Install a full engineering team into your AI agent. 7 SDLC roles · 105+ skills · 18 areas — Claude Code, opencode, Cursor, Codex, kilocode, antigravity, Gemini.
This repository also configures its own agents. See what agent-guides tells them →
Agent Claude Code
Use this agent for feature implementation, bug fixes, writing tests, and code delivery. Invoke after the team-lead has produced the implementation plan. This agent writes production code, maintains test coverage, and hands off to qa with evidence.
Agent Claude Code
Use this agent for CI/CD pipelines, infrastructure-as-code, deployment automation, container configuration, secrets management, and observability setup. Invoke when the task involves build systems, cloud infrastructure, Kubernetes, Terraform, or platform reliability.
Agent Claude Code
Use this agent for delivery planning, milestone tracking, dependency management, risk registers, and stakeholder status updates. Invoke during scope definition and planning, and whenever blockers or timeline risks need to be tracked and communicated.
Agent Claude Code
Main-session agent that defines scope, writes acceptance criteria, coordinates the SDLC role subagents in order, and makes final acceptance decisions. Run it as the main session (claude --agent product-owner or the agent setting); subagents cannot start other subagents.
Agent Claude Code
Use this agent for quality verification, test strategy, defect classification, and release go/no-go decisions. Invoke after the developer delivers an increment. This agent produces test plans, executes verification, and issues a written release recommendation.
Agent Claude Code
Use this agent for technical strategy, architecture decisions, code review, and quality gates. Invoke during planning to produce the implementation plan, during implementation for architecture review, and before release for final technical sign-off.
Agent Claude Code
Use this agent for system analysis: requirements, user and system scenarios, API/data contracts, testable acceptance criteria, and UX states. Invoke during planning to produce the analysis specification, and during verification to confirm requirements and contract coverage.
Agent Claude Code
Read-only post-task instruction effectiveness review with evidence-backed compact recommendations.
Agent Claude Code
Read-only post-task documentation and memory hygiene review with compact recommendations; never writes memory.
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: