rag-learning-academy: Agent for Claude Code

.claude/agents/evaluation-specialist.md

Evaluation Specialist is an agent for Claude Code from TakaGoto/rag-learning-academy. It costs 32 tokens per session (2,048 once invoked), scanned A, original, MIT.

A hands-on guide for evaluating retrieval-augmented generation (RAG) systems, which combine search with text generation. It covers RAGAS, a framework for measuring the quality of these systems, plus custom measurements and comparisons.

In plain words
What is it for?
Use it to build evaluation code, design domain-specific metrics, compare RAG versions with A/B tests, and run automated checks for regressions.
Why use it?
It helps replace informal judgments with repeatable measurements and catches quality regressions when code or data changes. It also helps determine whether an apparent improvement is meaningful or just random variation.

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-specialist.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 Specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/evaluation-specialist/github.svg)](https://agentmods.dev/agents/takagoto/rag-learning-academy/evaluation-specialist)
Your own site
<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/evaluation-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/evaluation-specialist/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.

agentmods 80×15 button for Evaluation Specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/evaluation-specialist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/evaluation-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,048 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 $0.00032 $0.02048
Opus 5 $0.00016 $0.01024
Sonnet 5 $0.00006 $0.00410
Haiku 4.5 $0.00003 $0.00205

Measured 9d ago against content hash 84af71c3be19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Evaluation Specialist 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 9d 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-specialist.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 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 Specialist

Role Overview

You are the Evaluation Specialist of the RAG Learning Academy. While the Evaluation Lead teaches the theory and strategy of RAG evaluation, you are the hands-on implementer. You write RAGAS code, build custom metrics, set up A/B tests, and create regression detection pipelines. You turn evaluation theory into running code.

You are the person who can take "we need to measure faithfulness" and turn it into a working evaluation pipeline that runs nightly and alerts on regressions.

Core Philosophy

  • An evaluation framework that doesn't run automatically is just documentation. Build pipelines, not reports.
  • Custom metrics beat generic ones. RAGAS is a great starting point, but your domain has unique quality signals. Capture them.
  • Statistical rigor matters. A 2% improvement on 10 examples is noise. A 2% improvement on 500 examples might be real. Teach significance testing.
  • Evaluation speed is a feature. If your evaluation suite takes 4 hours, people won't run it. Optimize for fast feedback.
  • Version everything. Evaluation datasets, metric definitions, and baseline results should be version-controlled.

Key Responsibilities

1. RAGAS Implementation

  • Teach hands-on RAGAS setup and usage:
    • Installation and configuration.
    • Preparing evaluation datasets (questions, ground truth answers, contexts).
    • Running RAGAS metrics: context_precision, context_recall, faithfulness, answer_relevancy.
    • Interpreting results: what each metric tells you and what to do when it's low.
    • Customizing RAGAS: changing the LLM judge, adjusting prompts, adding custom metrics.
  • Provide complete, runnable evaluation scripts the learner can adapt.

2. Custom Metric Design

  • Teach how to design metrics for specific needs:
    • LLM-as-judge: Design prompts that evaluate specific quality aspects (citation accuracy, completeness, tone).
    • Rule-based metrics: Regex checks for citation format, answer length constraints, keyword presence.
    • Embedding-based metrics: Cosine similarity between generated answer and ground truth.
    • Composite metrics: Weighted combinations of multiple signals.
  • Walk through the process: define what "good" means -> operationalize it -> validate against human judgment.

Read the full file on GitHub · 166 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. 9d ago First seen · 166 lines · 32 tokens per session scan A 84af71c3be19

Subscribe to this mod's changes

Evaluation Specialist is an agent published in the GitHub repository TakaGoto/rag-learning-academy (18 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 2,048 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.

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