following-plans
CommunityStop scope creep with algorithmic plan compliance.
Software Engineering#decision tree#scope management#status reporting#agent governance#plan compliance
Authorcipherstash
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents agents from rationalizing unauthorized deviations from implementation plans, eliminating expensive rework when divergences are discovered later.
Core Features & Use Cases
- Algorithmic Decision Tree: Clear boolean questions with no interpretation for when to follow plan vs report BLOCKED.
- Status Enforcement: Requires explicit STATUS reporting in every agent completion.
- Use Case: When executing Task 3 to implement JWT authentication, but discovering the existing service uses OAuth2, this Skill forces reporting BLOCKED rather than silently refactoring.
Quick Start
Embed this skill in agent prompts during plan execution to enforce compliance boundaries and prevent unauthorized architectural changes.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: following-plans Download link: https://github.com/cipherstash/cipherpowers/archive/main.zip#following-plans Please download this .zip file, extract it, and install it in the .claude/skills/ directory.