Product Build Gate (hplan) + 5 agent-PM lifecycle plugins — 6 plugins, 43 skills, 18 commands for PMs who decide what, why, and how to build AI agents
Plugin Claude Code
34 skills · 12 commands across 5 plugins for PMs who decide what, why, and how to build AI agents — evidence gate (hplan) → discovery → architecture → delivery → operations. Skills are consolidated via mode/check/type/step routing (e.g. prd --mode roadmap, ask-team --mode review, orchestration --pattern router), with…
Plugin Claude Code
Architect scalable, defensible AI agent systems — orchestration patterns (Sequential, Parallel, Router, Hierarchical/3-tier 계층 오케스트레이션 포함), business models, and competitive moats. Use when designing agent architecture, choosing orchestration patterns, planning memory systems, or analyzing competitive positioning.
Plugin Claude Code
Spec, build, and ship AI agents — PRD templates (prd --mode roadmap for roadmaps), instruction design, prompt engineering, sprint planning, context budget, stakeholder mapping, build-execution scaffolding (harness-design, parallel-team worktrees, build-loop), prompt-level progress tracking (velocity, estimate, blocker.
Plugin Claude Code
Discover which AI agent to build — map automation outcomes to solvable opportunities, validate assumptions, and decide build vs buy. Use when exploring agent ideas, analyzing automation opportunities, running build-or-buy analysis, or estimating agent development costs.
Plugin Claude Code
Evidence + COGS + Decision gate that runs BEFORE you commit to building. Mandatory competitor and interview evidence, executable COGS sentinel (p50/p90 margin with abuse blend), append-only Do-Not-Build exclusions registry, self-eval decision log, and multi-target handoff to Spec-Kit / Kiro / GStack / Claude Code. Use.
Plugin Claude Code
Operate and continuously improve AI agents — portfolio tiering, scorecards, weekly rollups, cross-team routing, KPI/North Star/OKR design (metrics-design), reliability measurement, cost monitoring, cohort analysis, incident response, stakeholder reporting (ops-review: exec-summary 임원 보고, weekly-update 팀 주간…