Stats
Actions
Tags
From m
Task implementation workflow for the /m:dev command. Provides two execution modes: single-task mode (7-step workflow for one task at a time) and multi-task mode (wave-based orchestration with parallel subagents for feature groups, ranges, and use cases).
How this skill is triggered — by the user, by Claude, or both
Slash command
/m:dev-workflowThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execution modes for implementing tasks from a feature's tasks.md file.
Execution modes for implementing tasks from a feature's tasks.md file.
| Mode | Trigger | Description |
|---|---|---|
| Single-task | 1 pending leaf task selected | Sequential 7-step workflow: gather context, clarify, plan, code, test, run tests, quality gate |
| Multi-task | 2+ pending leaf tasks selected | Wave-based orchestration: plan all tasks upfront, execute in dependency-ordered waves with parallel subagents |
| File | Purpose |
|---|---|
| references/single-task-mode.md | Full single-task workflow (Steps 1-7, quality gate with 4 parallel agents) |
| references/multi-task-mode.md | Multi-task orchestration (wave construction, parallel execution, session state) |
npx claudepluginhub molcajeteai/plugin --plugin mImplements features from tasks.json using test-driven development: writes failing tests, makes them pass, refactors, gates, and commits per task. Stack-agnostic command detection.
Orchestrates multi-task implementations by dispatching fresh subagents per task with two-stage review. Use for plans with 5+ tasks or multi-file changes; avoid for small fixes.
Use when executing implementation plans with independent tasks in the current session