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.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/instructions/jetbrains/mps/agents-md)<a href="https://agentmods.dev/instructions/jetbrains/mps/agents-md"><img src="https://agentmods.dev/badge/instructions/jetbrains/mps/agents-md/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/instructions/jetbrains/mps/agents-md"><img src="https://agentmods.dev/badge/instructions/jetbrains/mps/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01966 | $0.01966 |
| Opus 5.5 | $0.00786 | $0.00786 |
| Sonnet 5.5 | $0.00393 | $0.00393 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
MPS AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- MPS CLAUDE.md — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guide for This Project
This project is a mixed JetBrains MPS + plain Java/Kotlin codebase. Developers use two environments against the same checkout:
- IntelliJ IDEA for editing, debugging, testing, and inspecting Java/Kotlin code, including code generated by MPS.
- JetBrains MPS for editing languages, models, generators, and other MPS artifacts.
Use IDEA tools for JVM work and the full MPS MCP toolset for model work. Use this file as the cross-environment entry point.
For any MPS work, load the mps-mcp-workflow skill; it holds the MPS critical directives, project resolution, validation, and the index of companion skills. If your agent runtime does not explicitly confirm that project skills are auto-loaded, read .agents/skills/mps-mcp-workflow/SKILL.md before changing MPS artifacts.
⚠️ WARNING: Never Read Raw MPS Model Files
Do not open, parse, or edit .mps, .mpl, or other MPS XML files as text: the serialized format is opaque, gives no semantic insight, and hand-edits corrupt models. Use the MPS MCP tools (mps_mcp_*) instead. If the MPS MCP server is not connected, ask the user to start MPS and enable it; a connected server whose tools were filtered or deferred is not this case — restore the full toolset as described below.
⚠️ Keep the Full MPS MCP Toolset
The mps_mcp_* tools are how MPS code is read and edited, not an optional add-on the way MCP tools are for plain-text code. Which of them a session will need cannot be guessed from the opening request — inspection, validation, generation, and editing tools get pulled in as the work unfolds — so a relevance filter that keeps only an opening subset will strand the session.
- Do not reduce, defer, hide, or capability-filter the MPS MCP catalog. Keep every
mps_mcp_*tool available for the whole session, including tools that do not look relevant yet. Pruning unrelated servers (IDEA, YouTrack, and the like) is fine; this rule is only about the MPS MCP server. - If the host has already filtered that server (Junie:
[partially available],[installed, but unavailable], or listed under servers that can be enabled), restore the entire server before any MPS work. In Junie, callenable_mcpon the MPS MCP server — the one that exposesmps_mcp_*, or, if it was fully filtered, the server named likemps-mcprather than the IDEA or YouTrack server. If that call is not available, ask the user to enable the full server. Do not guess among unrelated servers. - A filtered tool is not unavailable. Do not continue on a reduced subset, and do not fall back to file tools or raw
.mpsXML in its place. Only when the server is not connected at all, ask the user to start MPS and enable it.
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 · -70 lines · -384 tokens per session 59f54904ddb6
- 1mo ago Changed · +229 tokens per session 6780208c38e7
- 1mo ago Changed · -32 lines · -777 tokens per session a1acf0ae87f0
- 2mo ago First seen · 181 lines · 2,898 tokens per session scan A 6f838ad9948f
MPS AGENTS.md is an instructions file published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,966 tokens to every session, about $0.0079 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 AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| MPS AGENTS.mdJetBrains/MPS | Instructions file | 1.7k | yesterday | Apache-2.0 | A | 1,966 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |