What is castorini-skills CLAUDE.md?

A set of shared instructions for coding agents working across Castorini research repositories. It covers repository setup, command-line references, pipelines, releases, and local HTTP serving.

Bootstrapping one or more repositories, running cross-repository pipelines, downloading Anserini, serving results locally, and publishing packages to PyPI or TestPyPI.

It gives agents consistent project conventions and points them to each repository’s own build, test, and lint instructions. This reduces repeated setup work and avoids conflicting guidance.

How castorini/castorini-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to castorini/castorini-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/castorini/castorini-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/castorini/castorini-skills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/castorini/castorini-skills/claude-md/github.svg)](https://agentmods.dev/instructions/castorini/castorini-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/castorini/castorini-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/castorini/castorini-skills/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/castorini/castorini-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/castorini/castorini-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 393 This file is loaded in full into every session.

When invoked 393 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00393	$0.00393
Opus 5.5	$0.00157	$0.00157
Sonnet 5.5	$0.00079	$0.00079
Haiku 4.5	$0.00039	$0.00039

Measured 2mo ago against content hash 6ba32edefd22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

castorini-skills CLAUDE.md 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 2mo 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.

castorini-serve/ # local HTTP serving and curl pipeline orchestration

CLAUDE.md · 32 lines

What it actually says

castorini-skills

This repo contains shared agent skills for cross-repo workflows in the Castorini research group.

Structure

skills/
  anserini-fatjar/          # download and run the latest Anserini fatjar quickly
  castorini-cli-reference/   # shared CLI contract docs
  castorini-onboard/         # single-repo or multi-repo clone/bootstrap and environment setup
  castorini-pipeline/        # cross-repo pipeline orchestration
  castorini-release/         # PyPI/TestPyPI publish workflow
  castorini-serve/           # local HTTP serving and curl pipeline orchestration

Conventions

Each skill has a SKILL.md with YAML frontmatter (name, description).
The description field is a trigger: write "Use when..." not "This skill does...".
Reference material goes in references/ so agents can load it on demand instead of inlining everything into SKILL.md.
Runnable helpers go in scripts/.
Skills describe what to check and what flags exist. They do not railroad agents into rigid step-by-step flows.
Skills reference per-repo instruction files such as CLAUDE.md or AGENTS.md for build, test, and lint instructions. They do not duplicate them.

Target repos

nuggetizer — nugget creation, assignment, and evaluation
ragnarok — RAG answer generation and TREC evaluation
rank_llm — retrieval and LLM reranking workflows
umbrela — LLM-based relevance assessment (0–3 labels)

Changes

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.

2mo ago First seen · 32 lines · 393 tokens per session scan A 6ba32edefd22

Subscribe to this mod's changes

castorini-skills CLAUDE.md is an instructions file published in the GitHub repository castorini/castorini-skills (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 393 tokens to every session, about $0.0016 per session on Opus 5.5. 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.

Research

castorini-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
castorini-skills CLAUDE.mdcastorini/castorini-skills	Instructions file	2	7mo ago	Apache-2.0	A	393	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

castorini-skills: Instructions file for Claude Code