executing-planslisted

# Executing Plans ## Overview Load plan, review critically, execute all tasks, report when complete. **Announce at start:** "I'm using the executing-plans skill to implement this plan." **Note:** Tell your human partner that Umbrella works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use umbrella:subagent-driven-development instead of this skill. ## The Process ### Step 1: Load and Review Plan 1. Read plan file 2. Review critically - identify any questions or concerns about the plan 3. If concerns: Raise them with your human partner before starting 4. If no concerns: Create TodoWrite and proceed ### Step 2: Execute Tasks For each task: 1. Mark as in_progress 2. Follow each step exactly (plan has bite-sized steps) 3. Run verifications as specified 4. Mark as completed ### Step 2b: Discipline Rules While You Work You are the coding agent here. These rules apply to you exactly as they apply to an implementer subagent. **Tests — minimum subset.** The unit of testing is the behavior in the contract, not the function. Write one test per behavior the plan's task describes, plus one per corner case a real caller can produce in production. If you cannot name the caller and the input that reaches a corner case, do not write the test. Pure passthroughs, constants, configuration, and branchless accessors need no test at all. No co