Skip to main content

Agents Overview

The ADLC Framework includes 15 constitutional agents and 163 marketplace agents for enterprise AI governance.

Constitutional Agents

AgentPrincipleResponsibility
product-ownerIFeature prioritization, business value validation
cloud-architectIVDeployment targets, architecture decisions
security-compliance-engineerII, VIThreat modeling, compliance audits
meta-engineering-expertVIIAgent/command/skill creation
python-engineerIIIPython CLI, boto3, FastAPI implementation
infrastructure-engineerIVCDK/Terraform implementation
kubernetes-engineerIVK3D/K3S cluster management
qa-engineerIIITest orchestration, 100% coverage enforcement
observability-engineerVMELT telemetry, SLO monitoring
fullstack-engineerVIIReact UIs, Docusaurus sites
devops-security-engineerIICI/CD pipelines, supply chain security
sre-engineerVIncident response, SLO management
finops-engineerIVGitOps workflows, cost optimization
qa-automation-engineerIIIBDD scenarios, test automation
technical-writerVIIRunbooks, playbooks, API docs
info

Constitutional agents are stored in .claude/agents/ alongside the framework. They are loaded at session start and participate in every coordination cycle. Marketplace agents are on-demand and invoked only when a specific domain skill is required.

Marketplace Agents (163)

Organized in 26 domain categories:

CategoryAgentsUse Cases
ai-specialists/9RAG, embeddings, fine-tuning
data-ai/10Data pipelines, analytics
database/11PostgreSQL, MongoDB, Redis
devops-infrastructure/10CI/CD, Docker, Kubernetes
security/7Vulnerability scanning, IAM
deep-research-team/15Research automation
development-team/10Full-stack development
...91 moreVarious domains
tip

Browse the full marketplace catalog at /marketplace to find agents for your specific domain. Each agent lists its tools, model tier (opus/sonnet/haiku), and required coordination prerequisites.

Usage Pattern

Mandatory Workflow (BLOCKING)

The mandatory execution order is: Product Owner first, Cloud Architect second, then a Specialist for implementation, and QA Engineer for validation. No agent may skip to a later position in the chain.

Example Task Delegation

The following sequence shows how the orchestrator delegates through the mandatory coordination chain using the Task tool.

# Start with product-owner
Task tool: subagent_type="product-owner"
Prompt: "Validate requirements for user authentication feature"

# Then cloud-architect
Task tool: subagent_type="cloud-architect"
Prompt: "Design authentication architecture"

# Then specialist
Task tool: subagent_type="infrastructure-engineer"
Prompt: "Implement Cognito CDK stack"

Agent Files

Constitutional agents are in .claude/agents/:

  • decision/product-owner.md
  • decision/cloud-architect.md
  • decision/security-compliance-engineer.md
  • execution/ (8 agents: meta-engineering-expert, python-engineer, infrastructure-engineer, kubernetes-engineer, qa-engineer, observability-engineer, fullstack-engineer, devops-security-engineer)
  • operations/ (4 agents: sre-engineer, finops-engineer, qa-automation-engineer, technical-writer)
  • ... (15 total)

Marketplace agents are in .claude/agents/marketplace/:

  • ai-specialists/
  • data-ai/
  • database/
  • ... (26 categories, 163 agents)