Agent Reference

July 14, 2026 · View on GitHub

Complete reference for all 203 local specialized AI agents organized by category with model assignments.

Agent Categories

Architecture & System Design

Core Architecture

AgentModelDescription
backend-architectopusRESTful API design, microservice boundaries, database schemas
frontend-developersonnetReact components, responsive layouts, client-side state management
graphql-architectopusGraphQL schemas, resolvers, federation architecture
architect-revieweropusArchitectural consistency analysis and pattern validation
cloud-architectopusAWS/Azure/GCP infrastructure design and cost optimization
hybrid-cloud-architectopusMulti-cloud strategies across cloud and on-premises environments
kubernetes-architectopusCloud-native infrastructure with Kubernetes and GitOps
service-mesh-expertopusIstio/Linkerd service mesh architecture, mTLS, and traffic management
event-sourcing-architectopusEvent sourcing, CQRS patterns, event stores, and saga orchestration
monorepo-architectopusMonorepo tooling with Nx, Turborepo, Bazel, and workspace optimization

UI/UX & Mobile

AgentModelDescription
ui-designeropusUI/UX design for mobile and web with modern patterns
accessibility-expertopusWCAG compliance, accessibility audits, inclusive design
design-system-architectopusDesign tokens, component libraries, theming systems
ui-ux-designersonnetInterface design, wireframes, design systems
ui-visual-validatorsonnetVisual regression testing and UI verification
mobile-developersonnetReact Native and Flutter application development
ios-developersonnetNative iOS development with Swift/SwiftUI
flutter-expertsonnetAdvanced Flutter development with state management

Programming Languages

Systems & Low-Level

AgentModelDescription
c-prosonnetSystem programming with memory management and OS interfaces
cpp-prosonnetModern C++ with RAII, smart pointers, STL algorithms
rust-prosonnetMemory-safe systems programming with ownership patterns
golang-prosonnetConcurrent programming with goroutines and channels

Web & Application

AgentModelDescription
javascript-prosonnetModern JavaScript with ES6+, async patterns, Node.js
typescript-prosonnetAdvanced TypeScript with type systems and generics
python-prosonnetPython development with advanced features and optimization
temporal-python-prosonnetTemporal workflow orchestration with Python SDK, durable workflows, saga patterns
ruby-prosonnetRuby with metaprogramming, Rails patterns, gem development
php-prosonnetModern PHP with frameworks and performance optimization

Enterprise & JVM

AgentModelDescription
java-prosonnetModern Java with streams, concurrency, JVM optimization
scala-prosonnetEnterprise Scala with functional programming and distributed systems
csharp-prosonnetC# development with .NET frameworks and patterns

Specialized Platforms

AgentModelDescription
elixir-prosonnetElixir with OTP patterns and Phoenix frameworks
django-prosonnetDjango development with ORM and async views
fastapi-prosonnetFastAPI with async patterns and Pydantic
haskell-prosonnetStrongly typed functional programming with purity, advanced type systems, and concurrency
unity-developersonnetUnity game development and optimization
minecraft-bukkit-prosonnetMinecraft server plugin development
sql-prosonnetComplex SQL queries and database optimization

Infrastructure & Operations

DevOps & Deployment

AgentModelDescription
devops-troubleshootersonnetProduction debugging, log analysis, deployment troubleshooting
deployment-engineersonnetCI/CD pipelines, containerization, cloud deployments
terraform-specialistsonnetInfrastructure as Code with Terraform modules and state management
dx-optimizersonnetDeveloper experience optimization and tooling improvements

Database Management

AgentModelDescription
database-optimizersonnetQuery optimization, index design, migration strategies
database-adminsonnetDatabase operations, backup, replication, monitoring
database-architectopusDatabase design from scratch, technology selection, schema modeling

Incident Response & Network

AgentModelDescription
incident-responderopusProduction incident management and resolution
network-engineersonnetNetwork debugging, load balancing, traffic analysis

Project Management

AgentModelDescription
conductor-validatoropusValidates Conductor project artifacts for completeness, consistency, and correctness

