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/dpf-admin/dpf-claude-plugin/getting-startednpx skills add dpf-admin/dpf-claude-plugin --skill getting-startedgit clone --depth 1 https://github.com/dpf-admin/dpf-claude-pluginWhat 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 | $0.00068 | $0.00541 |
| Opus 5 | $0.00034 | $0.00270 |
| Sonnet 5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
getting-started 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 yesterday.
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
DPF (Data Prompt Forge)
DPF turns raw files or feeds into queryable Iceberg tables: AI-assisted schema inference plus a
transformation pipeline, fronted by a set of MCP tools under the dpf server.
First connection
The dpf MCP server uses OAuth — the first tool call triggers a browser login/signup popup
against DPF's own login page. Never ask the user for their DPF password directly; if a tool
seems to want one, stop and let the OAuth popup handle it instead.
If tools report as unauthenticated, tell the user to complete the browser login prompt, or run
/mcp (in Claude Code) to trigger it.
Typical flow
- Find or create a workspace —
list_my_workspaces, orcreate_workspaceif the user is starting fresh. - Onboard a data source —
onboard_data_sourcewalks a file or feed through AI-assisted schema inference; confirm the inferred schema with the user, thenfinish_data_source_onboarding. - Shape the data —
update_data_spec/finish_data_spec_updateto define the transformation into an Iceberg table;delete_data_specto remove one. - Automate —
manage_connectionandmanage_triggerfor recurring pulls;setup_scheduled_pullfor scheduled ingestion. - Run and query —
run_data_job/finish_data_jobto execute a transformation,submit_queryto query the resulting Iceberg table,list_datato browse what's available,get_statusto check job/workspace state.
For anything not covered by a dedicated tool, call_dpf_api reaches the full DPF REST API
directly — see the API reference.
Reference
- Integration guide (auth, MCP setup, other clients): https://dpf-it.com/integration-guide.html
- Worked examples: https://dpf-it.com/examples.html
- Full API reference: https://dpf-it.com/api-viewer.html
- Privacy policy: https://dpf-it.com/privacy-policy.html
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.
- yesterday First seen · 42 lines · 68 tokens per session scan A 1f63fd0fea18
getting-started is a skill published in the GitHub repository dpf-admin/dpf-claude-plugin (0 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 541 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.