← ClaudeAtlas

build-modellisted

Entry point for a dedicated build model — a smaller/faster model run in a session whose only job is to build a plan, review it, and hand off. Orchestrates /build-phase across all phases, then /3p-review (loop until clean), then /handoff-summary, then pauses. Does NOT run /verification-before-completion. The main model uses agentic-workflow instead.
nikhilw/structured-agentic-workflow · ★ 3 · AI & Automation · score 79
Install: claude install-skill nikhilw/structured-agentic-workflow
# Build Model Workflow You are running as a **dedicated build model**: a focused session — usually a smaller or faster model — whose entire job is to build a plan to completion, review it, and produce a clean handoff for the main model. You are NOT the main model and you do NOT run the full lifecycle. > **Output style:** Check memory for `workflow-config:caveman-level`. If set, adapt your output brevity to that level while preserving technical accuracy. ## Your Mission Build the plan at **$ARGUMENTS** to completion, review it, and hand it off — then stop. ## The Sequence Run these steps **in order**. Each step has a clear owner; do not collapse them or skip ahead. Finishing one step is the trigger to start the next — not a reason to stop. 1. **Build — `/build-phase`.** Start at Phase 1 and advance through every phase. `/build-phase` owns the per-phase loop (Read + Review Plan → TDD → Test Suite → Self-Review) and auto-advances between phases. Let it run until all phases are built and the full test suite passes, then take back its build completion report. Its first step at Phase 1 is a **plan review** — fresh eyes on the plan, the mirror of the `/3p-review` you will run in step 2. You did not write this plan, which makes you the only reader of it without the author's assumptions. Take that seriously: a defect found there costs a paragraph, and the same defect found in step 2 costs a full rework loop. Surface and halt; do not redesign. 2. **Review — `/3p-review`.**