MPS: Skill for Claude Code

.agents/skills/mps-baselanguage/SKILL.md

mps-baselanguage is a skill for Claude Code, Codex from JetBrains/MPS. It costs 94 tokens per session (2,372 once invoked), scanned A, original, Apache-2.0.

A guide for authoring Java-like code in JetBrains MPS’s BaseLanguage, where Java code is edited as a structured model rather than plain text. It explains how to create and validate these model nodes.

In plain words
What is it for?
Use it to write classes, methods, fields, expressions, statements, constructors, and persistent references through the Java parser or structured JSON definitions.
Why use it?
It reduces errors caused by using the wrong MPS node type, reference, equality operation, or constructor structure.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is JetBrains/MPS's own configuration. It tells Claude Code and Codex how to work on MPS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MPS configures →

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 · 1,666 stars · on GitHub · jetbrains.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JetBrains/MPS/master/.agents/skills/mps-baselanguage/SKILL.md
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-baselanguage

README.md
[![agentmods](https://agentmods.dev/badge/skills/jetbrains/mps/mps-baselanguage/github.svg)](https://agentmods.dev/skills/jetbrains/mps/mps-baselanguage)
Your own site
<a href="https://agentmods.dev/skills/jetbrains/mps/mps-baselanguage"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-baselanguage/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.

agentmods 80×15 button for mps-baselanguage

Your own site · 80×15
<a href="https://agentmods.dev/skills/jetbrains/mps/mps-baselanguage"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-baselanguage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00094 $0.02372
Opus 5.5 $0.00038 $0.00949
Sonnet 5.5 $0.00019 $0.00474
Haiku 4.5 $0.00009 $0.00237

Measured 8d ago against content hash 0cd050c8195c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mps-baselanguage 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.

.agents/skills/mps-baselanguage/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MPS BaseLanguage (Java) Authoring

Loading companion skills

Companion names in this skill are lazy dependencies: load only those relevant to the current task. If this skill came from an MCP server, use the host's skill loader to resolve the companion's unique discovered entry URI on the same host-assigned originating server. If the host has no server-backed skill loader, stop and report that limitation; do not silently fall back to a filesystem copy. If this skill came from a filesystem catalog, load the named sibling from that same catalog at <skills-root>/<skill-name>/SKILL.md, even if remote skill loaders are also available. Do not invent a tool name or server endpoint.

jetbrains.mps.baseLanguage is MPS's Java-equivalent language. You edit it as an AST, not as text. Two authoring paths exist: the Java parser (mps_mcp_parse_java_and_insert) for plain Java, and JSON AST blueprints (mps_mcp_insert_root_node_from_json / mps_mcp_update_root_node_from_json / mps_mcp_update_node) for everything else — especially code that uses BaseLanguage extensions (jetbrains.mps.lang.smodel, jetbrains.mps.baseLanguage.closures, jetbrains.mps.baseLanguage.collections) or needs stable persistent member references.

Critical Directives

  • Node equality: always use :eq: and :ne: (concepts NPEEqualsExpression / NPENotEqualsExpression). Never == or .equals() between SNode references.
  • Constructor return type: ConstructorDeclaration.returnType MUST be a VoidType node. Leaving it empty fails validation.
  • ClassCreator wiring: ClassCreator.baseMethodDeclaration points at the constructor declaration, not the class. InstanceMethodCallOperation.baseMethodDeclaration points at the method declaration.
  • new … is a GenericNewExpression plus a creator: the GenericNewExpression is the Expression; its creator child is ClassCreator, ArrayCreator, ArrayCreatorWithInitializer, AnonymousClassCreator, a collections creator, or smodel SNodeCreator (new node<C>()). Creators are AbstractCreators, not Expressions, so none of them can stand alone in ReturnStatement.expression, an argument, or an initializer.
  • Inherited methods: use the declaring class ref for baseMethodDeclaration, not the subclass that calls the method. E.g. addActionListener is declared on AbstractButton, so use the AbstractButton class ref.
  • Expressions in statement lists: any Expression must be wrapped in ExpressionStatement to be valid inside a StatementList.
  • Variable declarations: in method bodies wrap LocalVariableDeclaration in LocalVariableDeclarationStatement. In ForStatement.variable use LocalVariableDeclaration directly, no wrapper.
  • Prefer primitives: use string (StringType) over String (ClassifierType) where possible; same for int, boolean, etc.
  • Compatibility: BaseLanguage core is Java 7 (including generics). When building AST directly (JSON blueprints), there is no lambda/record syntax — use the jetbrains.mps.baseLanguage.closures extension for closures (blueprints in the mps-collections-and-closures skill). The Java parser (mps_mcp_parse_java_and_insert) additionally accepts the Java 8+ syntax MPS recognizes — most notably lambdas, which it maps to closures ClosureLiterals (auto-imported when postProcess.importUsedLanguages is on); a lambda only type-checks against a matching functional-type target. Constructs the parser does not recognize (e.g. records) still fail to parse. See references/parse-java-tips.md.
  • Surgical edits: when a single child changes prefer mps_mcp_update_node over rewriting the whole root — full-root rewrites churn persistent IDs and break incoming refs.
  • Ask the running typesystem, not its rules: use mps_mcp_query_types OPERATION_TYPE for expressions such as int + long or String + int, IS_SUBTYPE for assignability, and COERCE to ClassifierType before reading classifier.targetReference for classifier members. See mps-mcp-workflow/references/analysis-tools/type-queries.md.

Read the full file on GitHub · 69 lines

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. 8d ago Changed 0cd050c8195c
  2. 11d ago Changed bc8bcd9aec75
  3. 29d ago Changed · +2 lines 1194923e0b2a
  4. 1mo ago Changed · +5 lines 11ccc47931ab
  5. 2mo ago First seen · 62 lines · 94 tokens per session scan A 31274d492f50

Subscribe to this mod's changes

mps-baselanguage is a skill published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 2,372 once invoked, about $0.0004 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.

Related

mps-baselanguage compared with skills from other repositories

mps-baselanguage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mps-baselanguageJetBrains/MPSSkill1.7kyesterdayApache-2.0A94Claude Code, Codex
langiumeclipse-langium/langium-aiSkill314d agoMITA33Claude Code
lai-gen-descriptoreclipse-langium/langium-aiSkill314d agoMITA49Claude Code
lai-gen-mcpeclipse-langium/langium-aiSkill314d agoMITA43Claude Code
lai-gen-language-skilleclipse-langium/langium-aiSkill314d agoMITA33Claude Code
java-affected-testsopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A120Claude Code
azure-security-keyvault-secrets-javamicrosoft/skillsSkill3.2kyesterdayMITA40Claude Code