plan-changes
plan-changes is a Planning & task breakdown skill for AI agents, published by vox-deorum in the vox-deorum repository on GitHub. Skillspace rates plan-changes D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Orchestrate a thorough, independently-reviewed implementation plan for a set of changes before any code is written. Use this whenever the user wants to "plan a change", "design an approach", "figure out how to implement X", "write a plan", "think through" a feature, refactor, or migration, or asks for a well-researched plan they can review and approve. The skill explores the codebase with delegated subagents (cheaper models for simple lookups, stronger models for hard reasoning), asks as many clarifying questions as it needs, drafts a plan, has a fresh-context subagent critique it, revises, and presents the result through the plan tool for approval. Prefer this skill over planning inline whenever the change is non-trivial, spans multiple files or systems, or benefits from independent review — even if the user never says the word "plan".
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 75
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.