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 alivirgo/Major-AI-Skills --skill rag-retrieval-auditgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/rag-retrieval-audit)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/rag-retrieval-audit"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/rag-retrieval-audit/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/alivirgo/major-ai-skills/rag-retrieval-audit"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/rag-retrieval-audit.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 | $0.00066 | $0.03890 |
| Opus 5.5 | $0.00026 | $0.01556 |
| Sonnet 5.5 | $0.00013 | $0.00778 |
| Haiku 4.5 | $0.00007 | $0.00389 |
Grade A, and why
rag-retrieval-audit 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 21d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Retrieval Audit AI Skill Guide (Claude)
Overview & Engine Architecture
A RAG system fails in stages. Most “the model is wrong” tickets are retrieval, indexing, chunking, filter, or context-assembly failures that a stronger generator only hides with fluent guesses. This skill audits the retriever path only: did the answer-bearing evidence enter the final model context at the application’s real cutoff K?
Claude operates as a Principal RAG Reliability Engineer, specializing in stage-isolated failure taxonomy, ID-based Recall@K / MRR / nDCG, chunk-boundary forensics, hybrid-search arm health, and ACL-safe relevance denominators.
┌─────────────────────────────────────────────────────────────┐
│ RAG Retrieval Audit Stack │
│ │
│ Corpus governance │
│ ├── Source docs → parse → chunk → embed → index revision │
│ └── Metadata: ACL, tenant, version/hash, embedding_model │
│ │
│ Query path │
│ ├── Rewrite / expand → dense ± sparse (BM25) → fuse (RRF) │
│ ├── Optional rerank → filters/thresholds → context pack │
│ └── Generator (out of scope for retrieval metrics) │
│ │
│ Audit harness │
│ ├── Labeled queries + eligible relevant chunk/doc IDs │
│ ├── Per-query traces (retrieved IDs, ranks, scores, filters│
│ └── Metrics @ app K: hit-rate, Recall@K, Precision@K, MRR, │
│ nDCG; separate faithfulness later │
└─────────────────────────────────────────────────────────────┘
When to use / when not to
Use when
- Answers are confident but wrong, and you need to know if evidence was missing vs ignored.
- You are changing chunk size, embeddings, hybrid weights, filters, or rerankers.
- Production has zero-result or “wrong doc family” clusters.
- Compliance requires proving which sources were eligible for a user.
What ships with it
2 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.
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.
- 21d ago Changed · +286 lines · +36 tokens per session 6b39bbb16512
- 1mo ago First seen · 35 lines · 30 tokens per session scan A c7da20e526d9
rag-retrieval-audit is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 3,890 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 2026-09-12.
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…
ai-pipeline-orchestration
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.