executing-plans

Executes written implementation plans step-by-step with mandatory verification evidence.

8|5|Updated Dec 30, 2025
One-click install
npx skills add https://github.com/axiomantic/spellbook --skill executing-plans-axiomantic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/axiomantic/spellbook/tree/main/skills/executing-plans
Command: npx skills add https://github.com/axiomantic/spellbook --skill executing-plans-axiomantic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams execute implementation plans exactly as written, ensuring evidence is produced and no deviations occur, so work is verifiable and traceable.

Core Features & Use Cases

  • Plan Fidelity: Follow architect-approved steps line-by-line to avoid drift.
  • Evidence Over Claims: Produce verification outputs for every completed task.
  • Blocking Over Guessing: Halt progress on uncertainty or missing inputs.
  • Review-First: Require review findings before advancing to the next phase.
  • Contextful Execution: Provide full task context to subagents to prevent information gaps.

Quick Start

Load a plan file and execute the first batch of three tasks with verification after each task.

Frequently Asked Questions about executing-plans

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

FAQPage Schema
How do I execute implementation plans without task drift?

To execute implementation plans without task drift, follow architect-approved steps line-by-line and enforce verification evidence after each task. This blocking approach halts progress on uncertainty, ensuring work remains verifiable and traceable.

What is plan-based task execution with mandatory verification?

Plan-based task execution with mandatory verification is a workflow that coordinates implementation by following authored steps exactly and producing verification outputs for every completed task. It enforces review findings before advancing to the next phase.

Does plan execution stop when missing inputs or uncertainty occurs?

Plan execution does stop when missing inputs or uncertainty occurs. The system blocks over guessing by halting progress immediately upon encountering uncertainty, enforcing strict stop conditions until clarifications or required data are provided.

Can I batch execute tasks and provide context to subagents?

You can batch execute tasks and provide context to subagents. The system supports modes for batch or subagent execution, delivering full task context to subagents to prevent information gaps during implementation.

Do I need plan documents from writing-plans to execute tasks faithfully?

You do need plan documents from writing-plans to execute tasks faithfully. The execution skill requires these architect-approved plan files as input to coordinate step-by-step implementation and produce task-level verification logs.