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 agentmods add skills/yonatangross/orchestkit/rag-retrievalnpx skills add yonatangross/orchestkit --skill rag-retrievalgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/rag-retrieval)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/rag-retrieval"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/rag-retrieval.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.04412 |
| Opus 5 | $0.00029 | $0.02206 |
| Sonnet 5 | $0.00012 | $0.00882 |
| Haiku 4.5 | $0.00006 | $0.00441 |
Grade A, and why
rag-retrieval 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 today.
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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Retrieval
Comprehensive patterns for building production RAG systems. Each category has individual rule files in rules/ loaded on-demand.
House thresholds, fusion ordering, and the latency and quality budgets we assert live in House delta below. Vendor documentation is linked, not restated (see Upstream coverage).
Quick Reference
| Category | Rules | Impact | When to Use |
|---|---|---|---|
| Core RAG | 4 | CRITICAL | Basic RAG, citations, hybrid search, context management |
| Embeddings | 3 | HIGH | Model selection, chunking, batch/cache optimization |
| Contextual Retrieval | 3 | HIGH | Context-prepending, hybrid BM25+vector, pipeline |
| HyDE | 3 | HIGH | Vocabulary mismatch, hypothetical document generation |
| Agentic RAG | 4 | HIGH | Self-RAG, CRAG, knowledge graphs, adaptive routing |
| Multimodal RAG | 3 | MEDIUM | Image+text retrieval, PDF chunking, cross-modal search |
| Query Decomposition | 3 | MEDIUM | Multi-concept queries, parallel retrieval, RRF fusion |
| Reranking | 3 | MEDIUM | Cross-encoder, LLM scoring, combined signals |
| PGVector | 4 | HIGH | PostgreSQL hybrid search, HNSW indexes, schema design |
Total: 30 rules across 9 categories
Core RAG
Fundamental patterns for retrieval, generation, and pipeline composition.
| Rule | File | Key Pattern |
|---|---|---|
| Basic RAG | rules/core-basic-rag.md |
Retrieve + context + generate with citations |
| Hybrid Search | rules/core-hybrid-search.md |
RRF fusion (k=60) for semantic + keyword |
| Context Management | rules/core-context-management.md |
Token budgeting + sufficiency check |
| Pipeline Composition | rules/core-pipeline-composition.md |
Composable Decompose → HyDE → Retrieve → Rerank |
Embeddings
Embedding models, chunking strategies, and production optimization.
What ships with it
42 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- checklists/rag-quality.md 1.9 KB
- checklists/search-implementation-checklist.md 18 KB
- examples/chatbot-with-rag-example.ts 1.8 KB runs code
- metadata.json 570 B
- rules/_sections.md 3.2 KB
- rules/_template.md 339 B
- rules/agentic-adaptive-retrieval.md 2.9 KB
- rules/agentic-corrective-rag.md 2.6 KB
- rules/agentic-knowledge-graph.md 1.9 KB
- rules/agentic-self-rag.md 2.8 KB
- rules/contextual-hybrid.md 3.0 KB
- rules/contextual-pipeline.md 3.7 KB
- rules/contextual-prepend.md 3.2 KB
- rules/core-basic-rag.md 3.0 KB
- rules/core-context-management.md 3.3 KB
- rules/core-hybrid-search.md 2.7 KB
- rules/core-pipeline-composition.md 3.4 KB
- rules/embeddings-advanced.md 3.6 KB
- rules/embeddings-chunking.md 3.1 KB
- rules/embeddings-models.md 3.5 KB
- rules/hyde-fallback.md 2.1 KB
- rules/hyde-generation.md 3.3 KB
- rules/hyde-per-concept.md 2.1 KB
- rules/multimodal-chunking.md 3.3 KB
- rules/multimodal-embeddings.md 3.2 KB
- rules/multimodal-pipeline.md 3.9 KB
- rules/pgvector-hybrid-search.md 4.0 KB
- rules/pgvector-indexing.md 3.5 KB
- rules/pgvector-metadata.md 2.2 KB
- rules/pgvector-schema.md 2.4 KB
- rules/query-decompose.md 3.1 KB
- rules/query-detection.md 2.4 KB
- rules/query-hyde-combo.md 2.7 KB
- rules/reranking-combined.md 3.3 KB
- rules/reranking-cross-encoder.md 2.3 KB
- rules/reranking-llm.md 3.9 KB
- scripts/chunk-repository.py 10 KB runs code
- scripts/rag-pipeline-template.ts 8.8 KB runs code
- scripts/scripts/crag-workflow.py 18 KB runs code
- scripts/scripts/self-rag-graph.py 16 KB runs code
- scripts/search-service.py 5.5 KB runs code
- test-cases.json 15 KB
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.
- today First seen · 359 lines · 58 tokens per session scan A a858fb8a4bc5
rag-retrieval is a skill published in the GitHub repository yonatangross/orchestkit (228 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 4,412 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
rag-expert
Design retrieval-augmented generation systems: chunking, embeddings, vector and hybrid search, reranking, grounding and evaluation. Use when the user mentions RAG, retrieval, semantic search, embeddings, vector databases, pgvector, Chroma, Qdrant, Pinecone, chunking or reranking, wants an assistant answering over…
Vector Databases
Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
nemotron-retrieval-recipes
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
rag-pipeline
Build a retrieval-augmented generation pipeline — chunking, indexing, retrieval, and grounded answer synthesis.