What is production-rag-checklist?

A checklist for preparing retrieval-augmented generation (RAG) systems for production. RAG systems retrieve relevant documents and give them to an AI model to help form an answer.

Use it when planning or reviewing a production RAG data pipeline and vector store.

It helps teams check data updates, document splitting, embeddings, vector indexes, scaling, backups, and access controls before deployment.

production-rag-checklist — Skill for Claude Code by latestaiagents

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 latestaiagents/agent-skills --skill production-rag-checklist

Clone the repo

git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install rag-architect, the plugin that ships this one along with the rest of its 7 skills, 3 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/production-rag-checklist/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/production-rag-checklist)

Your own site

<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/production-rag-checklist"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/production-rag-checklist/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/production-rag-checklist"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/production-rag-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,278 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.02278
Opus 5	$0.00030	$0.01139
Sonnet 5	$0.00012	$0.00456
Haiku 4.5	$0.00006	$0.00228

Measured 7d ago against content hash 06b8a540daba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

production-rag-checklist 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.

plugins/rag-architect/skills/production-rag-checklist/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Production RAG Checklist

Everything you need to deploy RAG systems with confidence.

Pre-Production Checklist

Data Pipeline

Document ingestion automated
- Scheduled updates for dynamic sources
- Change detection for modified documents
- Deletion handling for removed documents
Chunking strategy validated
- Chunk sizes tested with retrieval quality
- Overlap tuned for context preservation
- Document-specific splitters for code/tables
Metadata enriched
- Source tracking (URL, file path, version)
- Timestamps (created, updated, indexed)
- Document type classification
- Access control tags (if needed)
Embedding pipeline robust
- Batch processing for efficiency
- Rate limiting for API-based embeddings
- Fallback for embedding failures
- Version tracking for re-embedding

Vector Store

Index configured properly
- Appropriate index type (HNSW, IVF, etc.)
- Parameters tuned (ef_construction, m, nlist)
- Distance metric matches embedding model
Scaling planned
- Estimated vector count and growth rate
- Sharding strategy if needed
- Backup and recovery procedures
High availability
- Replicas configured
- Failover tested
- Connection pooling enabled

Retrieval Quality

Evaluation dataset created
- Minimum 100 query-answer pairs
- Edge cases covered
- Regular updates with new patterns
Baseline metrics established
- Recall@5 > 0.8
- MRR > 0.7
- Latency p99 < 500ms
Hybrid search configured (if applicable)
- BM25/keyword weight tuned
- Reranker added and tested

Generation Quality

Prompt engineering complete
- System prompt tested across scenarios
- Few-shot examples if needed
- Output format specified
Guardrails in place
- Hallucination detection
- Toxicity filtering
- PII redaction (if needed)
Fallback responses defined
- "I don't know" for low confidence
- Error messages user-friendly

Read the full file on GitHub · 333 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.

7d ago First seen · 333 lines · 60 tokens per session scan A 06b8a540daba

Subscribe to this mod's changes

production-rag-checklist is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 2,278 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.

Data and AI RAG and vectors agentic-ai agentic-rag agentic-workflow agentshub agentskills ai

agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

ruvnet/ruflo · 25 tokens

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

ruvnet/ruflo · 62 tokens

production-rag-checklist