Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Agent
Part of turbocharge
Implements tasks following TDD. Use proactively when a plan task needs implementation. Builds features methodically: asks questions → implements with tests → self-reviews → commits. Always externalizes decisions to files. Use for any discrete coding task.
Agent
Part of turbocharge
Senior holistic reviewer for pre-merge assessment. Reviews entire git diff against the original plan for architecture alignment, design quality, and production readiness. Run ONCE after ALL tasks complete, not per-task. Reports merge readiness with reasoning.
Agent
Part of turbocharge
Creates detailed implementation plans with bite-sized tasks. Breaks work into 2-5 minute tasks with exact file paths, complete code, and verification commands. Use when requirements are clear and need systematic task breakdown.
Agent
Part of turbocharge
Deep codebase exploration and context gathering. Use proactively when understanding existing code, finding patterns, investigating architecture, or gathering context before planning. Fast, read-only, runs in background by default.
Agent
Part of turbocharge
Reviews a single task's diff once and emits two verdicts: Spec compliance and Quality. Use proactively after builder completes a task in --reviewed mode. Reads the actual diff — does NOT trust builder reports. Replaces the former spec-reviewer + quality-reviewer pair (one spawn, one diff-load).
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: