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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/dev-rag)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/dev-rag"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-rag.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00465 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
dev-rag 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent DEV-RAG
Design and implementation of RAG (Retrieval-Augmented Generation) systems.
Request context
$ARGUMENTS
Objective
Design and implement a complete RAG pipeline: ingestion, embedding, vector storage, retrieval and augmented generation with quality evaluation.
Workflow
- Define the chunking strategy (fixed size, semantic, sentence, recursive) with overlap
- Choose the embedding model (text-embedding-3-small/large, voyage-2, e5)
- Configure the vector database (Pinecone, Weaviate, Chroma, pgvector, Qdrant)
- Implement retrieval (similarity, MMR, hybrid, reranking)
- Build the prompt template with context and anti-hallucination guards
- Evaluate with metrics: retrieval precision (>80%), recall (>70%), faithfulness (>90%), latency (<3s)
- Optimize with query expansion or HyDE if necessary
Expected output
RAG architecture with justified technical stack, configuration (chunk size, overlap, top-K, threshold), vector database schema, documented pipeline and evaluation results.
Related agents
| Agent | Usage |
|---|---|
/dev:dev-api |
RAG endpoints |
/ops:ops-database |
DB configuration |
/qa:qa-perf |
System performance |
See also (vendor depth)
This command stays the framework-neutral RAG layer (chunking, embeddings, vector-store choice, retrieval strategy, faithfulness metrics — independent of any one framework). If your project is on LangChain/LangGraph, pair it with langchain-ai/langchain-skills › langchain-rag — LangChain's own skill for the loaders/embeddings/vector-store pipeline. See docs/recipes/recommended-vendor-skills.md §"LangChain — langchain-rag".
IMPORTANT: Always evaluate retrieval quality before tuning generation.
IMPORTANT: Chunking is crucial - test multiple strategies.
YOU MUST implement guards against hallucinations.
NEVER ignore faithfulness metrics.
Think hard about the choice of chunking and embedding model for the use case.
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.
- 3d ago First seen · 51 lines · 0 tokens per session scan A c1ba9ddfdbc2
dev-rag is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 465 tokens. 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 commands, from other repositories
atlas
Architect the intelligence layer — RAG pipelines, model selection, embeddings, and evaluation for agentic systems.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
handoff
Create a handoff document for seamless session continuity.
deps-update
Audit and update dependencies safely.
contract-version-bump
Classify and apply a version bump to a machine-readable contract (JSON Schema, API spec, config schema) — version literals, consumer compatibility, changelog entry, downstream drift.