MPS: Skill for Claude Code

.agents/skills/ssr/SKILL.md

ssr is a skill for Claude Code, Codex from JetBrains/MPS. It costs 25 tokens per session (970 once invoked), scanned A, original, Apache-2.0.

A guide for IntelliJ’s Structural Search and Replace, a tool for finding code patterns and optionally replacing them. It explains how to create or edit these search rules in the project’s .idea files.

In plain words
What is it for?
Use it to create or modify IntelliJ inspections and code-pattern searches, such as detecting specific Java expressions and suggesting replacements.
Why use it?
It provides the file locations, search method, and XML format needed to change structural search inspections without relying on IDE search.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is JetBrains/MPS's own configuration. It tells Claude Code and Codex how to work on MPS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MPS configures →

About the project

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.

JetBrains/MPS · 1,666 stars · on GitHub · jetbrains.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JetBrains/MPS/master/.agents/skills/ssr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JetBrains/MPS

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ssr

README.md
[![agentmods](https://agentmods.dev/badge/skills/jetbrains/mps/ssr/github.svg)](https://agentmods.dev/skills/jetbrains/mps/ssr)
Your own site
<a href="https://agentmods.dev/skills/jetbrains/mps/ssr"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/ssr/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.

agentmods 80×15 button for ssr

Your own site · 80×15
<a href="https://agentmods.dev/skills/jetbrains/mps/ssr"><img src="https://agentmods.dev/badge/skills/jetbrains/mps/ssr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00970
Opus 5.5 $0.00010 $0.00388
Sonnet 5.5 $0.00005 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 2mo ago against content hash a4d05c554608, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ssr 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 2mo 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.

.agents/skills/ssr/SKILL.md · 61 lines

What it actually says

Structural Search and Replace

  • You must use terminal search (ls, cat and grep) to read directory .idea. Do not use IDE search.

  • The contents of structural search inspections is located in .idea/inspectionProfiles/idea_default.xml

  • Here is an example of a Structural Search and Replace inspection:


<replaceConfiguration name="Use Strings.areSameInstance instead of =="
                      description="Comparing Strings by references usually indicate a mistake, if you really need to do this (for performance reeasons or to implement &quot;Sentinel&quot; pattern), use Strings.areSameInstance method to make the intention explicit and get rid of warning."
                      suppressId="StringEqualitySSR"
                      problemDescriptor="Use !Strings.areSameInstance instead of '!=' if you really need to compare strings by reference"
                      text="$s1$ == $s2$" recursive="false" caseInsensitive="false" type="JAVA" pattern_context="default"
                      search_injected="false" reformatAccordingToStyle="false" shortenFQN="true"
                      replacement="com.intellij.openapi.util.text.Strings.areSameInstance($s1$, $s2$)">
  <constraint name="__context__" within="" contains=""/>
  <constraint name="s1" nameOfExprType="java\.lang\.String" within="" contains=""/>
  <constraint name="s2" nameOfExprType="java\.lang\.String" within="" contains=""/>
</replaceConfiguration>

This node should be located under <inspection_tool class="SSBasedInspection" tag.

  • Here is an example of a Structural Search inspection:

<searchConfiguration name="Raw coroutine scope creation" uuid="e11e9d2f-7cc2-3359-a78a-24f67cbe0850"
                     description="Coroutine scope should be created:&#10;&lt;ul&gt;&#10;&lt;li&gt;by a coroutine builder (&lt;code&gt;launch&lt;/code&gt;, &lt;code&gt;async&lt;/code&gt;, &lt;code&gt;runBlockingCancellable&lt;/code&gt;);&lt;/li&gt;&#10;&lt;li&gt;by a scoping function (&lt;code&gt;withContext&lt;/code&gt;, &lt;code&gt;coroutineScope&lt;/code&gt;, &lt;code&gt;supervisorScope&lt;/code&gt;);&lt;/li&gt;&#10;&lt;li&gt;by injecting it into a service constructor;&lt;/li&gt;&#10;&lt;li&gt;by explicitly creating a child scope (&lt;code&gt;childScope&lt;/code&gt;, &lt;code&gt;namedChildScope&lt;/code&gt;)&lt;/li&gt;&#10;&lt;/ul&gt; "
                     suppressId="RAW_SCOPE_CREATION"
                     problemDescriptor="Raw scope might not be linked to any parent unintentionally (if passed context does not have any &lt;code&gt;Job&lt;/code&gt;, or if passed &lt;code&gt;Job&lt;/code&gt; does not have any parent). Use &lt;code&gt;namedChildScope()&lt;/code&gt; on some existing scope instead. If no parent is actually intended, use &lt;code&gt;GlobalScope.namedScope()&lt;/code&gt;."
                     text="CoroutineScope($args$)" recursive="true" caseInsensitive="true" type="Kotlin" pattern_context="default"
                     search_injected="false">
  <constraint name="__context__" within="" contains=""/>
  <constraint name="args" within="" contains=""/>
</searchConfiguration>

This node should be located under <inspection_tool class="SSBasedInspection" tag.

  • To configure the scope of inspection, you need to make changes similar to this pattern, where class is UUID of the created replace configuration.

<inspection_tool class="e5d3c6f8-12ab-4cc9-8e51-8a8f1bd1c3e2" enabled="true" level="WARNING" enabled_by_default="false">
  <scope name="IDE Testing Framework" level="WARNING" enabled="true"/>
  <scope name="Tests" level="WARNING" enabled="true"/>
  <scope name="test-framework" level="WARNING" enabled="true"/>
</inspection_tool>
  • You must run InspectionProfileConsistencyTest after changing xml files
Changes

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.

  1. 2mo ago First seen · 61 lines · 25 tokens per session scan A a4d05c554608

Subscribe to this mod's changes

ssr is a skill published in the GitHub repository JetBrains/MPS (1,666 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 970 once invoked, about $0.0001 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.

Related

ssr compared with skills from other repositories

ssr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ssrJetBrains/MPSSkill1.7kyesterdayApache-2.0A25Claude Code, Codex
langiumeclipse-langium/langium-aiSkill314d agoMITA33Claude Code
lai-gen-evalseclipse-langium/langium-aiSkill314d agoMITA42Claude Code
laieclipse-langium/langium-aiSkill314d agoMITA52Claude Code
lai-gen-descriptoreclipse-langium/langium-aiSkill314d agoMITA49Claude Code
lai-gen-mcpeclipse-langium/langium-aiSkill314d agoMITA43Claude Code
lai-gen-language-skilleclipse-langium/langium-aiSkill314d agoMITA33Claude Code