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 GuitarAlchemist/ga --skill semantic-rag-architecturegit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/semantic-rag-architecture)<a href="https://agentmods.dev/skills/guitaralchemist/ga/semantic-rag-architecture"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/semantic-rag-architecture/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/guitaralchemist/ga/semantic-rag-architecture"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/semantic-rag-architecture.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 | $0.00033 | $0.00779 |
| Opus 5 | $0.00016 | $0.00390 |
| Sonnet 5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
Semantic Search & RAG Architecture 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Search & RAG Architecture
This skill governs the development of AI search capabilities, specifically within GA.Business.ML and the Common/GA.Domain.Services/Fretboard/Voicings search namespaces. It ensures that our vector search infrastructure remains consistent, deterministic, and high-performance.
1. Embedding Fundamentals
1.1 Model Standard
- Provider: ONNX Runtime.
- Model:
all-MiniLM-L6-v2(Quantized). - Dimensions: 384 (Fixed).
- Constraint: Never change the embedding model or dimension count without a coordinated full-system re-index. Doing so will break all existing vector search features.
1.2 Schema Governance
- Use the OPTIC-K Schema Guardian skill for specific weighting and dimension mapping rules. This skill focuses on the architecture around those embeddings.
2. Indexing Strategy
2.1 Deterministic Identity
Document IDs in the vector store must be deterministic and reproducible from the domain entity itself. Never use random UUIDs for domain entities.
- Format:
entity_type_discriminator - Example (Voicing):
voicing_standard_0_x_3_2_0_1_0(tuning + capo + fret diagram)
2.2 Document Payloads (Metadata)
- Searchable Text: Must be a natural language representation of the entity (e.g., "C Major 7 open chord high comfort").
- Facets: Store filtering fields (Difficulty, HandStretch, OmittedTones) as raw types (int, bool, string[]) in the payload to enable hybrid search (Vector + Filter).
3. RAG Pipeline & Orchestration
3.1 Retrieval Hierarchy
When assembling context for LLMs (e.g., Chatbot):
- Direct Match: Exact entity lookups (by name or text).
- Semantic Match: Vector neighbors (Top-K).
- Theoretical Context: Related keys/scales derived from the retrieved entities.
3.2 Context Window Management
- Token Budget: 4096 tokens (typical local model).
- Priority: System Prompt > User Query > Retrieved Voicings > Theoretical Rules.
- Truncation: Truncate the least relevant distinct search results first, preserving the highest-scored matches.
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.
- 10d ago First seen · 62 lines · 33 tokens per session scan A b2d73c7ad767
Semantic Search & RAG Architecture is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 779 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.