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/skill-optimization-study/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/skill-optimization-study)<a href="https://agentmods.dev/skills/jetbrains/mps/skill-optimization-study"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/skill-optimization-study/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/skill-optimization-study"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/skill-optimization-study.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 | $0.00093 | $0.01400 |
| Opus 5.5 | $0.00037 | $0.00560 |
| Sonnet 5.5 | $0.00019 | $0.00280 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
skill-optimization-study scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill optimisation study (MPS MCP)
A repeatable procedure for finding where agents waste turns and tokens when driving MPS through
mps_mcp_*, and for choosing the cheapest fix. The study folder is the home of the scripts,
scenarios, fixtures and reports. This file is the observer's entry: roles, the gate questions,
then the runbook. It is not a second copy of the study, and it does not absorb the scripts if
that folder is removed.
The same file is copied to .claude/skills/skill-optimization-study/SKILL.md. Keep the two
copies identical. Do not replace either with a symlink.
The 2026-09 documents under plugins/mcp-tools/docs/ are product history, not this procedure.
Conventions used below
Agent shells reset the working directory per call, so every command uses absolute paths through two variables — set them at the start of each Bash call (or export them in a wrapper script):
STUDY=<checkout>/plugins/mcp-tools/study
RUNS=$HOME/MPSProjects/mcp-study/runs
$RUNS/inventory.json is a load-bearing name: run_worker.sh records its sha in every run's meta.
Scratch projects go to $HOME/MPSProjects/mcp-study/workspace/<run-id>-<UTC stamp>/, one at a time and
never at a path an earlier run used. The map,
including that workspace contract, is $STUDY/README.md.
Roles
- Observer (this session, Opus-class): orchestrates, never performs the MPS task, never tells
workers they are measured, evaluates results read-only, writes the report. Owns the whole
lifecycle: synthesizes empty projects (
scripts/new_study_project.py), opens them via CLI (mps-project-management), closes them withmps_mcp_close_project, and starts, restarts and shuts MPS down withscripts/mps_control.sh. Before each swap, tell the user the absolute path about to close (if any) and the absolute path about to open — do not ask them to perform the swap and do not wait for approval. - Workers: headless CLI processes (
claude -porjunie --task), one per (scenario, model, run), launched bystudy/scripts/run_worker.sh. Evidence = their transcript + the server call log. - Human: answers the gate questions, approves pushes, and dismisses MPS dialogs when a call
returns
MODAL_BLOCKEDor a close/exit hangs on a confirmation. Does not open, close or create projects and does not restart MPS — those are observer actions now.
What ships with it
4 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.
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 · -138 lines fe961a1a2352
- 3d ago Changed · +4 lines 82b67fd07041
- 11d ago Changed · +4 lines 7c67e007c68f
- 29d ago Changed · +1 lines 258e64dc8043
- 1mo ago Changed · +28 lines 47af49bf61d2
- 1mo ago First seen · 189 lines · 93 tokens per session scan A bbb9a330c483
skill-optimization-study is a skill published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 1,400 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 2026-09-27.
skill-optimization-study compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-optimization-studyJetBrains/MPS | Skill | 1.7k | yesterday | Apache-2.0 | A | 93 | 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 |