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/study-run-cleanup/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/study-run-cleanup)<a href="https://agentmods.dev/skills/jetbrains/mps/study-run-cleanup"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/study-run-cleanup/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/study-run-cleanup"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/study-run-cleanup.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 | $0.00061 | $0.00424 |
| Opus 5.5 | $0.00024 | $0.00170 |
| Sonnet 5.5 | $0.00012 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
study-run-cleanup 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.
What it actually says
Study run cleanup
Observer-only. This skill is not in the bundled mps-* catalog, so a measured worker does not
load it. The same file is copied to .claude/skills/study-run-cleanup/SKILL.md. Keep the two
copies identical. Do not replace either with a symlink.
The procedure is plugins/mcp-tools/study/instructions/cleanup.md. Read it and follow it. Do not
keep a second copy here.
Before any deletion
- Dry-run is the default. Print the paths. Apply only the list a human accepted.
- The deletion unit is a directory that contains
.mps. Never a bucket (r10,unclosed,s15), neverharness*, never a probe or fixture-build tree. - The archive that existed on 2026-10-30 is classified and kept. The first dry-run does not emit
a delete list for
archive/workspaceorarchive/fixtures. Directory suffix is not the study round; do not maprNtoround-N. - A scratch with no
*.fixture.jsonstamp is not eligible. Every existing scratch is in that state. "Two newest per family" applies only after a stamp records the fixture name and sha256. - Stop if MPS has the project open, including under its pre-move
proj/orproj-rN/path, or if a listed open path does not exist on disk. - Do not delete transcripts in this step. Moving old files out of live
runs/is a separately named dry-run, and it leavesinventory.jsonin place.
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 First seen · 29 lines · 61 tokens per session scan A 651e5226dd04
study-run-cleanup is a skill published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 424 once invoked, about $0.0002 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 2026-11-04.
study-run-cleanup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| study-run-cleanupJetBrains/MPS | Skill | 1.7k | yesterday | Apache-2.0 | A | 61 | 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 |