By sumanth-14
Agentic delivery runtime. Orchestrates PM, BA, SM, Architect, Developer, QA, Security, and DevOps agents through a 3-phase SDLC with mandatory deliverables and human approval gates.
Approve the current phase gate and advance to the next stage.
Send the current artifact back for revision with specific feedback.
Begin a new Kernel-orchestrated delivery cycle. Loads the framework and prompts for the request.
Show current Kernel delivery state — active phase, agent, last artifact, pending approvals.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An agentic delivery runtime that orchestrates AI agents to ship production-grade software through a full Software Development Life Cycle (SDLC).
Kernel coordinates specialized AI agents across all phases of software development—from inception through construction to operations. It enforces quality gates, mandatory deliverables, and formal approval workflows to ensure every delivery meets professional standards.
kernel/
├── CLAUDE.md # Core framework definition
├── .kernel/ # Agent rules + generated artifacts
│ ├── common/ # Shared processes and standards
│ │ ├── process-overview.md
│ │ ├── session-continuity.md
│ │ ├── audit-format.md
│ │ └── quality-standards.md
│ ├── inception/ # Requirements and planning phase
│ │ ├── product-manager.md
│ │ ├── business-analyst.md
│ │ └── scrum-master.md
│ ├── construction/ # Design and development phase
│ │ ├── architect.md
│ │ ├── developer.md
│ │ └── qa-engineer.md
│ ├── operations/ # Deployment and security phase
│ │ ├── security.md
│ │ └── devops.md
│ └── artifacts/ # Generated deliverables (created during execution)
│ ├── state.md # Progress tracker
│ ├── audit.md # Audit log
│ ├── inception/ # Phase 1 deliverables
│ ├── construction/ # Phase 2 deliverables
│ └── operations/ # Phase 3 deliverables
└── README.md # This file
Agents: Product Manager → Business Analyst → Scrum Master
Deliverables: PRD, BRD, FRS, User Stories, Sprint/Bolt Plan
Gate: Human approval required before proceeding
Agents: Architect → Developer → QA Engineer
Deliverables: HLD, LLD, ADRs, Code, Test Suite
Gate: QA sign-off required before proceeding
Agents: Security Agent → DevOps Agent
Deliverables: Security Review, Deployment Plan, Monitoring Setup
Gate: Security clearance required before deployment
Start every session by stating your intent with "Using Kernel, ...":
Using Kernel, build a subscription management API
Using Kernel, add OAuth2 login to the existing app
Using Kernel, fix the race condition in the payment queue
The framework will automatically:
| Request Type | Phases Executed |
|---|---|
| New feature / greenfield | 01 Inception → 02 Construction → 03 Operations |
| Enhancement (existing) | BA stage → 02 Construction → Security check |
| Bug fix | Developer → QA → Security patch check |
| Infrastructure change | Architect → DevOps |
| Security patch | Security Agent → Developer → QA |
| Performance optimization | Architect → Developer → QA → DevOps |
Kernel ships as both a universal agent skill (works with Claude Code, Cursor, Copilot, Codex, Windsurf, Gemini CLI, Cline, and more) and a native Claude Code plugin.
npx skills add sumanth-14/kernel-dlc
npx claudepluginhub sumanth-14/kernel-dlc --plugin kernelComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.