execute-plan
The execute-plan command guides developers through feature implementation by breaking down a planning document into ordered tasks, executing them interactively one at a time, and tracking progress. Use this when implementing a feature that has a corresponding markdown planning document, starting work on a defined feature branch, or resuming work on a partially completed feature to maintain context and ensure tasks are addressed systematically rather than ad-hoc.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/codeaholicguy/ai-devkit/HEAD/commands/execute-plan.md -o ~/.claude/commands/execute-plan.mdexecute-plan.md
Help me work through a feature plan one task at a time.
1. **Gather Context** — If not already provided, ask for: feature name (kebab-case, e.g., `user-authentication`), brief feature/branch description, planning doc path (default: latest matching `docs/ai/planning/YYYY-MM-DD-feature-{name}.md`; fallback `docs/ai/planning/feature-{name}.md`), and any supporting docs (design, requirements, implementation).
2. **Use Memory for Context** — Search for prior implementation notes/patterns before starting: `npx ai-devkit@latest memory search --query "<feature implementation plan>"`.
3. **Load & Present Plan** — Read the planning doc and parse task lists (headings + checkboxes). Present an ordered task queue grouped by section, with status: `todo`, `in-progress`, `done`, `blocked`.
4. **Interactive Task Execution** — For each task in order: display context and full bullet text, reference relevant design/requirements docs, offer to outline sub-steps before starting, prompt for status update (`done`, `in-progress`, `blocked`, `skipped`) with short notes after work, and if blocked record blocker and move to a "Blocked" list.
- **Reuse before writing** — grep for existing utilities/functions before adding new ones. Reuse only if it fits cleanly; don't force-fit a near-match (a small duplicate beats a wrong abstraction).
- **Breaking changes** — if all callers live in this repo and can be updated atomically, modify in place and update callers in the same change. If callers are external, public, or cross-service, add a new function and deprecate the old one (parallel change) rather than mutating the existing signature.
5. **Update Planning Doc** — After each completed or status-changed task, run `/update-planning` to keep the selected planning doc accurate.
6. **Store Reusable Knowledge** — Save reusable implementation guidance/decisions with `npx ai-devkit@latest memory store ...`.
7. **Session Summary** — Produce a summary: Completed, In Progress (with next steps), Blocked (with blockers), Skipped/Deferred, and New Tasks.
8. **Next Command Guidance** — Continue `/execute-plan` until plan completion; then run `/check-implementation`.AI DevKit · Compare implementation with design and requirements docs to ensure alignment.
AI DevKit · Pre-push code review against design docs.
AI DevKit · Scaffold feature documentation from requirements through planning.
AI DevKit · Store reusable guidance in the knowledge memory service.
AI DevKit · Review feature design for completeness.
AI DevKit · Review feature requirements for completeness.
AI DevKit · Update planning docs to reflect implementation progress.
AI DevKit · Add tests for a new feature.