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 skills add CrestApps/CrestApps.AgentSkills --skill orchardcore-ai-data-sourcesgit clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkillsWrote 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/crestapps/crestapps.agentskills/orchardcore-ai-data-sources)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-data-sources"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-data-sources/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/crestapps/crestapps.agentskills/orchardcore-ai-data-sources"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-data-sources.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 | $0.00204 | $0.03151 |
| Opus 5 | $0.00102 | $0.01576 |
| Sonnet 5 | $0.00041 | $0.00630 |
| Haiku 4.5 | $0.00020 | $0.00315 |
Grade A, and why
orchardcore-ai-data-sources 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 9d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchard Core AI Data Sources - Prompt Templates
Configure AI Data Sources
You are an Orchard Core expert. Generate code, configuration, and recipes for configuring AI data sources in Orchard Core using CrestApps modules to enable knowledge base indexing and RAG (Retrieval-Augmented Generation) search.
Guidelines
- AI Data Sources provide knowledge base indexing and RAG search capabilities for AI profiles in Orchard Core.
- A data source maps a source index (e.g., Lucene, Elasticsearch, Azure AI Search content index) to an AI knowledge base index that stores chunked, embedded documents for vector search.
- The indexing pipeline reads documents from the source index, generates embeddings via a configured embedding deployment, chunks content, and writes vector documents into the knowledge base index.
- Supported knowledge-base index backends are Azure AI Search and Elasticsearch. Source documents can also be read from a PostgreSQL table with the PostgreSQL source module.
- The
DataSourceAlignmentBackgroundTaskruns daily at 2 AM to keep knowledge base indexes aligned with their mapped data sources. - Content item changes (create, update, publish, unpublish, remove) are automatically tracked and queued for re-indexing via
DataSourceContentHandler. - Data source configuration (source index, knowledge base index, field mappings) is locked after initial creation and cannot be changed.
- AI profiles reference data sources on the Knowledge tab, where you configure strictness, top-N documents, in-scope filtering, and OData filters.
- Strictness controls how closely results must match the query. Top-N documents limits how many retrieved documents are included in the AI context.
- Always secure API keys using user secrets or environment variables; never hardcode them.
- Install CrestApps packages in the web/startup project.
Feature Overview
| Feature | Feature ID | Description |
|---|---|---|
| AI Data Sources (Core) | CrestApps.OrchardCore.AI.DataSources |
Core data source management, indexing pipeline, and RAG search |
| AI Data Sources - Azure AI Search | CrestApps.OrchardCore.AI.DataSources.AzureAI |
Azure AI Search backend for embeddings, vector search, and indexing |
| AI Data Sources - Elasticsearch | CrestApps.OrchardCore.AI.DataSources.Elasticsearch |
Elasticsearch backend for embeddings, vector search, and indexing |
| AI Data Sources - PostgreSQL | CrestApps.OrchardCore.AI.DataSources.PostgreSQL |
Reads source documents from a PostgreSQL table using explicit connection settings |
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.
- 9d ago First seen · 317 lines · 204 tokens per session scan A e3898098c44a
orchardcore-ai-data-sources is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed 11d ago), licensed MIT. It adds 204 tokens to every session and 3,151 once invoked, about $0.0010 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.
Other skills, from other repositories
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
microsoft-extensions-ai
Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator…
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
opik-evaluate
Build an LLM evaluation and run it against your app, returning an experiment with scores. Covers datasets, LLM judges, RAG evaluation, synthetic data, error analysis, and validating evaluators against human labels. Use when the user wants to measure or improve AI product quality, or asks about evals, judges, or…
haiku-rag
Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own…
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…