agentmods.dev

getting-started

getting-started is a skill for Claude Code from dpf-admin/dpf-claude-plugin. It costs 68 tokens per session (541 once invoked), scanned A, original, MIT.

A guide for using Data Prompt Forge, a service that turns raw files or feeds into queryable Apache Iceberg tables. It covers connecting a workspace, inferring schemas, defining transformations, and scheduling data pulls.

In plain words
What is it for?
Use it when connecting to DPF, onboarding a data source, confirming its inferred schema, shaping data, scheduling imports, or querying Iceberg tables.
Why use it?
It lays out the required order of operations and explains how to handle first-time OAuth login without sharing a password with the assistant.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the dpf plugin — 1 skill, 1 MCP server shipped together

not rated 0repo 2mo ago A scan 68 tokens original MIT

Good fit Use it when connecting to DPF, onboarding a data source, confirming its inferred schema, shaping data, scheduling imports, or querying Iceberg tables.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dpf-admin/dpf-claude-plugin/getting-started
View source ↗ dpf-admin/dpf-claude-plugin
Install

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.

Any agent
npx skills add dpf-admin/dpf-claude-plugin --skill getting-started
Clone the repo
git clone --depth 1 https://github.com/dpf-admin/dpf-claude-plugin

Made for: Claude Code.

Or install dpf, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for getting-started

README.md
[![agentmods](https://agentmods.dev/badge/skills/dpf-admin/dpf-claude-plugin/getting-started/github.svg)](https://agentmods.dev/skills/dpf-admin/dpf-claude-plugin/getting-started)
Your own site
<a href="https://agentmods.dev/skills/dpf-admin/dpf-claude-plugin/getting-started"><img src="https://agentmods.dev/badge/skills/dpf-admin/dpf-claude-plugin/getting-started/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.

agentmods 80×15 button for getting-started

Your own site · 80×15
<a href="https://agentmods.dev/skills/dpf-admin/dpf-claude-plugin/getting-started"><img src="https://agentmods.dev/badge/skills/dpf-admin/dpf-claude-plugin/getting-started.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00541
Opus 5.5 $0.00027 $0.00216
Sonnet 5.5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 2mo ago against content hash 1f63fd0fea18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

plugins/dpf/skills/getting-started/SKILL.md · 42 lines

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

  1. Find or create a workspace — list_my_workspaces, or create_workspace if the user is starting fresh.
  2. Onboard a data source — onboard_data_source walks a file or feed through AI-assisted schema inference; confirm the inferred schema with the user, then finish_data_source_onboarding.
  3. Shape the data — update_data_spec / finish_data_spec_update to define the transformation into an Iceberg table; delete_data_spec to remove one.
  4. Automate — manage_connection and manage_trigger for recurring pulls; setup_scheduled_pull for scheduled ingestion.
  5. Run and query — run_data_job / finish_data_job to execute a transformation, submit_query to query the resulting Iceberg table, list_data to browse what's available, get_status to 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

Changes

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.

  1. 2mo ago First seen · 42 lines · 68 tokens per session scan A 1f63fd0fea18

Subscribe to this mod's changes

getting-started is a skill published in the GitHub repository dpf-admin/dpf-claude-plugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 541 once invoked, about $0.0003 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 2026-08-31.

Data and AIDatabases
Related

getting-started compared with skills from other repositories

getting-started next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
getting-starteddpf-admin/dpf-claude-pluginSkill02mo agoMITA68Claude Code
embeddingsruvnet/rufloSkill81kyesterdayMITA62Claude Code
rag-pineconedavila7/claude-code-templatesSkill33ktodayMITA65Claude Code, Codex
data-engineerdavila7/claude-code-templatesSkill33ktodayMITA35Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-SkillsSkill3.8ktodayApache-2.0A30Claude Code, Codex
ingesting-into-data-lakeaws/agent-toolkit-for-awsSkill3.4ktodayApache-2.0A228Claude Code
graphjin-envdosco/graphjinSkill3.2kyesterdayApache-2.0A61Claude Code, Codex