dev-engine
Multi-agent development execution - task decomposition, specialist agents, parallel dispatch, quality gates, and 50+ framework knowledge skills.
dev-engine
The execution arm of the hjemmesidekongen/ai methodology. Where claude-core provides the infrastructure and verification, dev-engine handles the actual development work - decomposing tasks, dispatching specialist agents, and enforcing quality gates before anything ships.
Version: 0.2.0 · 53 skills · 6 agents · 2 commands
What It Does
Give dev-engine a task description, and it handles the rest: scans your project to understand the tech stack, decomposes the task into subtasks, assigns each to the right specialist agent, dispatches them in parallel with file-ownership isolation, and runs a 10-point quality gate before anything is marked done.
No agent marks its own work complete. No file is written to by two agents simultaneously. No task ships without verification.
Commands
| Command | What It Does |
|---|---|
/dev:run | Full pipeline - decompose, assign, dispatch, verify. Supports --dry-run for preview. |
/dev:scan | Scan repo for tech stack and architecture. Outputs .ai/project-map.yml with Mermaid C4 diagram. |
Run the full pipeline:
/dev:run "Build user profile page with avatar upload and form validation"Or preview without executing:
/dev:run "Build user profile page" --dry-runKey Concepts
The Pipeline
Task Description
│
▼
┌─────────────┐
│ project-mapper │ Scans repo → detects stack, maps modules
└──────┬──────┘
│
▼
┌──────────────┐
│ taskflow-bridge │ Loads acceptance criteria (if taskflow active)
└──────┬───────┘
│
▼
┌───────────────┐
│ task-decomposer │ Breaks task into ordered subtasks with dependencies
└──────┬────────┘
│
▼
┌────────────────┐
│ tier-assignment │ Maps each subtask to junior/senior/principal model
└──────┬─────────┘
│
▼
┌──────────────────┐
│ context-assembler │ Packages relevant knowledge per agent (8k token budget)
└──────┬───────────┘
│
▼
┌──────────────────┐
│ agent-dispatcher │ Parallel execution with file ownership enforcement
└──────┬───────────┘
│
▼
┌────────────────┐
│ completion-gate │ 10-point quality check by code-reviewer agent
└────────────────┘Parallel Execution with File Ownership
When dev-engine dispatches multiple agents, each one gets exclusive ownership of specific files:
frontend-dev → owns: src/components/Profile.tsx, src/styles/profile.css
backend-dev → owns: src/api/profile.ts, prisma/schema.prisma
test-engineer → owns: tests/profile.test.ts, tests/api/profile.test.tsNo two agents write to the same file. If a task decomposition creates file conflicts, the dispatcher serializes those tasks instead of parallelizing them.
Interface contracts are defined at boundaries before implementation starts - agents agree on the API shape before building both sides.
Tier-Based Model Assignment
Not every subtask needs the most expensive model. dev-engine uses a 5-factor risk matrix to assign tiers:
| Factor | Weight | What It Measures |
|---|---|---|
| Scope | 20% | How many files/modules affected |
| Reversibility | 20% | How hard to undo if wrong |
| Ambiguity | 25% | How clear are the requirements |
| Impact | 20% | Blast radius of mistakes |
| Dependencies | 15% | How many other tasks depend on this |
Junior (haiku): Simple, well-defined tasks - rename a variable, add a CSS class, write a straightforward test.
Senior (sonnet): Typical development work - build a component, wire up an API endpoint, implement business logic.
Principal (opus): High-risk or complex tasks - architecture decisions, security reviews, design evaluations that affect multiple modules.
10-Point Completion Gate
Every task passes through these checks before it's marked done:
- Spec compliance - does it match the requirements?
- Lint - no warnings, no errors
- Type check - TypeScript strict mode passes
- Unit tests - written and passing
- Integration tests - component interactions verified
- E2E tests - user flows tested
- Test coverage - meets threshold
- Visual verification - responsive at 3 breakpoints
- Security - no OWASP Top 10 violations
- Artifacts - all deliverables present
The code-reviewer agent runs this gate. It's the only agent authorized to approve work. Implementing agents cannot mark their own tasks done.
Component Reference
Agents
Six agents, each with a defined role and expertise:
| Agent | Model | Specialty |
|---|---|---|
| frontend-dev | sonnet | React, Next.js, Vue, Nuxt, CSS, accessibility, responsive design |
| backend-dev | sonnet | NestJS, Prisma, Node.js, APIs, database schema, data layer |
| test-engineer | sonnet | Unit, integration, E2E tests across all frameworks |
| architect | opus | Design review, dependency analysis, module boundaries (read-only) |
| app-security-auditor | opus | OWASP checks, dependency audit, auth review, secret detection (read-only) |
| code-reviewer | opus | 10-point completion gate - the only agent that can approve work as done (read-only) |
The three read-only agents (architect, security, code-reviewer) never modify code. They analyze and report. This separation prevents conflicts of interest - the agent that writes the code never grades it.
