AutoRAG Agent is a librarian-style system that searches files on a computer, checks the original documents, and organizes findings into numbered knowledge units using multiple retrieval methods. It helps an agent answer questions from local documents without first copying them into a centralized vector database, while the repository also maintains the earlier AutoRAG tool for optimizing retrieval-augmented-generation pipelines. The catalogue entries provide skills and instructions for working with AutoRAG Agent.
Borrowing it
Nothing to install: this file belongs to Marker-Inc-Korea/AutoRAG. 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/Marker-Inc-Korea/AutoRAG/main/.github/ISSUE_TEMPLATE/datasource-skill.mdgit clone --depth 1 https://github.com/Marker-Inc-Korea/AutoRAGWrote 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/marker-inc-korea/autorag/datasource)<a href="https://agentmods.dev/skills/marker-inc-korea/autorag/datasource"><img src="https://agentmods.dev/badge/skills/marker-inc-korea/autorag/datasource/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/marker-inc-korea/autorag/datasource"><img src="https://agentmods.dev/badge/skills/marker-inc-korea/autorag/datasource.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.00452 |
| Opus 5.5 | $0.00005 | $0.00181 |
| Sonnet 5.5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
Datasource skill integration 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 1mo 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
Related: Agent task template for implementation work that is not a datasource skill, and the PR template for the pull request itself.
Datasource
Name: External API/CLI/SDK: Expected owner/maintainer:
Data description
Describe what the datasource contains in human terms. This description may appear in the AutoRAG prompt, so do not include secrets, account IDs, phone numbers, or real local paths.
Hierarchy
Examples:
- workspace -> channel
- account -> folder
- chat export -> room
- repository -> issue/PR
Opaque source root pattern:
/<datasource>/<instance-or-scope>/...
Indexing behavior
- Manual refresh supported
- Polling metadata (
mode: "poll",intervalMs) defined - Cron metadata (
mode: "cron",cronExpr) considered if routine schedule is needed - Missing credentials/binary/API permission returns diagnostics, not throws
Search behavior
- Retrieval methods plug into
RetrievalMethodRegistry - Results use opaque slash-hierarchical source IDs
- Source descriptions explain content without leaking storage paths
- Public
SearchDocumentsResponsestays path/PII opaque
Access boundaries
- Default deny without trusted
allowedTags - Trusted
allowedScopesenforced before merge - User/tool
scopeonly narrows trusted scopes - LLM tool arguments cannot grant tags/scopes
- Permission tags listed:
Tests
- Default deny
- Multi-scope filtering
- User-scope intersection
- Hash-fragment rejection
- No-throw diagnostics
- Path/PII leak regression
- Datasource-specific auth/rate-limit failures
Manual QA
Describe the smallest safe manual QA scenario and any credentials or local-app permissions required.
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.
- 1mo ago Changed · +2 lines 2f84fa648acf
- 1mo ago First seen · 67 lines · 12 tokens per session scan A 1fdb60b1d7eb
Datasource skill integration is a skill published in the GitHub repository Marker-Inc-Korea/AutoRAG (5,191 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 452 once invoked, about $0.0000 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 2026-09-05.
Other skills, from other repositories
rag-pipeline
Build a retrieval-augmented generation pipeline — chunking, indexing, retrieval, and grounded answer synthesis.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
huggingface-transformers
Use when running or fine-tuning Hugging Face Transformers models in Python — pipeline() inference for text classification and generation, loading weights with AutoModel/AutoTokenizer, devicemap and dtype memory management, tokenizer usage, Trainer fine-tuning, and BGE embeddings for Chinese RAG. Covers transformers…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…