plan-implementation

Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

509 stars

Best use case

plan-implementation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

Teams using plan-implementation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/plan-implementation/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/rpikit/skills/plan-implementation/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/plan-implementation/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How plan-implementation Compares

Feature / Agentplan-implementationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Plan Implementation

## Overview

Execute approved plans with discipline. Each step follows a read-modify-verify loop. Phase checkpoints require human approval. Failures trigger investigation before proceeding.

## When to Use

- After a plan has been approved via the planning phase
- For medium and high stakes changes (low stakes can proceed inline)
- When structured execution with verification is needed

## Process

1. **Load plan** - Validate plan exists and is approved
2. **Stakes enforcement** - High: halt without plan. Medium: ask. Low: proceed.
3. **Worktree isolation** - Offer git worktree based on stakes level
4. **Execute steps** - For each: mark in-progress, locate files, read, modify, verify, mark complete
5. **Phase checkpoints** - Summarize and ask: continue, review, or pause
6. **Failure handling** - Stop immediately, investigate, propose fix, get approval for deviations
7. **Code review** - Run code-reviewer agent (APPROVE / APPROVE_WITH_NITS / REQUEST_CHANGES)
8. **Security review** - Run security-reviewer agent (halt if failed)
9. **Completion summary** - Steps completed, files changed, test status, plan location

## Key Rules

- Follow the plan strictly; deviations require explicit approval
- Verify before declaring done; run verification after each step
- Track progress visibly via plan document updates
- Read files before modifying them
- Complete code and security reviews before finishing

## Tool Use

Invoke via babysitter process: `methodologies/rpikit/rpikit-implement`

Related Skills

plan

509
from a5c-ai/babysitter

Plan a Babysitter workflow without executing the run.

plantuml-renderer

509
from a5c-ai/babysitter

Render PlantUML diagrams to various image formats with theme and styling support

MoveIt Motion Planning Skill

509
from a5c-ai/babysitter

Deep expertise in MoveIt/MoveIt2 configuration and manipulation planning

Motion Planning Skill

509
from a5c-ai/babysitter

Sampling-based and optimization-based motion planning algorithms

Grasp Planning Skill

509
from a5c-ai/babysitter

Grasp planning and execution for robotic manipulation tasks

generics-implementation

509
from a5c-ai/babysitter

Expert skill for implementing parametric polymorphism including type parameter bounds, monomorphization, type erasure, variance, higher-kinded types, and associated types.

OKR Planning

509
from a5c-ai/babysitter

Objectives and Key Results planning, tracking, and alignment capabilities

metadata-standards-implementation

509
from a5c-ai/babysitter

Apply Dublin Core, METS, MODS, and other metadata schemas for digital collections and archival materials

risk-mitigation-planning

509
from a5c-ai/babysitter

Develop comprehensive risk management plans for collections and cultural venues including disaster preparedness, security protocols, and insurance coordination

experiment-planner-doe

509
from a5c-ai/babysitter

Design of Experiments skill for systematic optimization of nanomaterial synthesis and processing

test-planning

509
from a5c-ai/babysitter

Skill for comprehensive mechanical test plan development and execution support

process-planning

509
from a5c-ai/babysitter

Skill for manufacturing process planning including operation sequencing and work instructions