ADLC Framework
Enterprise AI Agent Governance, Testing & Deployment Orchestration
Version: 3.7.1 | Constitutional Checkpoints: 58 | Components: 214
What is ADLC?
The Agent Development Lifecycle (ADLC) framework provides enterprise-grade governance for AI agent teams. It implements 7 constitutional principles with 58 checkpoints to ensure safe, reliable, and auditable AI operations.
Quick Start
# Install via npm
npx adlc@latest
# Or add as submodule to your project
git submodule add https://github.com/1xOps/adlc-framework.git .adlc
ln -s .adlc/.claude .claude
ln -s .adlc/.specify .specify
Key Features
| Feature | Description |
|---|---|
| 9 Constitutional Agents | Product Owner, Cloud Architect, QA Engineer, and 6 specialists |
| 30 Marketplace Agents | Curated enterprise specialists across 11 domains |
| 82 Slash Commands | CDK, Terraform, K3D, FinOps, SpecKit workflows |
| 29 Skills | Reusable capability packages with bundled references |
| 12 Governance Hooks | Auto-enforced constitutional guardrails |
| 58 Checkpoints | Quality gates before deployment |
| 3-Tier Testing | Snapshot → LocalStack → AWS Sandbox |
| Component Marketplace | Browse and install 400+ components |
Seven Principles
- Acceptable Agency - HITL approval for git, deployments, cost >$100/mo
- Interoperability - MCP standard, OAuth, least-privilege
- Evaluation-First - 100% code coverage, ≥95% agent behavior
- Hybrid Deployment - LocalStack (Tier 2) + AWS Sandbox (Tier 3)
- Observability - MELT telemetry, evidence logging
- Governance - 58 checkpoints before deployment
- Agent Engineering - Orchestrator pattern (50-100 LOC agents)
Next Steps
- ADLC Workflow - The mandatory coordination pattern
- Using Commands - Slash command quick reference
- Using Skills - How skills provide domain knowledge
- Product Management - 65 PM skills, 35 commands, CLI team bundle
- Self-Improvement - Closed-loop learning system
- Installation Guide
- Constitutional Principles
- Agent Reference
- Component Marketplace - Browse and install components