System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
Senior backend engineer for Go API development. Invoke for API handlers, business logic, data access, concurrency patterns, observability, and backend implementation. Writes production code using TDD workflow.
Build orchestrator at Layer 1. Spawned by @overseer. Elicits requirements, assesses tier, decomposes into scope cards, dispatches Tech-Leads or Builders, monitors convergence, and reports completion to @overseer. Never writes code — pure orchestration.
Senior database engineer. Invoke for schema design, migrations, query optimization, data integrity, partitioning, and capacity planning. Writes migrations and SQL — not application code.
Senior DevOps engineer. Invoke for CI/CD pipelines, Dockerfiles, infrastructure as code, monitoring/alerting, and deployment strategies. Writes IaC and pipeline configs — not application code.
Senior frontend engineer for Vue 3 development. Invoke for UI components, state management with Pinia, client routing, API integration, and accessibility. Writes production code using component-first workflow.
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.
Senior mobile engineer for Flutter development. Invoke for Flutter widgets, Riverpod state management, gorouter navigation, platform APIs, and offline-first data patterns. Writes production code using widget-first workflow.
Pipeline supervisor at Layer 0. Spawns @conductor, monitors pipeline progress, handles conductor succession, spawns @red-team-lead (for structural information isolation), and reports final results to user. Ultra-lightweight — owns the pipeline flow loop, not the work. Never writes code, never decomposes work, never…
Active performance specialist for profiling, benchmarking, load testing, and optimization implementation. Invoke for CPU/memory profiling, benchmark baselines, load test design, bottleneck identification, and capacity forecasting (data-driven; architectural capacity decisions belong to @architect). Writes optimization…
Delivery validation coordinator. Activated at Tier 2+ only (Tier 1 skips Red Team). Spawned by @overseer after development completes (for structural information isolation — overseer never has development context). Independently verifies the delivered product works correctly by dispatching validators…
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
Dedicated research agent for codebase exploration, pattern discovery, technology research, and requirement decomposition. Read-only — produces research logs, findings documents, and feasibility assessments. Never writes code or makes architecture decisions.
Senior technical writer and documentation quality authority. Invoke for API documentation, architecture diagrams, user guides, release notes, README files, and migration guides. Writes documentation — not code.
Hands-on test automation engineer. Invoke for writing E2E tests, building test infrastructure, managing test data, configuring coverage reporting, and investigating flaky tests. MCP-first Playwright automation. This agent writes test code — not production code.
Architecture Decision Record skill for documenting significant architectural decisions with context, options, and consequences. Use during the Research phase when choosing between approaches, or whenever the user asks to document an architectural decision.
Shared protocols for all agents in the multi-agent pipeline: recursive nesting, pre-implementation restatement, agent spawn protocol, parallel dispatch format, completion reporting, and sovereign subagent awareness. Load this skill instead of inlining these protocols in every agent file.