executing-plans

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

Updated Jul 23, 2026
One-click install
npx skills add https://github.com/shrek-abaper/sap-nexus-agent --skill executing-plans-shrek-abaper
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/shrek-abaper/sap-nexus-agent/tree/main/.comet/skills/skills/executing-plans
Command: npx skills add https://github.com/shrek-abaper/sap-nexus-agent --skill executing-plans-shrek-abaper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often go stale or get executed inconsistently when an AI session improvises instead of following the plan. This Skill enforces disciplined execution of a pre-written plan in a separate session, with critical review up front and explicit stop conditions when blockers appear. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with the human partner before writing any code. - Task-by-Task Execution: Converts plan items into todos, marks each in progress, follows bite-sized steps exactly, and runs the specified verifications. - Defined Stop Conditions: Halts and asks for clarification on blockers, unclear instructions, or repeated verification failures instead of guessing. - Use Case: After drafting a multi-step refactoring plan in one session, hand the plan file to a fresh session and have every task executed, verified, and finished through the development-branch completion workflow. ## Quick Start Execute the implementation plan in plan.md task by task, verifying each step and stopping to ask if anything is blocked or 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?▼

Provide the plan file and instruct the assistant to load it, review it critically, and execute each task in order. Each task is marked in progress, its steps are followed exactly, and the specified verifications are run before marking it complete.

What should happen before plan execution starts?▼

The plan is read and reviewed critically first. Any questions or concerns are raised with the human partner before starting; only when there are no concerns are todos created and execution begun.

What happens when a task in the plan fails verification?▼

Execution stops immediately rather than guessing or forcing through the blocker. The assistant asks for clarification when a dependency is missing, a test fails repeatedly, or an instruction is unclear.

Can I start implementation directly on the main branch?▼

No. Implementation never starts on main or master without explicit user consent. The workflow expects an isolated workspace, typically a git worktree created or verified by the using-git-worktrees skill.

When should I use subagent-driven development instead of executing plans directly?▼

When the platform supports subagents (such as Claude Code, Codex CLI, or Copilot CLI), subagent-driven development is recommended because it produces higher-quality execution. This skill is the fallback for sessions without subagent support.