agentmods.dev

mps-model-manipulation

mps-model-manipulation is a skill for Claude Code, Codex from JetBrains/MPS. It costs 262 tokens per session (3,330 once invoked), scanned A, original, Apache-2.0.

A guide for writing MPS BaseLanguage code inside models, including behavior methods, rules, generator queries, and related callbacks.

In plain words
What is it for?
It helps create or edit MPS model code, query nodes and usages across project scopes, and avoid errors such as using ordinary equality instead of MPS node equality.
Why use it?
It explains the special MPS syntax and node-building approach needed when BaseLanguage is combined with smodel, collections, and closures extensions.

Skill for Claude CodeCodex

not rated 1.7k +2 today A scan 262 tokens original Apache-2.0
View the source file JetBrains/MPS jetbrains.com
About the project

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.

JetBrains/MPS · 1,658 stars · on GitHub · jetbrains.com

Install

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.

agentmods
npx agentmods add skills/jetbrains/mps/mps-model-manipulation
Any agent
npx skills add JetBrains/MPS --skill mps-model-manipulation
Clone the repo
git clone --depth 1 https://github.com/JetBrains/MPS

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mps-model-manipulation

README.md
[![agentmods](https://agentmods.dev/badge/skills/jetbrains/mps/mps-model-manipulation.svg)](https://agentmods.dev/skills/jetbrains/mps/mps-model-manipulation)
Your own site
<a href="https://agentmods.dev/skills/jetbrains/mps/mps-model-manipulation"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-model-manipulation.svg" alt="Measured on agentmods" height="20"></a>
Per session 262 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00262 $0.03330
Opus 5 $0.00131 $0.01665
Sonnet 5 $0.00052 $0.00666
Haiku 4.5 $0.00026 $0.00333

Measured 6d ago against content hash 42aef704213e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mps-model-manipulation 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 6d 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.

.agents/skills/mps-model-manipulation/SKILL.md · 71 lines

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.

Writing MPS BaseLanguage with smodel / collections / closures

Use this skill when authoring code inside an MPS model where BaseLanguage is mixed with the smodel, collections, and closures extensions: behavior methods, checking/typesystem/dataflow rules, generator query functions, intentions, constraints, scope/canBe callbacks. The mps_mcp_parse_java_and_insert parser understands only plain Java, so most non-trivial code requires hand-built node blueprints — this skill is the catalog.

To enumerate nodes/instances/usages across a scope (a whole project, module, model, or repository) rather than navigating from one root, add the jetbrains.mps.lang.smodel.query language — it supplies #instances / #usages / #nodes / #references / #models / #modules and a with (<scope>) { … } wrapper, the same queries the MPS Console runs. Its results compose with the smodel/collections/closures operations catalogued here. See the mps-console skill.

Critical Directives

  • Node equality uses :eq: and :ne:, never == or .equals(). Use NPEEqualsExpression / NPENotEqualsExpression. See references/node-equality.md.
  • Every InferredClosureParameterDeclaration needs a type child, even though MPS infers the type. Use jetbrains.mps.baseLanguage.structure.UndefinedType as placeholder. Omitting it cascades into misleading "different parameter numbers" / "out of search scope" / "operation is not applicable to null" errors. See references/closures-catalog.md.
  • The Java parser cannot produce smodel/collection types in method return types, cannot parse :Concept casts, .link accesses, .behaviorMethod() calls, or MetaAdapterFactory.getContainmentLink inline. Use LINKS.xxx/CONCEPTS.xxx constants and replace types post-parse. See references/java-parser-capabilities.md.
  • Mutations need command { … }, reads from non-UI code need read action { … }. There is no separate "write action". Behavior methods and rule bodies already hold the right lock. See references/concurrent-access.md.
  • Pick the right cardinality: SLinkAccess for 0..1 / 1; SLinkListAccess for 0..n / 1..n. One pair serves both reference links and containment children (there is no SChildAccess/SChildListAccess). Wrong choice triggers "out of search scope" / "access to link X is not expected here". See references/dot-expression-basics.md.
  • foreach has two concepts: collections ForEachStatement for sequence/list/set, BaseLanguage ForeachStatement for Java arrays/iterables. Wrong choice → type error. See references/foreach-statements.md.
  • Used-language imports: NF_* operations require jetbrains.mps.lang.actions in the model's used languages; without it, add new initialized(...) etc. fail. See references/property-and-mutation-ops.md and references/openapi-and-dependencies.md.
  • Never recommend deprecated operations: .role (use .containingLink), .linkDeclaration (use .link), .role on SReference (use .link.name), .concept Node_GetConceptOperation (use node.concept via typesystem).

Read the full file on GitHub · 71 lines

Files

What ships with it

18 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.

Changes

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.

  1. 6d ago First seen · 71 lines · 262 tokens per session scan A 42aef704213e

Subscribe to this mod's changes

mps-model-manipulation is a skill published in the GitHub repository JetBrains/MPS (1,658 stars, last pushed today), licensed Apache-2.0. It adds 262 tokens to every session and 3,330 once invoked, about $0.0013 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.

domain-specific-languagedsl
Related

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.

eclipse-langium/langium-ai · 33 tokens

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.

eclipse-langium/langium-ai · 42 tokens

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.

eclipse-langium/langium-ai · 43 tokens

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.

eclipse-langium/langium-ai · 52 tokens

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.

eclipse-langium/langium-ai · 49 tokens

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.

eclipse-langium/langium-ai · 33 tokens