JetBrains MPS is a development environment for creating domain-specific languages, which are programming languages designed for a particular field or task. It provides editors with features such as completion, semantic checks, and type checking, and can generate code in languages including Java and XML.
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 agentmods add skills/jetbrains/mps/mps-aspect-behaviornpx skills add JetBrains/MPS --skill mps-aspect-behaviorgit clone --depth 1 https://github.com/JetBrains/MPSWrote 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/mps/mps-aspect-behavior)<a href="https://agentmods.dev/skills/jetbrains/mps/mps-aspect-behavior"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-aspect-behavior.svg" alt="Measured on agentmods" 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 | $0.00135 | $0.02439 |
| Opus 5 | $0.00068 | $0.01220 |
| Sonnet 5 | $0.00027 | $0.00488 |
| Haiku 4.5 | $0.00014 | $0.00244 |
Grade A, and why
mps-aspect-behavior 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 5d 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.
MPS Behavior Aspect
The behavior aspect attaches methods and a constructor to a concept, much like adding methods to a Java class. Bodies are written in BaseLanguage + smodel and are callable from any other aspect (editor, constraints, typesystem, generator, intentions, plugin) via node.methodName(...). Lives in <lang>/languageModels/behavior.mps, language jetbrains.mps.lang.behavior.
Critical Directives
- One
ConceptBehaviorroot per concept. Theconstructorchild is mandatory (an empty body is fine). - Constructors run before the node is attached to the model.
parent, ancestors, and all children/descendants evaluate tonull. Constructors can only set own property/reference defaults and add mandatory children — use aNodeFactory(actions aspect) for anything that needs the parent/model context. - Quotations (
<C()>) bypass behavior constructors. Usenew node<C>()oradd new initialized Cwhen you need the constructor to fire. - Constructors are not inherited — each concept has at most one, and they do not chain (no
super()). MPS runs each ancestor's constructor in ancestor-first order independently. - An overriding method must match the signature of the supertype/interface method exactly. When implementing an interface method (e.g.
ScopeProvider.getScope), setoverriddenMethodon the new method to the interface declaration — MPS uses it for dispatch and signature validation. - Behavior calls on a
nullnode do not NPE — MPS returnsnullfor reference/String returns and the default for primitives. Still handle thenullreturn for reference types. - Hoist shared methods to an abstract super-concept rather than duplicating per-sub-concept
ConceptBehaviorroots — virtual dispatch covers all non-abstract sub-concepts. (Seereferences/inheritance-and-dispatch.md.) - Methods are non-virtual by default: all modifier booleans (
isVirtual,isAbstract,isStatic,isFinal) default tofalse. Onlyvirtualmethods can be overridden; mark a methodvirtualup front if sub-concepts may ever need to specialise it. - When the same piece of node-handling logic repeats across several places or several aspects of one concept (editor, constraints, typesystem, generator, intentions, textgen), extract it into a behavior method and call it everywhere via
node.m(...)— this de-duplication is the behavior aspect's primary purpose. Pick the modifier with the table below. - Edit behavior models through MPS MCP tools (
mps_mcp_insert_root_node_from_json,mps_mcp_update_node,mps_mcp_parse_java_and_insert). Do not hand-edit.mpsfiles. - For MPS-typed return types (
sequence<node<X>>,list<node<X>>),mps_mcp_parse_java_and_insertproduces JavaList<SNode>— replacereturnTypeafterwards with the correct MPS blueprint (seemps-model-manipulation/references/variable-declarations.md). - After edits run
mps_mcp_check_root_node_problemsand rebuild the language.
What ships with it
8 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.
- references/calling-from-other-aspects.md 1.8 KB
- references/common-failures.md 2.0 KB
- references/constructors.md 7.7 KB
- references/inheritance-and-dispatch.md 2.8 KB
- references/json-blueprints.md 2.6 KB
- references/lang-core-behavior-overrides.md 1007 B
- references/local-and-super-calls.md 5.6 KB
- references/method-declarations.md 8.5 KB
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.
- 5d ago First seen · 71 lines · 135 tokens per session scan A 652db9881396
mps-aspect-behavior is a skill published in the GitHub repository JetBrains/MPS (1,658 stars, last pushed today), licensed Apache-2.0. It adds 135 tokens to every session and 2,439 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
langium
A comprehensive skill to understanding how Langium-based projects work — from grammar definition through code generation, runtime parsing, linking, validation, and LSP integration.
lai-gen-evals
Expand and refine the evaluation suite for a Langium DSL project. Generates comprehensive eval files that cover syntactic correctness, semantic validity, user intent matching, edge cases, and language understanding.
lai-gen-mcp
Generate a Model Context Protocol (MCP) server that exposes a Langium DSL's parser and validator as an MCP tool, allowing any MCP-compatible client to validate DSL code and receive diagnostics.
lai
Guide for using the langium-ai (LAI) CLI to generate language descriptors, synthesize system prompts, run evaluations, and iteratively refine AI-powered tooling in Langium projects. Use when working with lai commands, descriptors, or evaluation files.
lai-gen-descriptor
Generate or refine a language descriptor for a Langium DSL project. Bootstraps a new descriptor via lai gen descriptor if none exists, then guides refinement of paths, services, examples, documentation, and structure.
lai-gen-language-skill
Skill for generating a skill for understanding a specific Langium-based DSL. Used in cooperation with the lai & langium skills for understanding.