Quality Assurance & Security

Code Quality & Review

AgentModelDescription
code-revieweropusCode review with security focus and production reliability
security-auditoropusVulnerability assessment and OWASP compliance
backend-security-coderopusSecure backend coding practices, API security implementation
frontend-security-coderopusXSS prevention, CSP implementation, client-side security
mobile-security-coderopusMobile security patterns, WebView security, biometric auth
threat-modeling-expertopusSTRIDE threat modeling, attack trees, and security requirements

Testing & Debugging

AgentModelDescription
test-automatorsonnetComprehensive test suite creation (unit, integration, e2e)
tdd-orchestratorsonnetTest-Driven Development methodology guidance
debuggersonnetError resolution and test failure analysis
error-detectivesonnetLog analysis and error pattern recognition

Performance & Observability

AgentModelDescription
performance-engineeropusApplication profiling and optimization
observability-engineeropusProduction monitoring, distributed tracing, SLI/SLO management
search-specialisthaikuAdvanced web research and information synthesis

Data & AI

Data Engineering & Analytics

AgentModelDescription
data-scientistopusData analysis, SQL queries, BigQuery operations
data-engineersonnetETL pipelines, data warehouses, streaming architectures

Machine Learning & AI

AgentModelDescription
ai-engineeropusLLM applications, RAG systems, prompt pipelines
ml-engineeropusML pipelines, model serving, feature engineering
mlops-engineeropusML infrastructure, experiment tracking, model registries
prompt-engineeropusLLM prompt optimization and engineering
vector-database-engineeropusVector databases, embeddings, similarity search, and hybrid retrieval
llm-finetuning-architectopusFine-tuning strategy, method/model selection, eval-gate ownership
llm-finetuning-training-engineersonnetDataset prep, Unsloth training runs, artifact export
llm-finetuning-eval-engineersonnetGolden sets, judge calibration, checkpoint promotion verdicts
dgx-spark-ops-engineersonnetDGX Spark (GB10/aarch64/CUDA 13) environment setup and diagnostics

Documentation & Technical Writing

AgentModelDescription
docs-architectopusComprehensive technical documentation generation
api-documentersonnetOpenAPI/Swagger specifications and developer docs
reference-builderhaikuTechnical references and API documentation
tutorial-engineersonnetStep-by-step tutorials and educational content
mermaid-expertsonnetDiagram creation (flowcharts, sequences, ERDs)
c4-codehaikuC4 Code-level documentation with function signatures and dependencies
c4-componentsonnetC4 Component-level architecture synthesis and documentation
c4-containersonnetC4 Container-level architecture with API documentation
c4-contextsonnetC4 Context-level system documentation with personas and user journeys

Business & Operations

Business Analysis & Finance

AgentModelDescription
business-analystsonnetMetrics analysis, reporting, KPI tracking
quant-analystopusFinancial modeling, trading strategies, market analysis
risk-managersonnetPortfolio risk monitoring and management

Marketing & Sales

AgentModelDescription
content-marketersonnetBlog posts, social media, email campaigns
social-publishing-publisherhaikuMulti-platform social media publishing via SocialClaw
sales-automatorhaikuCold emails, follow-ups, proposal generation
AgentModelDescription
customer-supportsonnetSupport tickets, FAQ responses, customer communication
hr-proopusHR operations, policies, employee relations
legal-advisoropusPrivacy policies, terms of service, legal documentation

SEO & Content Optimization

AgentModelDescription
seo-content-auditorsonnetContent quality analysis, E-E-A-T signals assessment
seo-meta-optimizerhaikuMeta title and description optimization
seo-keyword-strategisthaikuKeyword analysis and semantic variations
seo-structure-architecthaikuContent structure and schema markup
seo-snippet-hunterhaikuFeatured snippet formatting
seo-content-refresherhaikuContent freshness analysis
seo-cannibalization-detectorhaikuKeyword overlap detection
seo-authority-buildersonnetE-E-A-T signal analysis
seo-content-writersonnetSEO-optimized content creation
seo-content-plannerhaikuContent planning and topic clusters

Specialized Domains

AgentModelDescription
arm-cortex-expertsonnetARM Cortex-M firmware and peripheral driver development
blockchain-developersonnetWeb3 apps, smart contracts, DeFi protocols
payment-integrationsonnetPayment processor integration (Stripe, PayPal)
legacy-modernizersonnetLegacy code refactoring and modernization
context-managerhaikuMulti-agent context management

Model Configuration

Agents are assigned to specific Claude models based on task complexity and computational requirements.

