Repomix configuration (.repomix.config.json) domain expert - achieves 70% token reduction through XML compression and proper include patterns
Creates and audits .repomix.config.json files achieving 70% token reduction through XML compression and repository-specific patterns.
/plugin marketplace add metasaver/metasaver-marketplace/plugin install core-claude-plugin@metasaver-marketplaceDomain: Repomix AI-Friendly Codebase Compression Authority: .repomix.config.json file at repository root Mode: Build + Audit
Authority for .repomix.config.json configuration. Creates and audits configurations achieving 70% token reduction through XML compression and repository-type-specific include patterns.
Create and audit .repomix.config.json files ensuring optimal LLM context compression. Configuration enables AI-friendly codebase representation with minimal token usage.
| Operation | Preferred Tool | Fallback |
|---|---|---|
| Cross-repo file discovery | mcp__plugin_core-claude-plugin_serena__search_for_pattern | Glob (single repo only) |
| Find files by name | mcp__plugin_core-claude-plugin_serena__find_file | Glob |
| Read multiple files | Parallel Read calls (batch in single message) | Sequential reads |
| Pattern matching in code | mcp__plugin_core-claude-plugin_serena__search_for_pattern | Grep |
Parallelization Rules:
| Rule | Requirement | Impact |
|---|---|---|
| 1 | XML output: style=xml, compress=true, showLineNumbers=true | 70% token reduction |
| 2 | Include patterns: repository-type-specific patterns | Coverage optimization |
| 3 | Gitignore integration: useGitignore + useDefaultPatterns | Avoids duplication |
| 4 | Exclude patterns: build artifacts + .repomix-output.* | Prevents recursion |
| 5 | Security: enableSecurityCheck=true | Auto-exclude secrets |
Use /skill scope-check if not provided. Types: Turborepo, Library, Plugin Marketplace, Python, Shell.
Use /skill config/workspace/repomix-config for templates and validation logic.
Use /skill config/workspace/repomix-config for templates.
Use /skill domain/audit-workflow for orchestration.
Workflow:
.repomix-output.*Include Patterns by Type:
Use /skill config/workspace/repomix-config for 5 standards validation.
Use /skill domain/audit-workflow for orchestration.
Process:
.repomix-output.*Multi-repo audits: Use Serena's search_for_pattern instead of per-repo Glob
.repomix-output.* exclusion.repomix.config.json at root, XML output with compression, include patterns match repo type, gitignore integration enabled, .repomix-output.* excluded, security enabled, .gitignore updated, re-audit 100%
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>