MPS: Skill for Claude Code

.agents/skills/mps-language-inheritance/SKILL.md

mps-language-inheritance is a skill for Claude Code, Codex from JetBrains/MPS. It costs 56 tokens per session (814 once invoked), scanned A, original, Apache-2.0.

A guide for tracing inheritance in JetBrains MPS, a language-workbench tool where developers define programming languages. It covers relationships between languages and between the concepts those languages define.

In plain words
What is it for?
Use it to trace language extensions, find places where a language can be extended, inspect parent concepts and interfaces, and check whether one concept can be used where another is expected.
Why use it?
It helps you find where a language or concept gets its structure, behavior, or allowed relationships. It also avoids manually walking long inheritance chains or checking assignability by hand.

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 · 1,656 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-language-inheritance/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-language-inheritance

README.md
[![agentmods](https://agentmods.dev/badge/skills/jetbrains/mps/mps-language-inheritance.svg)](https://agentmods.dev/skills/jetbrains/mps/mps-language-inheritance)
Your own site
<a href="https://agentmods.dev/skills/jetbrains/mps/mps-language-inheritance"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-language-inheritance.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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.
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 $0.00056 $0.00814
Opus 5 $0.00028 $0.00407
Sonnet 5 $0.00011 $0.00163
Haiku 4.5 $0.00006 $0.00081

Measured 7d ago against content hash 9dd00ac6fe5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mps-language-inheritance 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.

.agents/skills/mps-language-inheritance/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MPS Language and Concept Inheritance

Two layers of inheritance matter in MPS: module-level (one language extends another) and concept-level (concepts inherit superconcepts and implement interface concepts).

Critical Directives

  • Concept-level inheritance is realized through module-level extension — different languageReference on a concept and its superConcept indicates a cross-language specialization, which usually requires the consumer's language to extend the parent.
  • GET_ALL_SUPERCONCEPTS gives the full transitive closure in a single call — prefer it over recursive walking of superConcept / superInterfaces.
  • IS_SUBCONCEPT_OF is the fastest way to verify a single assignability question; do not enumerate GET_SUB_CONCEPTS and search by hand.

Module-Level Inheritance (Language Extension)

One language can inherit the structure and functionality of another via an "extends" relationship.

  1. Tool: mps_mcp_get_project_structure (with includeDependencies: true).
  2. Workflow: check the extendedLanguages field in the response for the target language. This lists direct parent languages.
  3. Hierarchy tracing: recursively call this tool for each parent to build the full inheritance tree.

Concept-Level Inheritance

Upward Hierarchy (Ancestors)

  • Direct ancestors: use mps_mcp_get_concept_details. The response includes:
    • superConcept: immediate parent concept.
    • superInterfaces: immediate implemented interface concepts.
    • superConceptContainingProject and superInterfaceDetails[*].containingProject when an ancestor comes from another open MPS project and is read-only from the selected project.
  • Full closure: use mps_mcp_query_structure with GET_ALL_SUPERCONCEPTS to get the complete chain of ancestors and interfaces in one call.

Downward Hierarchy (Descendants)

  • Specializations: use mps_mcp_query_structure with GET_SUB_CONCEPTS to find all concepts (direct and indirect) inheriting from a base.
  • Implementations: use GET_ASSIGNABLE_CONCEPTS to retrieve only non-abstract subconcepts that can be instantiated.

Read the full file on GitHub · 56 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. 7d ago First seen · 56 lines · 56 tokens per session scan A 9dd00ac6fe5f

Subscribe to this mod's changes

mps-language-inheritance is a skill published in the GitHub repository JetBrains/MPS (1,656 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 814 once invoked, about $0.0003 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.