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-generator/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-generator)<a href="https://agentmods.dev/skills/jetbrains/mps/mps-aspect-generator"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-aspect-generator.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 5.1 | $0.00120 | $0.02715 |
| Opus 5 | $0.00060 | $0.01358 |
| Sonnet 5 | $0.00024 | $0.00543 |
| Haiku 4.5 | $0.00012 | $0.00271 |
Grade A, and why
mps-aspect-generator 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 7d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPS Generator Aspect
A generator transforms models written in the source language into models of one or more target languages (usually BaseLanguage or another DSL). It is a separate MPS module — a generator module — owned by the language and driven by templates: target-language code snippets annotated with macros.
Generator architecture (read first)
A generator translates from the problem domain (source language) toward the implementation domain, often as a cascade: each generator lowers the abstraction level by producing its target language, which becomes the next generator's input, until a base language (usually BaseLanguage) is reached and TextGen emits plain text.
A generator definition has a stable part and a variable part:
- the stable part does not change with the model being generated — engines, base classes, helpers. Provide it once in a runtime solution (an MPS
Solutionthe language declares as a runtime module — as MPS-authored source or a bundled JAR), not as a template. - the variable part is the templates + macros, which react to the input model and choose different output.
Idiomatic generators keep the stable part out of the templates and emit thin code that calls into the runtime solution. Before adding rules, decide how much is stable: see the architecture ladder in references/cookbook.md and the stable-vs-variable split + wiring in mps-aspect-accessories/references/runtime-solutions.md (worked example: the Kaja language + its JavaKaja runtime).
Critical Directives
- Edit the generator, not
source_gen/. If a bug appears in generated Java, the fix almost always belongs in a template, macro body, or concept behavior. Patch generated output only when explicitly told to. applicableConceptmust be a structure-model node ref (r:<modelUUID>(<lang>.structure)/<nodeId>), never thec:<langUUID>/<conceptId>form. Wrong form → silentUnresolved reference: c:.... Seereferences/rule-consequences.md.- A
TemplateDeclarationused as a reduction target requires at least oneTemplateFragmenton the produced subtree, or the rule fires and emits nothing. - Module dependencies vs. model used-languages are two distinct layers (see
references/module-structure.md). Adding a class to the wrong one yields "cannot resolve" in generated Java or unusable concepts in templates. - Macros attach via the
smodelAttributechild role, and co-located macros are chained in child order — order is semantics.$IF$before$LOOP$gates the whole loop in the outer context;$LOOP$before$IF$evaluates the condition per iteration. The$LOOP$+$COPY_SRC$pair is order-insensitive only because$COPY_SRC$is terminal — don't generalize. Seereferences/macro-catalog.md. - Reductions can self-loop when they produce their own concept — break out with
DismissTopMappingRule, a marker subconcept, or$COPY_SRC$. - Cross-rule/cross-template references go through mapping labels. Direct references survive only within a single fragment.
What ships with it
19 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/algorithm.md 4.2 KB
- references/calling-into-generator.md 811 B
- references/common-failures.md 3.8 KB
- references/concept-fqns.md 1.4 KB
- references/cookbook.md 11 KB
- references/generation-context.md 5.3 KB
- references/macro-catalog.md 16 KB
- references/macro-map-src.md 5.7 KB
- references/macro-reference.md 6.8 KB
- references/macros-rare.md 12 KB
- references/mapping-labels.md 5.0 KB
- references/mapping-scripts.md 2.2 KB
- references/module-structure.md 9.9 KB
- references/pattern-rules.md 2.4 KB
- references/query-bodies.md 3.0 KB
- references/rule-consequences.md 4.1 KB
- references/template-switches.md 5.6 KB
- references/utility-models.md 4.3 KB
- references/weaving-rules.md 3.2 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.
- 7d ago First seen · 91 lines · 120 tokens per session scan A 7568e6d17fbe
mps-aspect-generator is a skill published in the GitHub repository JetBrains/MPS (1,656 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 2,715 once invoked, about $0.0006 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.