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/sigistry/marketplaceWrote 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/sigistry/marketplace/rag-tune)<a href="https://agentmods.dev/commands/sigistry/marketplace/rag-tune"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/rag-tune/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.
<a href="https://agentmods.dev/commands/sigistry/marketplace/rag-tune"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/rag-tune.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00752 |
| Opus 5 | $0.00008 | $0.00376 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
rag-tune 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the RAG (retrieval-augmented generation) pipeline at $ARGUMENTS (default: directories that look like a pipeline, rag/, ingest/, retrieval/, embeddings/, or files importing a vector store) for both answer quality and cost, and output prioritized, concrete fixes. Most RAG quality problems are retrieval problems, not model problems: the right chunk never reaches the context, or the wrong chunks crowd it out. This is a static read of the pipeline code and config, no index rebuild or query run required.
Process
Step 1: Detect the stack
Identify the framework and vector store from imports and config:
| Layer | Signal |
|---|---|
| Framework | langchain, llama-index, haystack, or hand-rolled retrieval |
| Vector store | pinecone, weaviate, qdrant, chroma, pgvector, faiss, milvus |
| Embeddings | embedding model name/dimension in config or client calls |
| Reranker | cohere.rerank, rerank, cross-encoder, bge-reranker, or none |
Step 2: Audit each stage
Walk the pipeline stage by stage and flag issues with the file:line where each is configured:
| Stage | What to check |
|---|---|
| Chunking | Strategy (fixed vs. recursive vs. semantic), size, and overlap; whether chunks split mid-sentence/mid-table and whether structure (headings, code, tables) is preserved |
| Embedding model | Fit for domain and language; dimension vs. store config; query/document asymmetry; staleness vs. current models |
| Retrieval | top_k, similarity metric, metadata/namespace filtering, hybrid (dense + keyword/BM25) vs. pure vector |
| Reranking | Presence of a reranker; over-fetch-then-rerank (retrieve N, rerank to k); model choice |
| Context assembly | Ordering (lost-in-the-middle: strongest evidence at the ends), dedup, token budget, and whether low-score chunks are padding the prompt |
| Grounding / citations | Whether the prompt demands source-grounded answers and returns citations; guard against answering from unretrieved knowledge |
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.
- 6d ago First seen · 43 lines · 16 tokens per session scan A 84cb32036ee9
rag-tune is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 752 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 2026-09-03.
Other commands, from other repositories
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.
index
Index this repository for local RAG search, then report which rung it is on — descriptions still to write, a promotion to apply, or nothing left.
prompt-review
Scan prompts for ground rule, KISS/DRY, AI sweep, and context budget violations.
prompt-optimize
Apply fixes for issues found by prompt-review.
prompt-create
Create a new prompt following ground rules.
new-rag
Scaffold a new RAG (Retrieval-Augmented Generation) pipeline with best practices.