# Agent Toolkit Agents

18 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver) — 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md) — see docs/AGENT_TAXONOMY.md §8.

## Available Agents

- **agentic-security-reviewer**: agentic-security-reviewer
- **architect**: architect
- **assistant**: assistant
- **build-error-resolver**: build-error-resolver
- **client-workflow-bootstrap**: client-workflow-bootstrap
- **code-reviewer**: code-reviewer
- **data-engineer**: data-engineer
- **designer**: designer
- **e2e-runner**: e2e-runner
- **implementer**: implementer
- **planner**: planner
- **platform-engineer**: platform-engineer
- **qa-engineer**: qa-engineer
- **researcher**: researcher
- **reviewer**: reviewer
- **security-engineer**: security-engineer
- **security-reviewer**: security-reviewer
- **tdd-guide**: tdd-guide

## Scope

These instructions are project-scoped. Rules in `rules/` provide always-on behavioral constraints. Skills in `skills/` are on-demand procedures invoked explicitly.