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-pipelinegit 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-pipeline)<a href="https://agentmods.dev/skills/castorini/castorini-skills/castorini-pipeline"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-pipeline/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-pipeline"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-pipeline.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 | $0.00056 | $0.00976 |
| Opus 5 | $0.00028 | $0.00488 |
| Sonnet 5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
castorini-pipeline 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 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.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Castorini Pipeline
End-to-end pipeline orchestration across rank_llm, ragnarok, nuggetizer, and umbrela.
Use this skill to reason about handoffs between repositories, not as a substitute for repo-local verification. After each stage, inspect the actual artifacts before advancing.
rank_llm usually belongs before ragnarok: use it to retrieve and rerank candidate passages, then feed those contexts into ragnarok for answer generation and downstream nuggetizer evaluation.
Pipeline Stages
[0. Retrieve + Rerank] rank-llm rerank --dataset ...
│ JSONL / TREC rerank artifacts
▼
[1. Generate Answers] ragnarok generate --dataset ...
│ JSONL (cited answers)
▼
[2. Create Nuggets] nuggetizer create --input-file ...
│ JSONL (scored nuggets)
▼
[3. Assign Nuggets] nuggetizer assign --contexts ... --nuggets ...
│ JSONL (assigned nuggets)
▼
[4. Calculate Metrics] nuggetizer metrics --input-file ...
│ JSONL (per-query scores)
▼
[5. Judge Relevance] umbrela evaluate --qrel ... --result-file ...
│ Modified qrels + nDCG@10
▼
[Results]
Reference Files
references/pipeline-walkthrough.md— Complete end-to-end example with commandsreferences/stage-handoffs.md— JSONL format compatibility between stages
Stage Dependencies
| Stage | Tool | Input From | Output Format |
|---|---|---|---|
| 0. Retrieve + rerank | rank_llm | Dataset, request JSONL, or retrieval cache | Reranked JSONL / TREC-style run artifacts |
| 1. Generate | ragnarok | Dataset or request JSONL, often after rank_llm retrieval/rerank | Cited answers JSONL |
| 2. Create nuggets | nuggetizer | Stage 1 output (as pool) | Scored nuggets JSONL |
| 3. Assign nuggets | nuggetizer | Stage 1 output + Stage 2 output | Assigned nuggets JSONL |
| 4. Metrics | nuggetizer | Stage 3 output | Per-query metrics JSONL |
| 5. Judge | umbrela | Retrieval run file from rank_llm or another retriever + standard qrel | Modified qrels + nDCG@10 |
What ships with it
2 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 · 71 lines · 56 tokens per session scan A 8a362243e03e
castorini-pipeline is a skill published in the GitHub repository castorini/castorini-skills (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 976 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 2026-08-31.
Other skills, from other repositories
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.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
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"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.