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.
npx skills add ggozad/haiku.rag --skill haiku-raggit clone --depth 1 https://github.com/ggozad/haiku.ragWrote 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/skills/ggozad/haiku.rag/haiku-rag)<a href="https://agentmods.dev/skills/ggozad/haiku.rag/haiku-rag"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.rag/haiku-rag/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/skills/ggozad/haiku.rag/haiku-rag"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.rag/haiku-rag.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 | $0.00076 | $0.00917 |
| Opus 5 | $0.00038 | $0.00458 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
haiku-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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with the knowledge base
Check the knowledge base before answering from memory whenever the question could be about the user's documents. Say so when it has nothing relevant.
Find
search_documents is the first call. Results come best first with the document
title, section headings, the matched chunk's metadata when it has any, and the
passage in its section. Pictures in the results arrive as images: answer
figure questions from them. filter restricts which documents are searched,
limit how many results come back. If it misses, rephrase once or narrow with
a filter before concluding the material is not there. When the question is
about an image rather than words and the server offers
search_documents_by_image, it takes the image as the query.
Read
Every search result shows its Document ID (and Collection when there are
several); pass them to the read tools. get_document returns a document's
whole text in reading order. For a long one, get_document_outline gives the
heading tree with page numbers and get_document_section the text of one
section, subsections included.
Compute
execute_code runs a Python program on the server over the same documents.
Under /documents/{id}/ each has metadata.json, content.txt, items.jsonl,
chunks.jsonl and toc.json, and the program can await search(query) and
await list_documents(). Write code when the answer is a count, an aggregate, a
comparison across many documents, a lookup by document or chunk metadata, or a
pattern over whole documents: whatever search cannot rank. Each call is one
program and variables do not carry over, so gather, compute and print a
compact result in the same program. filter and sources select the documents
it sees. For a known document's structure read its toc.json first; search()
ranks across every document. Map a title or URI to an id with one
list_documents() call rather than reading every metadata.json; the files
carry no source, so over several collections group by its rows. Answer and
cite from what it printed.
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.
- 2d ago First seen · 78 lines · 76 tokens per session scan A 8eb18b207f7d
haiku-rag is a skill published in the GitHub repository ggozad/haiku.rag (606 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 917 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
hybrid-rag
Use when creating, updating, or querying a local Hybrid RAG database from PRISMA JSON metadata or PDF documents in a folder. Triggered by prisma-review (after Fase 4) or educational-pilot-design (to query evidence). Hybrid RAG combines dense vector search (sentence-transformers) and sparse retrieval — native FTS via…
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
opik-evaluate
Build an LLM evaluation and run it against your app, returning an experiment with scores. Covers datasets, LLM judges, RAG evaluation, synthetic data, error analysis, and validating evaluators against human labels. Use when the user wants to measure or improve AI product quality, or asks about evals, judges, or…
basemind-documents
Semantic + full-text search over documents and the web via basemind's RAG store — PDFs, Office, HTML, email, images (OCR), plus scraped/crawled web pages, with cross-encoder reranking, keyword and named-entity (NER) filters, and per-document summaries. Reach for it whenever the user asks to "search the docs / PDFs"…
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…