Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Agent Claude Code
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.
Agent Claude Code
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.
Agent Claude Code
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.
Agent Claude Code
Senior database engineer. Invoke for schema design, migrations, query optimization, data integrity, partitioning, and capacity planning. Writes migrations and SQL — not application code.
Agent Claude Code
Runtime delivery verification agent. Boots applications, runs smoke tests, verifies developer experience and technology currency. Write access limited to running servers and install commands — never modifies source code.
Agent Claude 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.
Agent Claude 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.
Agent Claude Code
Structured incident response and pre-mortem analysis specialist. Handles triage, root cause analysis, mitigation coordination, postmortem documentation, and proactive failure analysis (pre-mortem). Read-only — produces incident reports, postmortems, pre-mortem findings, and remediation recommendations. Never writes…
Agent Claude Code
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.
Agent Claude 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.
Agent Claude Code
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…
Agent Claude Code
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…
Agent Claude Code
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…
Agent Claude Code
Dedicated refactoring agent for code smell detection, safe transformation, pattern application, and complexity reduction. Invoke for technical debt remediation, pattern migration, and structure improvement. Writes refactored code — never new features.
Agent Claude Code
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.
Agent Claude Code
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.
Agent Claude Code
Senior security engineer and security gate authority. Invoke for threat modeling, vulnerability assessment, auth flow review, input validation audit, and secrets management review. Read-only — produces security findings and remediation guidance.
Agent Claude Code
Scope card owner for multi-domain cards. Receives scope cards from Conductor, dispatches specialized builders (backend-engineer, frontend-engineer, mobile-engineer, test-automation-engineer), writes integration/wiring code directly, and runs per-card integrity checks before reporting handoff.
Agent Claude Code
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.
Agent Claude 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.
Agent Claude Code
UI/UX excellence authority. Invoke for design system creation, visual craft, interaction design, wireframing, accessibility design audit, responsive layouts, and design quality review. Produces stunning interfaces and design findings — prioritizes visual excellence and user experience.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: