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.
npx agentmods add instructions/jetbrains/mps/claude-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/claude-md)<a href="https://agentmods.dev/instructions/jetbrains/mps/claude-md"><img src="https://agentmods.dev/badge/instructions/jetbrains/mps/claude-md.svg" alt="Measured on agentmods" 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 | $0.02970 | $0.02970 |
| Opus 5 | $0.01485 | $0.01485 |
| Sonnet 5 | $0.00594 | $0.00594 |
| Haiku 4.5 | $0.00297 | $0.00297 |
Grade A, and why
MPS CLAUDE.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 3d 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.
This is a copy
98% identical to MPS AGENTS.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 181 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 typically 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.
Agents must adapt to the tools available in the current session. Use this file as the cross-environment entry point.
For detailed MPS node, model, language, generator, validation, and MCP workflows, load the mps-mcp-workflow skill. 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
If you are opening or reading .mps, .mpl, or other MPS XML files directly, you are way off track and must stop immediately.
MPS model files are binary-like serialized XML that cannot be safely understood or edited as plain text. Reading them gives you opaque node IDs and no semantic insight — you will misinterpret the content and likely corrupt the model if you try to edit it.
What to do instead:
- Use MPS MCP tools (
mps_mcp_*) to inspect, navigate, and edit MPS models. - If MPS MCP tools are not available in your session, ask the user to start MPS and enable the MPS MCP server before continuing with any MPS work.
- Do not attempt to parse, edit, or reason from raw
.mpsXML.
Project Nature: JVM + MPS
Treat this repository as having two kinds of source of truth:
- Plain Java/Kotlin and related project files, usually edited and validated through IntelliJ IDEA tooling.
- MPS models and language definitions, edited and validated through MPS-aware tooling.
Prefer the highest-level source of truth:
- If behavior is defined by an MPS language, model, or generator, prefer fixing the MPS artifact rather than only patching generated Java.
- If behavior is implemented in hand-written Java/Kotlin, use IDEA-oriented tools and workflows.
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.
- 3d ago First seen · 181 lines · 2,970 tokens per session scan A 156c32936e4b
MPS CLAUDE.md is an instructions file published in the GitHub repository JetBrains/MPS (1,657 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,970 tokens to every session, about $0.0149 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to MPS AGENTS.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
langium-ai CLAUDE.md
Instructions for eclipse-langium/langium-ai, covering claude.md, project overview, commands, build & test (all workspaces) and lint & format.
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目（模块集由 jdk 版本自动选择 —— 见下方说明）.
liteflow AGENTS.md
Instructions for dromara/liteflow, covering agents.md, commands, build, build with tests and build specific module.
onebase CLAUDE.md
Instructions for ivanarama/onebase, covering claude.md, сборка и запуск, cli + сервер (без cgo) — основной бинарь, gui с нативным окном (cgo + webview2 на windows) and тесты.
allo AGENTS.md
Instructions for cornell-zhang/allo, covering building, testing, code style and don'ts.
ainativelang AGENTS.md
Instructions for sbhooley/ainativelang, covering agents.md — ground truth for ai agents, for agents — install ainl (one step), what this repo is, repository layout and commands that work.