Framework Knowledge (53 Skills)
dev-engine doesn't give generic advice. Each framework skill contains verified, version-specific knowledge that agents load as context before working.
Frontend
| Skill | Coverage |
|---|---|
| react-patterns | Hooks, context, composition, performance, React 19 features (use(), Actions, useOptimistic) |
| nextjs-app-router | Server components, route handlers, caching, layouts, server actions |
| vue-patterns | Composition API, reactivity, Pinia, provide/inject, compiler macros |
| nuxt-patterns | Auto-imports, useFetch, server routes, layers, module development |
| tailwind-v4 | CSS-first config, @theme, @utility, container queries, dark mode |
| accessibility-wcag | WCAG 2.1 AA, ARIA, keyboard navigation, semantic HTML, color contrast |
| storybook-patterns | CSF3, args, play functions, interaction testing, Chromatic CI |
Backend
| Skill | Coverage |
|---|---|
| nestjs-patterns | Modules, providers, guards, interceptors, pipes, exception filters |
| prisma-patterns | Schema design, migrations, relations, N+1 elimination, transactions |
| nodejs-patterns | Streams, worker threads, event loop, clustering, Node 22+ features |
Infrastructure & Tooling
| Skill | Coverage |
|---|---|
| typescript-modern | TS 5.4+ features, branded types, module augmentation, type-level testing |
| vite-patterns | Config, plugins, HMR, build optimization, manual chunks |
| turborepo-patterns | Pipeline config, caching, filtering, remote cache, Docker pruning |
| eslint-config | Flat config (ESLint 9), custom rules, TypeScript integration |
| package-managers | pnpm workspaces, lockfile management, peer deps, Node version pinning |
| openapi-typescript | Code generation, type-safe clients, contract-first development |
Testing
| Skill | Coverage |
|---|---|
| e2e-testing-patterns | Playwright/Cypress, page objects, fixtures, network interception, visual regression |
| playwright-testing | Locators, assertions, fixtures, visual comparison, CI sharding, trace viewer |
| tdd-workflow | Red-green-refactor enforcement with framework-specific guidance |
| systematic-debugging | 4-phase protocol: evidence, patterns, hypotheses, validated fix |
Security
| Skill | Coverage |
|---|---|
| security-audit | OWASP Top 10, CVE scanning, secret detection, CSP headers |
| auth-patterns | OAuth 2.0 + PKCE, JWT (RS256/ES256), refresh rotation, RBAC/ABAC |
| api-security | Rate limiting, input validation (zod/joi), CORS, Helmet.js |
| web-security-owasp | XSS, CSRF, SQL/NoSQL injection, SSRF, clickjacking |
Expo (React Native) - 12 Skills
Full coverage for React Native development with Expo:
- Deployment (EAS Build, OTA updates, app store submission)
- Upgrading (SDK migration, breaking changes, rollback)
- Native UI (platform components, gestures, animations)
- API Routes (server functions in Expo Router)
- Data Fetching (React Query, SWR, offline support)
- Dev Client (custom builds, native module debugging)
- Tailwind (NativeWind integration)
- DOM Components (web components in native, WebView patterns)
- SwiftUI integration (native iOS views via Expo modules)
- Jetpack Compose (native Android views via Expo modules)
- CI/CD (GitHub Actions, EAS, automated pipelines)
- Simulators (iOS Simulator, Android Emulator management)
Quality & Integration
| Skill | Coverage |
|---|---|
| code-review | Bidirectional review with severity classification |
| verification-before-completion | Stack-specific verification commands |
| visual-verification | Playwright screenshots at 3 breakpoints with LLM comparison |
| error-handling-patterns | Custom error hierarchy, retry strategies, error boundaries |
| git-advanced-workflows | Scripted bisect, monorepo patterns, pre-commit hooks |
| package-audit | npm audit, outdated dependency triage, license compliance |
| skill-quality-rubric | 8-dimension quality framework for skill auditing |
Integration with taskflow
When taskflow is installed, dev-engine automatically:
- Loads acceptance criteria from the active task
- Maps criteria to completion gate checks
- Uses task context to inform decomposition
When taskflow is not installed, dev-engine works standalone using only the task description you provide. No hard dependencies.
See also
- claude-core - the foundation plugin that dev-engine depends on
- taskflow - task management that feeds acceptance criteria into the pipeline
- Workflows - recipes showing dev-engine in action
claude-core
Foundation plugin - planning, brainstorming, verification, tracing, memory governance, debugging, learning pipelines, and workplace integrations.
taskflow
Task management and workplace integration - Jira ingestion, contradiction detection, PR workflows, QA handover, and cross-session continuity.