Executing Plans
A Skill for loading and executing implementation plans in batches with architect review checkpoints.
Core Principle
Batch execution with checkpoints for architect review.
The Process
Step 1: Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Batch
- Default: First 3 tasks
- Execute tasks systematically
- Follow TDD principles
- Make frequent, atomic commits
Step 3: Report and Checkpoint
- Report progress after each batch
- Wait for architect review before continuing
- Address any feedback or adjustments
Perfect for systematic plan execution with proper oversight and quality control.
Comments
No comments yet. Be the first to comment!
Related Tools
Writing Plans Skill
github.com/obra/superpowers
Create comprehensive implementation plans with bite-sized tasks assuming zero context, before touching code.
Subagent-Driven Development Skill
github.com/obra/superpowers
Execute plans by dispatching fresh subagent per task with two-stage review - spec compliance then code quality.
Brainstorming Skill
github.com/obra/superpowers
Explores user intent, requirements and design before implementation through collaborative dialogue.
Related Insights
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.
Claude Code's Next Frontier: Not Code, But Your Local Obsidian Knowledge Base
Explore how Obsidian + Claude Code transforms from a knowledge management tool into your private AI assistant. Complete guide including obsidian-skills, Claudian plugin, Claudesidian template, and best practices for achieving both data privacy and AI capabilities.
Six AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.