plan-handoff

SkillAI & models

Execute an approved plan from .agents/plans/Plan.md in a fresh session. Use when handed an approved plan to implement.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the plan-handoff skill

What this skill tells your AI

The instructions your AI receives, as published by nmdra/dotfiles in .pi/agent/skills/plan-handoff/SKILL.md and read by ahel’s review.

The plan file .agents/plans/Plan.md is the source of truth — read it first.

Done when you can state the goal and the task list.

Work through the tasks in order. Update each task's checkbox (- [ ] → - [x]) in the plan file as it completes.
Each task names its files, its test seam, and its verification — follow them.
Keep the plan's decisions and scope; ask before changing either.

Done when every checkbox is ticked or every blocker has been raised.

Run typechecking regularly; run single test files regularly — follow the tdd skill for test-first tasks.
Run the full test suite once at the end.
Use /code-review before committing; commit to the current branch via the git-commiter skill.

When a task cannot be completed as written, stop and ask — do not silently improvise a different implementation.
When all tasks are done, summarize what changed and the verification results.

Advanced