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 zorost/AI-Engineering-Lab --skill rag-pipeline-checkupgit clone --depth 1 https://github.com/zorost/AI-Engineering-LabWrote 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/zorost/ai-engineering-lab/rag-pipeline-checkup)<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/rag-pipeline-checkup"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/rag-pipeline-checkup/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/zorost/ai-engineering-lab/rag-pipeline-checkup"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/rag-pipeline-checkup.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 | $0.00042 | $0.01038 |
| Opus 5 | $0.00021 | $0.00519 |
| Sonnet 5 | $0.00008 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
rag-pipeline-checkup 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Pipeline Checkup
1 · Purpose
Debug a RAG system as five separable stages, so "the answer was wrong" becomes "retrieval missed the policy section" or "the model ignored the citation", each with its own fix.
2 · When to use
- Building any RAG feature, or when a RAG feature's answers are wrong, ungrounded, or stale.
- Before adding complexity (HyDE, hybrid search, graphs) to a pipeline whose basics are unmeasured.
3 · Inputs
- The document corpus and the chunking code/config.
- A question set: ≥ 20 real questions with the passage that should answer each
(the retrieval golden set, build it with
eval-first-development). - The ability to log intermediate stage outputs.
4 · Procedure
- Chunking. Print 10 random chunks. Check: each chunk is one topic, carries its source and section, and respects the size budget (~300 to 500 tokens with 10 to 15% overlap is the default start). Fix splits that cut tables or definitions in half.
- Embedding. Embed three paraphrases of one question. Confirm they retrieve each other's chunks, if paraphrases diverge wildly, the embedding model does not match the domain. Try a domain-appropriate model before tuning anything else.
- Retrieval. Score the golden set: for each question, is the right passage in the top-k? Record recall@5. Below 0.8, fix retrieval before touching generation, a model cannot cite what it never saw.
- Reranking. Add a reranker over the top-20 and re-measure recall@5 of the reranked top-5. Keep it only if recall rises; record the latency cost either way.
- Generation. Require citations: every factual sentence must reference a retrieved chunk ID, and the answer must say "not in the documents" when retrieval came back empty. A schema constrains shape, never truth, spot-check that cited chunks actually contain the claim.
- End-to-end eval. Score the full pipeline on the question set with the answer grader. Record: retrieval recall, answer score, citation precision (sampled).
- Attribute every failure to exactly one stage. Fix the stage with the most failures first. Re-run the full eval after each fix.
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.
- 11d ago First seen · 92 lines · 42 tokens per session scan A 505f0d9ea3f3
rag-pipeline-checkup is a skill published in the GitHub repository zorost/AI-Engineering-Lab (303 stars, last pushed 24d ago), licensed MIT. It adds 42 tokens to every session and 1,038 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 2026-08-30.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready 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.
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.
ai-engineering-toolkit
AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready 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 and the operator…
ai-engineer
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design…
fine-tuning-os
Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
ai-engineering-toolkit
6 production-ready 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.