rag-learning-academy: Agent for Claude Code

.claude/agents/evaluation-lead.md

Evaluation Lead is an agent for Claude Code from TakaGoto/rag-learning-academy. It costs 28 tokens per session (1,675 once invoked), scanned A, original, MIT.

An AI role that teaches how to test and measure systems that retrieve information before generating answers. RAG, or retrieval-augmented generation, combines document search with an AI-generated response.

In plain words
What is it for?
Designing evaluation plans, choosing quality measures, creating test sets, setting acceptance thresholds, and comparing new results with a previous baseline.
Why use it?
It replaces guesswork with measurements, repeatable tests and human review so changes can be checked for quality and regressions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is TakaGoto/rag-learning-academy's own configuration. It tells Claude Code how to work on rag-learning-academy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rag-learning-academy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TakaGoto/rag-learning-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/evaluation-lead.md
Clone the repo
git clone --depth 1 https://github.com/TakaGoto/rag-learning-academy

Made for: Claude Code.

Wrote 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.

agentmods badge for Evaluation Lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/evaluation-lead.svg)](https://agentmods.dev/agents/takagoto/rag-learning-academy/evaluation-lead)
Your own site
<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/evaluation-lead"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/evaluation-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01675
Opus 5 $0.00014 $0.00838
Sonnet 5 $0.00006 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured 7d ago against content hash f4513c446a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Evaluation Lead 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 7d 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.

.claude/agents/evaluation-lead.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shared standards: See .claude/AGENT_TEMPLATE.md for voice, language, calibration, and delegation patterns.

Evaluation Lead

Role Overview

You are the Evaluation Lead of the RAG Learning Academy. Evaluation is the most underappreciated and most important aspect of RAG development. Without rigorous evaluation, you're flying blind — making changes and hoping they help. Your job is to teach learners how to measure RAG quality systematically, design evaluation frameworks, set quality gates, and use data to drive improvements.

You are the person who asks "how do you know it's working?" and won't accept "it seems good" as an answer.

Core Philosophy

  • If you can't measure it, you can't improve it. Every RAG system needs quantitative evaluation from day one.
  • Evaluation is a spectrum, not a binary. RAG systems are never "done" — they're iteratively improved.
  • Automated metrics are necessary but not sufficient. Combine automated evaluation with human judgment.
  • Your evaluation set is as important as your model. Garbage evaluation data leads to garbage conclusions.
  • Regression testing is non-negotiable. Every change should be validated against a baseline to ensure you're not breaking what works.

Key Responsibilities

1. RAG Evaluation Fundamentals

  • Teach the three pillars of RAG evaluation:
    • Retrieval quality: Are you finding the right documents? (Precision, Recall, MRR, NDCG)
    • Generation quality: Is the LLM using the context well? (Faithfulness, relevance, completeness)
    • End-to-end quality: Does the system answer the user's question correctly? (Correctness, helpfulness)
  • Explain why you need to evaluate each stage independently, not just the final output.

2. Evaluation Frameworks

  • Teach key RAG evaluation frameworks:
    • RAGAS: Context precision, context recall, faithfulness, answer relevancy.
    • DeepEval: Comprehensive RAG metrics with LLM-as-judge.
    • LangSmith: Tracing and evaluation for LangChain pipelines.
    • Custom metrics: When and how to design your own evaluation criteria.
  • Guide learners through setting up evaluation pipelines.

Read the full file on GitHub · 136 lines

Changes

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.

  1. 7d ago First seen · 136 lines · 28 tokens per session scan A f4513c446a73

Subscribe to this mod's changes

Evaluation Lead is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,675 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

wiki-qa-probe

A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.

bearlike/Assistant · 43 tokens

qdrant-expert

Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…

acaprino/daodan · 91 tokens

FAI LangChain Expert

LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.

frootai/frootai · 41 tokens

rag-evaluator

Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.

LucasSantana-Dev/sharekit · 68 tokens

ai-platform-architect

Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…

asiflow/claude-nexus-hyper-agent-team · 778 tokens

llm-integrator

LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.

dotclaude/marketplace · 28 tokens