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 castorini/castorini-skills --skill castorini-servegit clone --depth 1 https://github.com/castorini/castorini-skillsWrote 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/castorini/castorini-skills/castorini-serve)<a href="https://agentmods.dev/skills/castorini/castorini-skills/castorini-serve"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-serve/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/castorini/castorini-skills/castorini-serve"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-serve.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 | $0.00081 | $0.00771 |
| Opus 5 | $0.00041 | $0.00385 |
| Sonnet 5 | $0.00016 | $0.00154 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
castorini-serve scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Use when serving Anserini retrieval together with any subset of rank_llm, ragnarok, nuggetizer, or umbrela over HTTP, especially for local port planning, direct request payload compatibility, curl or jq pipe How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Castorini Serve
Serve the Castorini stack as cooperating local HTTP services.
Treat Anserini retrieval as the entry point, then add only the downstream services the user actually needs. Prefer gpt-4o as the default OpenAI-backed model for rank_llm, ragnarok, nuggetizer, and umbrela unless the user explicitly asks for a different model.
Default Stack
Use this local port layout unless the user asks for different ports:
8081— AnseriniRestServer8082—rank_llm serve http8083—ragnarok serve8084—umbrela serve8085—nuggetizer serve
Service Selection
- Retrieval only: serve Anserini through
io.anserini.api.RestServer. - Retrieval + rerank: add
rank_llm. - Retrieval + answer generation: use Anserini ->
ragnarok, or Anserini ->rank_llm->ragnarok. - Retrieval + relevance judgment: use Anserini ->
umbrela, or Anserini ->rank_llm->umbrela. - Retrieval + nugget creation: use Anserini ->
nuggetizer create, or Anserini ->rank_llm->nuggetizer create. - Full answer-evaluation flow: keep the original retrieval or rerank payload for
nuggetizer create, generate answers withragnarok, then join the two envelopes fornuggetizer assign.
Reference Files
references/service-recipes.md— startup commands, port conventions, and per-service defaultsreferences/curl-pipelines.md— direct curl, pipe, jq, and full multi-step examples
Gotchas
rank_llmserves HTTP asrank-llm serve http ..., not plainrank-llm serve ....- The Anserini fatjar skill documents standalone
RestServeron8080, but the shared Castorini HTTP stack uses8081by convention so the other services can stay on8082through8085. ragnarok,nuggetizer create, andumbrelacan accept raw Anserini search payloads directly because they normalize{query, candidates}inputs.ragnarok,nuggetizer create, andumbrelacan also accept thecastorini.cli.v1envelope returned byrank_llm, so a raw pipe fromrank_llmusually works.nuggetizer createmust consume the retrieval pool, notragnarokanswer output.nuggetizer assigndoes not consume a bareragnarokenvelope by itself; wrapanswer_envelopeplusnugget_envelope, oranswers_envelopeplusnugget_envelope, withjq.umbrelajudges passage relevance, not answer quality. For answer quality, use theragnarokplusnuggetizerpath instead.
What ships with it
3 files 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.
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.
- 12d ago First seen · 48 lines · 81 tokens per session scan A 2cce85b59811
castorini-serve is a skill published in the GitHub repository castorini/castorini-skills (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 771 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
azure-search-documents-ts
Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.
convex-agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
langchain4j-spring-boot-integration
Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot…
azure-search-documents-py
Full-text, vector, and hybrid search with AI enrichment capabilities.