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-build-language/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-build-language)<a href="https://agentmods.dev/skills/jetbrains/mps/mps-build-language"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-build-language/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.
<a href="https://agentmods.dev/skills/jetbrains/mps/mps-build-language"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/mps-build-language.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00171 | $0.02957 |
| Opus 5.5 | $0.00068 | $0.01183 |
| Sonnet 5.5 | $0.00034 | $0.00591 |
| Haiku 4.5 | $0.00017 | $0.00296 |
Grade A, and why
mps-build-language 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPS Build Language
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.
The MPS Build Language is a declarative DSL (a stack of MPS languages on top of Ant) that generates an Apache Ant build.xml file. It is used to package MPS-language plugins, build standalone IDE/RCP distributions, package plain Java modules, and run MPS tests or generation-diff tests. Build scripts are root nodes of concept BuildProject inside a regular solution module; pressing Make on that solution runs a generator that writes build.xml to disk.
Critical Directives
- The generator writes
build.xml— it does not invoke Ant. To produce artifacts you must runantseparately (from MPS right-click → Run, or from the command line in the generated folder). - Build scripts are MPS nodes. Edit them via projectional editing or
mps_mcp_*JSON tools. Never hand-edit the.mpsfile as if it were Ant XML. - Declaring a module in
BuildProject.partsdoes not cause it to be built. Only items referenced from thelayoutend up in the output.partsis declaration;layoutis packaging. - Build scripts compile languages but do not regenerate them. Generate languages to Java first (or enable the
mpsbuild plugin's full-make task) before running Ant. - Always import
jetbrains.mps.ide.build(422c2909-59d6-41a9-b318-40e6256b250f) on the build solution — it is the catalog of well-known externals (IDEA,mps,mpsStandalone, JDK, MPS modules). - After every change to a module's
.mpl/.msd, re-run the Load required information from file intention on the matchingBuildMps_*node. Build-script module dependencies must match the actual.mpldeclarations or the chunk generator throws "class not found". - A
BuildMps_Groupmust contain the transitive closure of language dependencies. Missing members appear as red squiggles at generation time. - Always set
internalBaseDirectory— every relative path is resolved against it.
What ships with it
16 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/ant-targets.md 1.0 KB
- references/buildproject-skeleton.md 2.4 KB
- references/common-failures.md 1.5 KB
- references/concept-catalog.md 5.6 KB
- references/dependencies.md 1.4 KB
- references/disambiguation.md 2.6 KB
- references/groups.md 1018 B
- references/idea-plugins.md 2.9 KB
- references/java-parts.md 3.6 KB
- references/layouts.md 3.0 KB
- references/mps-modules.md 5.0 KB
- references/mps-settings.md 904 B
- references/plugins-and-macros.md 3.3 KB
- references/solution-setup.md 2.7 KB
- references/standalone-ide.md 2.1 KB
- references/tests-and-workflow.md 3.6 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.
- 2d ago Changed · -3 tokens per session a577dc822664
- 1mo ago Changed · +4 lines 34580de2b913
- 2mo ago First seen · 76 lines · 174 tokens per session scan A bcfbdc8cdbb7
mps-build-language is a skill published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 171 tokens to every session and 2,957 once invoked, about $0.0007 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.
mps-build-language compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mps-build-languageJetBrains/MPS | Skill | 1.7k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| langiumeclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 33 | Claude Code |
| lai-gen-evalseclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 42 | Claude Code |
| laieclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 52 | Claude Code |
| lai-gen-descriptoreclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 49 | Claude Code |
| lai-gen-mcpeclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 43 | Claude Code |
| lai-gen-language-skilleclipse-langium/langium-ai | Skill | 31 | 4d ago | MIT | A | 33 | Claude Code |