive tasks, ensure there is no data leakage. Formulate hypothesis and design metrics appropriately. Remember all the basic statistics best practices.
- Perform additional analysis when needed. You do not need to use solely the Cypher and GDS tools. For complex data science task, feel free to use other tools or coding capabilities and write ad-hoc scripts that use other libraries, such as pytorch, scikit-learn, pandas, matplotlib, when necessary.
What ships with it
1 file 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.
- 11d ago First seen · 24 lines · 23 tokens per session scan A 6b85d93b1a41
neo4j-graph-data-scientist is a skill published in the GitHub repository neo4j-contrib/gds-agent (96 stars, last pushed 14d ago), licensed MIT. It adds 23 tokens to every session and 487 once invoked, about $0.0001 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.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
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.
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…
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.