By yannickloth
Intelligent routing system for Claude Code with IVP-compliant architecture. Routes all requests through a central router that delegates to specialized or general agents based on task complexity, risk assessment, and cost optimization.
npx claudepluginhub yannickloth/claude-router-system --plugin infolead-claude-subscription-routerFast, cost-effective agent for straightforward tasks with no specialized agent available. Use for mechanical operations where the approach is obvious and unambiguous (pattern matching, simple transforms, basic file operations). Route here when task requires speed over reasoning and involves no judgment calls or significant consequences.
Cost-optimized first-pass routing using mechanical escalation checklist. Handles simple unambiguous requests directly; escalates complex ones to Sonnet router. Provides ~80% cost savings for straightforward requests.
High-capability agent for complex reasoning tasks with no specialized agent available. Use when task requires deep analysis beyond Sonnet's capabilities - mathematical proofs, sophisticated logical verification, detecting subtle flaws, or high-stakes decisions where errors would be very costly. Choose this when correctness is critical and requires exceptional reasoning depth.
Design implementation plans for complex tasks with cost-aware batching strategies. Use when entering plan mode or when task requires multi-step planning before execution.
Optimistically route HIGH confidence requests to Haiku with validation and auto-escalate to Sonnet if validation fails. Enables 35-40% additional quota savings for simple mechanical tasks.
Handles routing decisions when router is uncertain. Analyzes edge cases with deeper reasoning, determines the appropriate agent, and spawns it directly.
Entry point for all requests. Interprets user intent, assesses risk, and routes to the appropriate specialized or general agent. Use proactively for EVERY user request.
Balanced agent for general tasks with no specialized agent available. Use when task requires reasoning, analysis, judgment calls, or assessing trade-offs. Default choice for non-specialized work. Handles multi-step planning, cross-referencing, and coordination. Choose this when task complexity is uncertain or involves any risk assessment.
Analyzes execution cost/benefit trade-offs and recommends optimal execution strategy (direct, propose-review, draft-then-evaluate, or partitioned) based on task volume, mechanical complexity, context homogeneity, and API pricing models. Use after router identifies agent but before execution.
Classify work as sync vs async and queue async work for overnight execution to maximize quota utilization. Use for batch processing, literature searches, and background analysis.
Manages parallel work queue with WIP limits to ensure 90%+ task completion. Use for multi-task coordination, dependency tracking, and stall recovery.
A collection of plugins and tools for extending Claude Code with intelligent agent routing, cost optimization, and workflow automation.
This marketplace provides production-ready plugins that enhance Claude Code's capabilities through:
Status: Production-ready
Location: plugins/infolead-claude-subscription-router/
An intelligent routing system that analyzes user requests and delegates to the appropriate model tier. Features include:
Quick start:
# Install the plugin
ln -s $(pwd)/plugins/infolead-claude-subscription-router/.claude-plugin \
~/.claude/plugins/infolead-claude-subscription-router
# Copy the configuration template to your project
cp plugins/infolead-claude-subscription-router/EXAMPLE.claude.md \
your-project/.claude/CLAUDE.md
# Verify installation
claude /plugins
See plugin documentation for full details.
See REFACTOR_PLAN.md for the marketplace evolution plan, including:
claude-router-system/
├── plugins/
│ └── infolead-claude-subscription-router/ # Router plugin
│ ├── .claude-plugin/ # Plugin definition
│ ├── docs/ # Documentation
│ └── README.md # Plugin-specific docs
├── tests/
│ └── infolead-claude-subscription-router/ # Plugin tests
├── README.md # This file
└── REFACTOR_PLAN.md # Roadmap
Option 1: Symlink (recommended for development)
ln -s $(pwd)/plugins/PLUGIN_NAME/.claude-plugin \
~/.claude/plugins/PLUGIN_NAME
Option 2: Copy (for stable usage)
cp -r plugins/PLUGIN_NAME/.claude-plugin \
~/.claude/plugins/PLUGIN_NAME
# Start Claude Code and check plugins loaded
claude /plugins
# Verify agents available
claude /agents
Each plugin includes comprehensive tests:
# Run all tests for a plugin
./tests/PLUGIN_NAME/run_all_tests.sh
# Run specific test suites
./tests/PLUGIN_NAME/test_hooks.sh
nix-shell -p python312Packages.pytest python312Packages.pyyaml \
--run "pytest tests/PLUGIN_NAME/ -v"
See individual plugin documentation for detailed testing guides.
plugins/your-plugin-name/.claude-plugin/ structure (see existing plugins as templates)tests/your-plugin-name/plugins/your-plugin-name/README.mdEach plugin must include:
.claude-plugin/plugin.json - Plugin metadata.claude-plugin/agents/*.md - Agent definitions.claude-plugin/hooks/ - Event hooks (optional)README.md - Plugin documentationtests/ - Comprehensive test suiteContributions are welcome! Please:
./tests/PLUGIN_NAME/run_all_tests.shMIT License - see individual plugin directories for specific licensing details.
plugins/*/docs/ for detailed guidesCreated and maintained by Infolead.
Built on Claude Code by Anthropic.
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Uses power tools
Uses Bash, Write, or Edit tools
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that can be implemented quickly within 6-day sprints. Examples:\n\n<example>\nContext: Starting a new app or feature design
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Use this agent when you need expert assistance with React Native development tasks including code analysis, component creation, debugging, performance optimization, or architectural decisions. Examples: <example>Context: User is working on a React Native app and needs help with a navigation issue. user: 'My stack navigator isn't working properly when I try to navigate between screens' assistant: 'Let me use the react-native-dev agent to analyze your navigation setup and provide a solution' <commentary>Since this is a React Native specific issue, use the react-native-dev agent to provide expert guidance on navigation problems.</commentary></example> <example>Context: User wants to create a new component that follows the existing app structure. user: 'I need to create a custom button component that matches our app's design system' assistant: 'I'll use the react-native-dev agent to create a button component that aligns with your existing codebase structure and design patterns' <commentary>The user needs React Native component development that should follow existing patterns, so use the react-native-dev agent.</commentary></example>