Koog is a Kotlin and Java framework for building AI agents that use tools, interact with people, and run multi-step workflows. JVM and Kotlin developers use it to deploy agents across platforms such as JVM, Android, iOS, JavaScript, and WebAssembly, with features for persistence, fault recovery, model switching, and monitoring. The catalogue entries provide agents, skills, and instructions for building with Koog.
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 JetBrains/koog --skill arithmetic-evaluatorgit clone --depth 1 https://github.com/JetBrains/koogWrote 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/jetbrains/koog/arithmetic-evaluator)<a href="https://agentmods.dev/skills/jetbrains/koog/arithmetic-evaluator"><img src="https://agentmods.dev/badge/skills/jetbrains/koog/arithmetic-evaluator/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/jetbrains/koog/arithmetic-evaluator"><img src="https://agentmods.dev/badge/skills/jetbrains/koog/arithmetic-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00129 |
| Opus 5.5 | $0.00016 | $0.00052 |
| Sonnet 5.5 | $0.00008 | $0.00026 |
| Haiku 4.5 | $0.00004 | $0.00013 |
Grade A, and why
arithmetic-evaluator 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 1mo 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.
What it actually says
Evaluate the arithmetic expression the user provides.
- Extract the arithmetic expression from the user request.
- If the expression is missing or ambiguous, ask for a clear arithmetic expression.
- Evaluate it by passing the expression to
scripts/evaluate_arithmetic_exp.py - Return the computed result clearly and concisely.
If script execution fails, explain that clearly and ask the user to provide a valid arithmetic expression.
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.
- 1mo ago First seen · 13 lines · 39 tokens per session scan A b629fbec4ded
arithmetic-evaluator is a skill published in the GitHub repository JetBrains/koog (4,622 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 129 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 2026-08-30.
Other skills, from other repositories
papyrus-writing
Base skill for the Papyrus writing assistant — conduct, paper-quality principles and LaTeX house style every Papyrus edit builds on. Load first when working on a .tex paper in Papyrus, then the task skill (papyrus-latex-comments, -suggestions, -make-fluent or -diagnose-compilation).
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
academic-literature-search
A multi-database search tool for academic papers and other scholarly publications. It searches sources such as Semantic Scholar, Crossref, arXiv, and PubMed, which cover research across fields including computing, physics, and medicine.
research-scout
Mines recent papers, blogs, and newsletters for methods worth stealing, with graded evidence. Use when finding recent papers or techniques for RAG, evals, or agents.