executing-plans

Executes implementation plans task by task with verification and blocker escalation.

Updated Jan 2, 2025
One-click install
npx skills add https://github.com/mcinnisd/gymbro --skill executing-plans-mcinnisd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/mcinnisd/gymbro/tree/main/.agents/skills/executing-plans
Command: npx skills add https://github.com/mcinnisd/gymbro --skill executing-plans-mcinnisd

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 silently worked around. This Skill enforces a disciplined process: load the plan, review it critically, execute every task exactly as written, and stop to ask when something is unclear. ## Core Features & Use Cases - Critical Plan Review: Reads the plan file first and raises questions or concerns with you before writing any code. - Task-by-Task Execution: Creates todos for plan items, marks each in progress, follows bite-sized steps exactly, and runs the specified verifications before marking tasks complete. - Safe Blocker Handling: Stops immediately on missing dependencies, failing tests, or unclear instructions instead of guessing, and hands off to a finishing-a-development-branch workflow when done. - Use Case: You have a multi-step refactoring plan saved as a Markdown file. Invoke this Skill to have the agent work through every task in an isolated git worktree, verify each step, and report back when the branch is ready to finish. ## Quick Start Ask the agent to use the executing-plans skill to implement the plan in your plan file, and it will review, execute, and verify 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 an implementation plan with an AI agent?

Invoke the executing-plans skill and point it at your plan file. The agent reviews the plan critically, creates todos for each task, executes the steps exactly as written, and runs the specified verifications before marking tasks complete.

What happens if a plan step fails during execution?

Execution stops immediately when a blocker is hit, such as a missing dependency, failing test, or unclear instruction. The agent asks you for clarification rather than guessing or forcing through the problem.

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. Without subagents, this skill executes the plan directly in the main session.

Can I run plan execution on the main branch?

No. The skill requires an isolated workspace, typically a git worktree, and explicitly forbids starting implementation on main or master without your explicit consent.

What happens after all plan tasks are completed?

After all tasks are verified, the skill hands off to the finishing-a-development-branch skill, which verifies tests, presents completion options, and executes your choice for wrapping up the branch.