# Implement

> Use when an approved feature plan is ready to become code - executes plan.md task by task with verification, in subagents or inline as you pick, reviews the diff recursively until no new findings survive, then refreshes the affected reference chapters.

- Skill: `gentbajko/implement` (Agent Skill)
- Install (CLI): `npx skillmds@latest add gentbajko/implement`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gentbajko/implement/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: GentBajko (https://skillmd.com/u/gentbajko)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/gentbajko/implement

---


# Capstone: implement

From this skill's base directory, read `../core/references/core.md`
and `../core/references/core-authoring.md`, then execute
`../core/references/protocols/implement.md`
exactly.

Inherit the current feature run's explicit execution choice. On a
standalone invocation, including a resume, always ask subagents or
inline and wait before prerequisite work, coding, review or refresh.

