executing-plans

Executes written implementation plans task-by-task with verification checkpoints and coding-convention reviews.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/epicodic/drift --skill executing-plans-epicodic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/epicodic/drift/tree/main/.agents/skills/executing-plans
Command: npx skills add https://github.com/epicodic/drift --skill executing-plans-epicodic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a written implementation plan into working code often drifts off track: steps get skipped, verifications are forgotten, and coding conventions are ignored. This Skill enforces a disciplined execution loop so every task in the plan is completed, verified, and checked against project conventions. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with you before writing any code. - Task-by-Task Execution: Marks each task in progress, follows its steps exactly, runs the specified verifications, and marks it completed only after checks pass. - Mandatory Convention Checklist: After each task, re-reads docs/coding-conventions.md, confirms naming and style rules, and re-runs verification commands. - Use Case: You have a multi-task implementation plan written in a previous session. Hand it to the agent and it executes every task in order, runs the full test suite at the end, and stops to ask for help whenever it hits a blocker instead of guessing. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-x.md, executing each task with its verifications and reporting when complete.

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 agent?▼

Provide the plan file and invoke the executing-plans skill. The agent reviews the plan critically, raises concerns before starting, then executes each task in order with its specified verifications, reporting completion after the full test suite passes.

What happens when a plan step fails verification?▼

The agent stops executing immediately rather than guessing. It treats blockers such as failing tests, missing dependencies, or unclear instructions as signals to ask you for clarification before continuing.

Does this skill work without subagent support?▼

Yes, it works in a single session, but the skill notes that quality is significantly higher on platforms with subagent support such as Claude Code or Codex, where subagent-driven-development is recommended instead.

How are coding conventions enforced during plan execution?▼

After each task, the agent runs a mandatory follow-up checklist: it re-reads docs/coding-conventions.md, confirms naming and style rules for all changed symbols, and re-runs verification commands before marking the task completed.

When should I not use the executing-plans skill?▼

Avoid it when no written plan exists yet; use the writing-plans skill first to create one. Also do not start implementation on the main or master branch without explicit user consent.