AutoGineer
Generated banner for Executing Plans
Generated logo for Executing Plans

Executing Plans

OpenAIOfficialCreated by Jesse VincentDistributed by OpenAI

  • Skill
  • Workflow
  • Software development
  • MIT
  • No issues found
Download ZIP

From the author

Use when you have a written implementation plan to execute in a separate session with review checkpoints
— the description by Jesse Vincent

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The executing-plans skill provides a systematic approach for AI agents to carry out development tasks defined in a written plan. It emphasizes critical review, isolated workspace management, and strict adherence to verification steps. The process ensures that agents do not proceed blindly, requiring them to pause for human clarification if blockers arise or if the plan contains gaps. It integrates with other development skills to manage branches and finalize work, ensuring a disciplined execution flow.

What it does

  • Guides the agent through loading and critically reviewing a provided implementation plan.
  • Ensures work is performed in an isolated environment using git worktrees.
  • Manages task status tracking from in-progress to completion.
  • Enforces mandatory verification steps for every task in the plan.
  • Provides clear protocols for when to stop and request human intervention.
  • Coordinates with finishing-a-development-branch to wrap up work.

When to use it

  • When you have a detailed, step-by-step implementation plan ready for execution.
  • When you need to ensure that development tasks are verified and tracked systematically.
  • When working on complex changes that require a structured, checkpoint-based approach.
  • When you want to prevent guessing or unauthorized changes on main branches.

Advantages

  • Reduces errors by mandating critical review before execution begins.
  • Maintains workspace cleanliness through isolated worktrees.
  • Prevents agent drift by requiring strict adherence to defined plan steps.
  • Improves reliability by forcing verification after every task.
  • Provides a clear escalation path when blockers are encountered.

Usage examples

“I have a plan in plan.md. Please use the executing-plans skill to implement it.”
The agent will load the file, review the steps, set up a git worktree, and begin executing the tasks while reporting progress and verification results.
“I've updated the plan based on your feedback. Can you resume the executing-plans workflow?”
The agent will re-review the updated plan, identify any new concerns, and continue the execution process from the appropriate task.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/openai/executing-plans/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip executing-plans.zip -d .agents/skills

Documentation by Jesse Vincent

Executing Plans

Overview

Load plan, review critically, execute all tasks, report when complete.

Announce at start: "I'm using the executing-plans skill to implement this plan."

Note: Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in ../using-superpowers/references/). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

The Process

Step 1: Load and Review Plan

  1. Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one

  2. Read plan file

  3. Review critically - identify any questions or concerns about the plan

  4. If concerns: Raise them with your human partner before starting

  5. If no concerns: Create todos for the plan items and proceed

Step 2: Execute Tasks

For each task:

  1. Mark as in_progress

  2. Follow each step exactly (plan has bite-sized steps)

  3. Run verifications as specified

  4. Mark as completed

Step 3: Complete Development

After all tasks complete and verified:

  • Announce: "I'm using the finishing-a-development-branch skill to complete this work."

  • REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch

  • Follow that skill to verify tests, present options, execute choice

When to Stop and Ask for Help

STOP executing immediately when:

  • Hit a blocker (missing dependency, test fails, instruction unclear)

  • Plan has critical gaps preventing starting

  • You don't understand an instruction

  • Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Review (Step 1) when:

  • Partner updates the plan based on your feedback

  • Fundamental approach needs rethinking

Don't force through blockers - stop and ask.

Remember

  • Review plan critically first

  • Follow plan steps exactly

  • Don't skip verifications

  • Reference skills when plan says to

  • Stop when blocked, don't guess

  • Never start implementation on main/master branch without explicit user consent

Files

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Jesse Vincent
Publisher
OpenAI (Official)
Distributed by
OpenAI
Source
openai/plugins · plugins/superpowers/skills/executing-plans · commit d420d13
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from plugins/superpowers/LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Jesse Vincent or OpenAI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download executing-plans.zip