agentmods.dev

rag-eval

rag-eval is a skill for Claude Code, Codex from glebis/claude-skills. It costs 106 tokens per session (1,457 once invoked), scanned A, original, MIT.

A testing workflow for retrieval-augmented generation (RAG), where an AI searches a document collection before answering. It runs planned comparisons against a set of known questions and answers.

In plain words
What is it for?
It is for comparing RAG pipeline versions, investigating poor answers, and tracking evaluation costs across experiments.
Why use it?
It replaces guesswork when tuning search, prompts, models, or document splitting. Results are ranked with costs and structured feedback so you can see which change actually helps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code.

not rated 413repo +3 2d ago A scan SkillSpector: pass 106 tokens original MIT

Good fit It is for comparing RAG pipeline versions, investigating poor answers, and tracking evaluation costs across experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glebis/claude-skills/rag-eval
View source ↗ glebis/claude-skills skills.salient.community
Install

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.

Any agent
npx skills add glebis/claude-skills --skill rag-eval
Clone the repo
git clone --depth 1 https://github.com/glebis/claude-skills

Made for: Claude Code, Codex.

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 rag-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/glebis/claude-skills/rag-eval/github.svg)](https://agentmods.dev/skills/glebis/claude-skills/rag-eval)
Your own site
<a href="https://agentmods.dev/skills/glebis/claude-skills/rag-eval"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/rag-eval/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 rag-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/glebis/claude-skills/rag-eval"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/rag-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,457 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00106 $0.01457
Opus 5.5 $0.00042 $0.00583
Sonnet 5.5 $0.00021 $0.00291
Haiku 4.5 $0.00011 $0.00146

Measured 2mo ago against content hash 7374ab664deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rag-eval 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/session_ingest.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

rag-eval/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rag-eval

Purpose

Replace the "tweak → squint → swap model → burn credits" loop with a single command that runs a grid of eval variants on the user's gold-set, ranks them by a cost-aware score, and returns structured feedback on architecture, stack, and likely-issues. Draws on evidence-based RAG practices and learns from the user's past runs.

When to use

Trigger on: "help me test a RAG", "tune my RAG", "my RAG is bad", "compare retrieval prompts", "how do I eval this", "what's the best embedding model for X", "my RAG eval is expensive". Also trigger when the user reports burning OpenRouter / OpenAI credits with no clear signal of improvement.

Prerequisites — gather before running

Collect these from the user before the first sweep. Many are optional with sensible defaults; always confirm the ones that gate cost.

  1. RAG codebase root — path to the repo/module under test.
  2. Gold-set — at least 10 Q&A pairs. If missing, offer to generate a starter gold-set from the user's dataset (LLM-synthesized, human-reviewed). See references/best-practices.md.
  3. Dataset — the corpus the RAG retrieves over.
  4. Budget cap — hard dollar limit per run (default: $2 if user doesn't specify). Always confirm before any sweep.
  5. Provider keys — OPENROUTER_API_KEY or OPENAI_API_KEY (read from env).
  6. Vector-store config — collection name, embedding model, chunk size (read from repo; confirm if ambiguous).
  7. Eval history path (optional) — defaults to .rag-eval/history.jsonl in the repo root.

Workflow

Follow this order. Refer to references/best-practices.md for the canonical checklist and references/evidence-base.md for the research-backed defaults.

Step 0 — (Optional) Ingest a prior iteration session

When the user provides a session ID (Claude Code transcript, skill-studio session, or a Fathom meeting), run the deterministic ingest first — no LLM calls. This extracts only the useful signals (models tried, prompt variants, cost events, eval results) as compact JSON, so the rest of the skill works off a tiny structured bundle instead of a long raw transcript.

Read the full file on GitHub · 96 lines

Files

What ships with it

1 file 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.

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. 2mo ago First seen · 96 lines · 106 tokens per session scan A 7374ab664deb

Subscribe to this mod's changes

rag-eval is a skill published in the GitHub repository glebis/claude-skills (413 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,457 once invoked, about $0.0004 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 2026-09-03.

Analytics and metricsData and AIRAG and vectorsagent-skillsclaude-skillscodex-skill
Related

rag-eval compared with skills from other repositories

rag-eval next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rag-evalglebis/claude-skillsSkill4132d agoMITA106Claude Code, Codex
speckit.ai-engineerwedabro/bro-skillsSkill31mo agoMITB35Claude Code, Codex
ChatDOC Studio--KnowledgeMatePaodingAI/skillsSkill1714d agononeA92Codex
cm-deep-searchtody-agent/codymasterSkill562mo agononeA50Claude Code
markitdownK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA62Claude Code, Codex
rag-architectJeffallan/claude-skillsSkill12k2d agoMITA73Claude Code
pgvector-semantic-searchtimescale/pg-aiguideSkill1.9ktodayApache-2.0A190Cursor