Model Distribution Summary

ModelAgent CountUse Case
Fable0Longest-horizon autonomous work (tier above Opus; see criteria)
Opus55Critical architecture, security, code review, production coding
Sonnet71Complex tasks, support with intelligence
Haiku25Fast operational tasks
Inherit52Complex tasks where the user chooses the model at runtime

Model Selection Criteria

Haiku - Fast Execution & Deterministic Tasks

Use when:

  • Generating code from well-defined specifications
  • Creating tests following established patterns
  • Writing documentation with clear templates
  • Executing infrastructure operations
  • Performing database query optimization
  • Handling customer support responses
  • Processing SEO optimization tasks
  • Managing deployment pipelines

Sonnet - Complex Reasoning & Architecture

Use when:

  • Designing system architecture
  • Making technology selection decisions
  • Performing security audits
  • Reviewing code for architectural patterns
  • Creating complex AI/ML pipelines
  • Providing language-specific expertise
  • Orchestrating multi-agent workflows
  • Handling business-critical legal/HR matters

Fable - Longest-Horizon Autonomous Work

Claude Fable 5 (model: fable) is the tier above Opus. It is opt-in in Claude Code (v2.1.170+, never the default) and carries roughly 2.6× the effective cost of Opus ($10/$50 per MTok plus a ~30% heavier tokenizer), so reserve it for agents where Opus demonstrably needs multiple attempts.

Use when:

  • Running multi-hour autonomous sessions (large codebase migrations, overnight refactors)
  • Executing end-to-end work from a single well-specified goal
  • Coordinating long-lived parallel sub-agent workstreams

Avoid for:

  • Security-analysis agents — Fable 5's cyber/bio safety classifiers fall back to Opus 4.8 on that content anyway
  • Anything Sonnet or Opus already completes in one pass

Other harnesses map fable to their top available model (see authoring.md). Fable-tier agent bodies should state goals and constraints rather than step-by-step scaffolding, and must not ask the model to echo its internal reasoning.

Hybrid Orchestration Patterns

The plugin ecosystem leverages Sonnet + Haiku orchestration for optimal performance and cost efficiency:

Pattern 1: Planning → Execution

Sonnet: backend-architect (design API architecture)

Haiku: Generate API endpoints following spec

Haiku: test-automator (generate comprehensive tests)

Sonnet: code-reviewer (architectural review)

Pattern 2: Reasoning → Action (Incident Response)

Sonnet: incident-responder (diagnose issue, create strategy)

Haiku: devops-troubleshooter (execute fixes)

Haiku: deployment-engineer (deploy hotfix)

Haiku: Implement monitoring alerts

Pattern 3: Complex → Simple (Database Design)

Sonnet: database-architect (schema design, technology selection)

Haiku: sql-pro (generate migration scripts)

Haiku: database-admin (execute migrations)

Haiku: database-optimizer (tune query performance)

Pattern 4: Multi-Agent Workflows

Full-Stack Feature Development:
Sonnet: backend-architect + frontend-developer (design components)

Haiku: Generate code following designs

Haiku: test-automator (unit + integration tests)

Sonnet: security-auditor (security review)

Haiku: deployment-engineer (CI/CD setup)

Haiku: Setup observability stack

Agent Invocation

Natural Language

Agents can be invoked through natural language when you need Claude to reason about which specialist to use:

"Use backend-architect to design the authentication API"
"Have security-auditor scan for OWASP vulnerabilities"
"Get performance-engineer to optimize this database query"

Slash Commands

Many agents are accessible through plugin slash commands for direct invocation:

/backend-development:feature-development user authentication
/security-scanning:security-sast
/incident-response:smart-fix "memory leak in payment service"

Contributing

To add a new agent:

  1. Create plugins/{plugin-name}/agents/{agent-name}.md
  2. Add frontmatter with name, description, and model assignment
  3. Write comprehensive system prompt
  4. Update plugin definition in .claude-plugin/marketplace.json

See Contributing Guide for details.