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-cli-referencegit 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-cli-reference)<a href="https://agentmods.dev/skills/castorini/castorini-skills/castorini-cli-reference"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-cli-reference/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-cli-reference"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-cli-reference.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 | $0.00059 | $0.00783 |
| Opus 5.5 | $0.00024 | $0.00313 |
| Sonnet 5.5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
castorini-cli-reference 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 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.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Castorini CLI Reference
Quick reference for the shared CLI contract across the four Python Castorini repos: nuggetizer, ragnarok, rank_llm, and umbrela.
All four repos expose a repo-named binary (nuggetizer, ragnarok, rank-llm, umbrela) with converged introspection commands and the castorini.cli.v1 JSON envelope.
The flag matrix is closest across nuggetizer, ragnarok, and umbrela. rank_llm shares the introspection surface and envelope shape, but some execution flags and artifact naming are repo-specific.
When a task depends on the current contract shape, start with <repo> describe ..., <repo> schema ..., or <repo> doctor --output json before assuming a sibling repo matches remembered behavior.
Shared Command Families
Every repo exposes:
| Command | Purpose |
|---|---|
describe <cmd> |
Machine-readable contract: flags, defaults, enums, examples |
schema <name> |
JSON Schema for inputs, outputs, envelope |
doctor |
Environment and dependency preflight |
validate <target> |
Input/artifact validation without model execution |
prompt list|show|render |
Inspect and render prompt templates |
view <path> |
Inspect existing artifact files |
Plus repo-specific execution verbs:
- nuggetizer:
create,assign,metrics - ragnarok:
generate,validate,convert - rank_llm:
rerank,evaluate,analyze,retrieve-cache,serve - umbrela:
judge,evaluate
Reference Files
Read these on demand for detailed specifications:
references/envelope-schema.md— Fullcastorini.cli.v1envelope specificationreferences/shared-flags.md— Common flags and introspection commands across the shared Castorini CLIsreferences/artifact-shape.md— Artifact metadata shape and conventions
Gotchas
- Flag casing: All four repos use kebab-case for packaged CLI flags (
--input-file, not--input_file). Legacy compatibility scripts may still use snake_case internally. --outputvs--output-file:--outputcontrols format (text|json|jsonl);--output-filecontrols destination path. These are independent.- Write policies are mutually exclusive:
--resume,--overwrite, and--fail-if-existscannot be combined. --dry-runvs--validate-only:--dry-runresolves inputs and reports what would happen.--validate-onlychecks the declared contract (schemas, types) without resolving resources.- Exit code 7 means partial success — some records succeeded, others failed. Check
errorsarray in the JSON envelope. rank_llmcommand names differ: its primary execution verbs arererankandevaluate, notgenerateorjudge.- No automated contract tests yet verify sibling CLIs agree on the shared envelope. When in doubt, inspect the target repo directly with
<repo> schema <name>or<repo> describe <command>.
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.
- 2mo ago First seen · 55 lines · 59 tokens per session scan A 76bd53136930
castorini-cli-reference is a skill published in the GitHub repository castorini/castorini-skills (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 783 once invoked, about $0.0002 per session on Opus 5.5. 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.
castorini-cli-reference compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| castorini-cli-referencecastorini/castorini-skills | Skill | 2 | 7mo ago | Apache-2.0 | A | 59 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |