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 perniemann/pnCore --skill pn-rag-evaluationgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-rag-evaluation)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-rag-evaluation"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-rag-evaluation/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/perniemann/pncore/pn-rag-evaluation"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-rag-evaluation.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 | $0.00062 | $0.01292 |
| Opus 5 | $0.00031 | $0.00646 |
| Sonnet 5 | $0.00012 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
pn-rag-evaluation 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG evaluation
When to use
- Adding or changing chunking, embeddings, rerankers, or retrieval top-k
- Before promoting a RAG release to production or a large user cohort
- After incidents: hallucinated citations, wrong doc retrieved, "empty" answers
- Setting up CI so RAG changes cannot silently degrade quality
When not to use
- Pure generative Q&A with no retrieval (use normal eval harnesses)
- Full search-engine relevance tuning without generation (IR metrics only)
Evaluation layers (run all three for production-grade)
| Layer | Purpose | Owner |
|---|---|---|
| Golden set | Fixed questions + expected behavior | Engineering |
| Automated metrics | Scalable regression signal | CI + notebooks |
| Human rubric | Catches what metrics miss | Product / SME spot checks |
1. Golden set
Build a versioned dataset (JSONL or table) with at least:
| Field | Content |
|---|---|
id |
Stable id |
question |
User query (realistic phrasing) |
gold_docs or gold_chunk_ids |
Doc ids or chunk ids that should be retrievable (when known) |
answer_policy |
must_cite, refuse_if_missing, or acceptable paraphrase notes |
must_not |
Forbidden claims or sources (optional) |
Sizing: Start 50–200 items covering head + long tail; expand per domain. Stratify: easy retrieval, multi-hop, ambiguous, adversarial (prompt injection in retrieved text).
Regression rule: New pipeline version must meet or beat baseline on the golden set (see §4).
2. Automated metrics
Use framework-agnostic goals; implement with RAGAS, deepeval, custom LLM-judge, or classical IR where appropriate.
| Concern | What to measure | Notes |
|---|---|---|
| Faithfulness / groundedness | Answer supported by retrieved context | Penalize facts not in context |
| Answer relevance | Answer addresses the question | Not just fluent |
| Context precision | Retrieved chunks are useful | Reduce noise |
| Context recall | Needed facts appear in retrieved set | Tune k, chunking, reranker |
| Citation alignment (if citations exposed) | Quoted spans exist in cited chunks | Prevents fake cites |
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.
- 5d ago First seen · 121 lines · 62 tokens per session scan A 72582b7527df
pn-rag-evaluation is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,292 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 2026-09-03.
Other skills, from other repositories
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
dbt-transformation-patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
generate-rag-dataset
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
trulens-running-evaluations
Execute TruLens evaluations and view results.
neuron-test-engineer
Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.