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.
Borrowing it
Nothing to install: this file belongs to JetBrains/MPS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JetBrains/MPS/master/.agents/skills/mps-aspect-structure-concepts/SKILL.mdgit 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-structure-concepts)<a href="https://agentmods.dev/skills/jetbrains/mps/mps-aspect-structure-concepts"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-aspect-structure-concepts.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.01454 |
| Opus 5 | $0.00044 | $0.00727 |
| Sonnet 5 | $0.00017 | $0.00291 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
mps-aspect-structure-concepts 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPS Structure Aspect — Concepts
Concepts (ConceptDeclaration), interface concepts (InterfaceConceptDeclaration), enumerations (EnumerationDeclaration), and constrained data types (ConstrainedDataTypeDeclaration) are root nodes in a language's structure model. They use the language jetbrains.mps.lang.structure.
Critical Directives
- Implement
INamedConceptinstead of declaringnamedirectly. Anameproperty declared directly on a concept is an antipattern in MPS — implementjetbrains.mps.lang.core.structure.INamedConceptinstead. - Smart reference check (CRITICAL): before setting a
conceptAlias, determine whether the concept is an "Implicit Smart Reference". If it has exactly one mandatory reference and no properties or children of its own, do NOT set aconceptAlias— the concept should be transparent in the editor and completion menu so the user types the target's name directly. Examples: variable references, method calls, routine calls. - Leave alias empty on transparent collections too (e.g.
StatementList). - Set alias on concepts that can be root — that's how the user reaches them through the new-root menu.
- Always rebuild the language with
mps_mcp_alter_nodes MAKEandrebuild="true"after structural changes, so the new concepts are discoverable by runtime tools.
Prerequisites
- Requires the target language and its
structuremodel. - Uses the
jetbrains.mps.lang.structurelanguage. - Concepts, interface concepts, and enums are root nodes in the
structuremodel.
Workflow
- Locate language: use
mps_mcp_get_project_structureto find the language and itsstructuremodel. - Module creation: if needed, create the module via
mps_mcp_create_moduleusing an absolute path. - Define elements:
- ConceptDeclaration: core entities.
- InterfaceConceptDeclaration: orthogonal functionality.
- EnumerationDeclaration: fixed values.
- ConstrainedDataTypeDeclaration: regex-restricted properties.
- Attributes (annotations): concepts extending
NodeAttribute/PropertyAttribute/ChildAttribute/LinkAttributethat graft extra children/data onto other concepts without editing them — see Attributes section below.
- Inheritance & interfaces:
- Use inheritance and abstract concepts for shared logic.
- Implement
jetbrains.mps.lang.core.structure.INamedConceptif the concept needs anameproperty.
- Smart reference assessment: see directives above.
- Set alias on concepts that can be root: helps the user instantiate the concept through a menu.
- Leave alias empty on smart references and transparent collections: e.g.
StatementList. - Property definition:
- For enum properties: create the
EnumerationDeclarationfirst, then set the propertydataTypeto reference it.
- For enum properties: create the
- Proper cardinality: make sure intended child collections have the cardinality of
0..nor1..n. - Bulk operations: use
mps_mcp_alter_structurefor creating multiple concepts or enums efficiently.- Local references within the same JSON blueprint can use names for resolution.
- Reload runtime: always rebuild the language (via
mps_mcp_alter_nodeswithMAKEandrebuild="true") after structural changes to make concepts discoverable.
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.
- 8d ago First seen · 67 lines · 87 tokens per session scan A 7e4da8bb554d
mps-aspect-structure-concepts is a skill published in the GitHub repository JetBrains/MPS (1,656 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 1,454 once invoked, about $0.0004 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-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-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-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.
triton-syntax
A guide to Triton, a Python-like language for writing GPU programs in blocks of data. It explains its program model, data types, masking, and compiler-managed optimizations.
triton-ascend
A guide to writing Triton kernels for Ascend NPUs. Triton is a Python-based language for describing parallel operations that run in blocks across the device.