executing-plans

Executes written implementation plans task by task with verification checkpoints and review gates.

1|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/stefaniuk/loadout --skill executing-plans-stefaniuk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/stefaniuk/loadout/tree/main/.github/skills/executing-plans
Command: npx skills add https://github.com/stefaniuk/loadout --skill executing-plans-stefaniuk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often drift during execution: steps get skipped, verifications are ignored, and blockers are worked around instead of surfaced. This Skill enforces disciplined execution of a written plan in a separate session, with critical review up front and explicit stop conditions when things go wrong. ## Core Features & Use Cases - Critical Plan Review: Loads the plan, identifies questions or concerns, and raises them with the human partner before any code is written. - Task-by-Task Execution: Converts plan items into todos, marks each in progress, follows steps exactly, and runs the specified verifications before marking complete. - Controlled Completion and Stop Conditions: Hands off to the finishing-a-development-branch sub-skill after all tasks pass, and halts immediately on blockers, unclear instructions, or repeated verification failures instead of guessing. - Use Case: After a planning session produces an implementation plan document, start a fresh session with this Skill to execute every task in an isolated git worktree, verify each step, and finish the development branch cleanly. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-auth.md and stop if anything is unclear.

Frequently Asked Questions about executing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an implementation plan with an AI coding assistant?▼

Load the plan file, review it critically for gaps or concerns, then create todos for each task and execute them one by one. Run the verifications specified in the plan for every task before marking it complete, and stop to ask when anything is blocked or unclear.

What should I do before starting to implement a written plan?▼

Set up an isolated workspace such as a git worktree, read the full plan, and review it critically. Raise any concerns with your human partner before writing code, and never start implementation on the main or master branch without explicit consent.

When should plan execution stop instead of continuing?▼

Stop immediately when you hit a blocker such as a missing dependency, a failing test, an unclear instruction, or a critical gap in the plan. Ask for clarification rather than guessing, and return to plan review if the fundamental approach needs rethinking.

Can this skill run alongside Spec Kit workflow commands?▼

No. The skill requires the active workflow mode to be superpowers, checked via the workflow-mode status script. If the mode is speckit, switch modes first and do not mix Superpowers skills with speckit commands in the same session or worktree.

What happens after all plan tasks are completed?▼

After every task is executed and verified, the workflow hands off to the finishing-a-development-branch sub-skill. That step verifies tests, presents completion options, and executes the chosen option to close out the development branch.