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.
curl -O https://raw.githubusercontent.com/NomaDamas/AutoRAG-Research/main/.agents/skills/create-ingestor-plugin/SKILL.mdgit clone --depth 1 https://github.com/NomaDamas/AutoRAG-ResearchWrote 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/nomadamas/autorag-research/create-ingestor-plugin)<a href="https://agentmods.dev/skills/nomadamas/autorag-research/create-ingestor-plugin"><img src="https://agentmods.dev/badge/skills/nomadamas/autorag-research/create-ingestor-plugin/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/nomadamas/autorag-research/create-ingestor-plugin"><img src="https://agentmods.dev/badge/skills/nomadamas/autorag-research/create-ingestor-plugin.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 | $0.00071 | $0.01173 |
| Opus 5.5 | $0.00028 | $0.00469 |
| Sonnet 5.5 | $0.00014 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
create-ingestor-plugin 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Ingestor Plugin
Workflow
1. Scaffold
autorag-research plugin create my_dataset --type=ingestor
Read the generated ingestor.py, pyproject.toml, and test file to understand the structure.
The generated pyproject.toml registers the autorag_research.ingestors entry point. The @register_ingestor decorator handles automatic CLI parameter extraction from __init__ type hints.
2. Implement the ingestor
For the code-level implementation rules that are shared with the agent workflows, read:
ai_instructions/implementation_specialist.mdai_instructions/schema_architect.mdai_instructions/test_writer.md
Required methods:
__init__(embedding_model, ...)— accept embedding model + dataset-specific paramsdetect_primary_key_type()→"bigint"or"string"ingest(subset, query_limit, min_corpus_cnt)— load data and save viaself.service
__init__ type hints drive CLI generation automatically:
| Type Hint | CLI Behavior |
|---|---|
Literal["a", "b"] |
--param with choices, required |
str |
--param, required |
int = 100 |
--param, optional with default |
bool = False |
--param/--no-param flag |
Parameters named embedding_model or late_interaction_embedding_model are auto-skipped (injected by CLI).
self.service is injected after construction via set_service(). Read existing ingestors for exact service method signatures.
3. Database Schema (critical)
Ingestors must populate the correct entity hierarchy:
Document → Page → Chunk (text)
→ ImageChunk (images)
- Document — top-level container (e.g., a Wikipedia article, a PDF)
- Page — subdivision within a document (linked via
document_id) - Chunk — text passage with embedding vector (linked to Page via
PageChunkRelation) - ImageChunk — image binary with embedding vector (linked to Page via
PageChunkRelation) - Query — search query with
generation_gt: list[str] | None(ground truth answers)
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.
- 2mo ago First seen · 127 lines · 71 tokens per session scan A b372ab2142cd
create-ingestor-plugin is a skill published in the GitHub repository NomaDamas/AutoRAG-Research (151 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,173 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 2026-08-30.
Other skills, from other repositories
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.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
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…
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.
qdrant-search-quality-diagnosis
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', 'quality dropped after quantization', 'how to measure retrieval quality', 'build a golden…