executing-plans

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

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/Yvesdefaria/GymLab --skill executing-plans-yvesdefaria
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/Yvesdefaria/GymLab/tree/main/.opencode/skills/executing-plans
Command: npx skills add https://github.com/Yvesdefaria/GymLab --skill executing-plans-yvesdefaria

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a written implementation plan into working code often goes wrong when steps are skipped, verifications are ignored, or blockers are guessed through. This Skill enforces a disciplined process: load the plan, review it critically, execute every task exactly as written, and stop to ask when blocked. ## Core Features & Use Cases - Critical Plan Review: Reads the plan first, raises questions or concerns with you before writing any code, and ensures an isolated workspace via git worktrees. - Structured Task Execution: Tracks each plan item as a todo, marks it in progress, follows bite-sized steps exactly, and runs the specified verifications before marking it complete. - Safe Stop Conditions: Halts immediately on blockers, unclear instructions, or repeated verification failures instead of guessing, and hands off to a finishing-a-development-branch workflow when done. - Use Case: You have a detailed markdown implementation plan for a new feature. Hand it to the agent in a fresh session, and it executes every task in order, verifies each one, and reports back when the branch is ready to finish. ## Quick Start Execute the implementation plan in docs/feature-plan.md using the executing-plans skill, reviewing it critically first and stopping 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 agent?

Provide the written 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 verifications, marking todos as it progresses.

What should an implementation plan contain before executing it?

The plan should have bite-sized tasks with exact steps and specified verifications for each. The skill reviews the plan critically first and raises questions about gaps or unclear instructions before any code is written.

What happens when plan execution hits a blocker?

Execution stops immediately when a blocker occurs, such as a missing dependency, failing test, or unclear instruction. The agent asks for clarification rather than guessing, and never forces through repeated verification failures.

Does executing-plans work with subagents?

The skill notes that if subagents are available (Claude Code, Codex CLI, Copilot CLI, Gemini CLI), the subagent-driven-development skill is recommended instead. Executing-plans is the fallback for single-session execution.

Can plan execution start directly on the main branch?

No. The skill requires an isolated workspace, typically a git worktree, and never starts implementation on main or master without explicit user consent. Completed work is handed off to a finishing-a-development-branch workflow.