subagent-driven-developmentlisted

# Subagent-Driven Development Execute an implementation plan by giving each task a focused implementation agent, then running two review gates before moving on. Core rule: the main session coordinates. Agents implement or review bounded work. The main session integrates, verifies, and decides when to proceed. ## When To Use Use this skill when: - An implementation plan already exists. - The plan has checkbox tasks or similarly bounded steps. - Tasks can be assigned with clear ownership. - The current runtime has subagent support, or the main session can follow the same task discipline sequentially. If there is no plan yet, use `workbench:writing-plans` first. If implementation is starting, use `workbench:test-driven-development` before writing production code. ## Task Loop For each plan task: 1. Paste the task text into the agent prompt. 2. Define ownership: files, directories, or behavior the agent may change. 3. Include acceptance criteria and verification commands. 4. Tell the agent it is not alone in the codebase and must not revert edits made by others. 5. Wait for the implementation agent to return. 6. Run the spec compliance reviewer. 7. Fix any spec gaps and re-review. 8. Run the code quality reviewer. 9. Fix any quality issues and re-review. 10. Mark the task complete only after both review gates pass. ## Two review gates Spec compliance reviewer: - Confirms the implementation matches the plan and spec. - Flags missing requested behavior. - Flags extra be