What is design-ingestor?

A planning step that designs how data from a source should be imported into a software system. It uses an existing data profile and requires a person to approve the proposed field mappings and transformations before implementation.

Use it after inspecting a dataset to propose the target class, parent class, column mappings, transformations, and known edge cases.

It prevents import work from starting with an unreviewed or misunderstood data structure. The human approval step provides a checkpoint for catching incorrect mappings and edge cases.

How NomaDamas/AutoRAG-Research configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to NomaDamas/AutoRAG-Research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/NomaDamas/AutoRAG-Research/main/.claude/commands/design-ingestor.md

Clone the repo

git clone --depth 1 https://github.com/NomaDamas/AutoRAG-Research

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nomadamas/autorag-research/design-ingestor/github.svg)](https://agentmods.dev/commands/nomadamas/autorag-research/design-ingestor)

Your own site

<a href="https://agentmods.dev/commands/nomadamas/autorag-research/design-ingestor"><img src="https://agentmods.dev/badge/commands/nomadamas/autorag-research/design-ingestor/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/nomadamas/autorag-research/design-ingestor"><img src="https://agentmods.dev/badge/commands/nomadamas/autorag-research/design-ingestor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 587 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00587
Opus 5	$0.00007	$0.00293
Sonnet 5	$0.00003	$0.00117
Haiku 4.5	$0.00001	$0.00059

Measured 12d ago against content hash 52c28f5fc812, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

design-ingestor 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 12d 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.

.claude/commands/design-ingestor.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Ingestor Strategy (Human-in-the-Loop)

This skill orchestrates the schema design phase with mandatory human approval before proceeding to implementation.

Prerequisites

Source_Data_Profile.json must exist (generated by dataset-inspector agent)
If not found, inform user to run dataset inspection first

Workflow

Step 1: Invoke Schema Architect

Call the schema-architect agent with the source data profile:

Task(subagent_type="schema-architect", prompt="Design ingestion strategy for [dataset] using Source_Data_Profile.json")

Step 2: Present Strategy Summary

After the agent completes, present a concise summary to the user:

Target class and parent class
Key column mappings
Notable transformations
Potential edge cases

Step 3: MANDATORY Human Review

YOU MUST use AskUserQuestion with the following options:

AskUserQuestion:
  question: "Review the Mapping_Strategy.md above. How would you like to proceed?"
  header: "Strategy Review"
  options:
    - label: "Approve"
      description: "Strategy looks good. Proceed to test writing phase."
    - label: "Request Changes"
      description: "I have feedback. Revise the strategy based on my input."
    - label: "Reject"
      description: "Stop the workflow. Strategy needs major rework or is not viable."

Step 4: Handle Response

If "Approve":

Confirm approval and indicate next step (test writing phase)
Output: "Strategy approved. Ready for Phase 3: Test Writing"

If "Request Changes":

Ask user for specific feedback using AskUserQuestion (free text via "Other")
Re-invoke schema-architect with the feedback
Return to Step 2 (present revised strategy)
Repeat until approved or rejected

If "Reject":

Acknowledge rejection
Clean up any generated artifacts if needed
Output: "Workflow stopped. Strategy rejected by user."

Critical Rules

NEVER skip the AskUserQuestion step - This is the entire purpose of this skill
NEVER proceed to implementation without explicit "Approve"
Loop on "Request Changes" - Keep revising until user is satisfied
Track iterations - If more than 3 revision cycles, suggest pausing to clarify requirements

Read the full file on GitHub · 79 lines

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.

12d ago First seen · 79 lines · 14 tokens per session scan A 52c28f5fc812

Subscribe to this mod's changes

design-ingestor is a command published in the GitHub repository NomaDamas/AutoRAG-Research (148 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 587 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.

Data and AI Planning

music-suno-prompt

Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.

frankxai/Starlight-Intelligence-System · 23 tokens

laravel-ai-sdk

Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.

jpcaparas/superpowers-laravel · 27 tokens

audit-prompt

Evaluate an existing prompt for clarity, effectiveness, and edge cases.

Owl-Listener/ai-design-skills · 13 tokens

develop-image-prompt.eval

Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.

davistroy/claude-marketplace · 0 tokens

dare-llm-integration

Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.

dewtech-technologies/dare-method · 0 tokens

prompt-create

Create a new prompt following ground rules.

NVZver/claude-marketplace · 10 tokens

AutoRAG-Research: Command for Claude Code