Skip to content
SkillModel-led92 tokens in use

Refactoring

Martin Fowler-inspired rules for behavior-preserving refactoring in small steps, separate from feature changes.

3,324 stars on the repository MIT Licenseciembor/agent-rules-books · refactoring
npx skills add ciembor/agent-rules-books --skill refactoring
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Refactoring costs

20tokens idle
92tokens in use
4,465tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Needs attention
  • Frontmatter11/15
  • Structure0/25
  • Examples0/15
  • Output2/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity44
  • Maintenance72
  • Community52
  • Maturity28
  • Momentum40

This skill loads a compact rule set inspired by Martin Fowler’s Refactoring. It tells a coding agent to preserve observable behavior, work in small buildable steps and keep structural edits apart from feature work.

It covers preparatory and follow-up refactoring around a change, safety nets such as characterization tests, and a stop condition before cleanup turns into a rewrite.

What You Get

  • A mini rule set with decision rules, trigger rules and a closing checklist for refactoring work
  • A nano version for tight context budgets and a full version for reference
  • A skill description that makes the agent load the rules for cleanup and bug-fix tasks

Common Use Cases

  • Reshaping local structure before adding a feature, then cleaning up after it
  • Writing characterization tests before touching unclear code
  • Splitting a patch that renames, moves and changes logic together
  • Replacing repeated conditionals with a table or polymorphism only when the variation is real

What Makes It Unique

It ties refactoring to the task in hand: what blocks the requested change gets treated, and the next smell is left for later. The agent is told never to delete a failing test to finish cleanup and to keep patch intent reviewable. A companion set in the repository takes the same topic from the Refactoring.Guru smell catalog.

Under The Hood

The skill is a SKILL.md with a name and description, plus Markdown files holding the mini, nano and full versions of the rules. The SKILL.md tells the agent to read the mini file before design or code decisions and the full file only for harder tradeoffs. It contains no scripts. It does not fetch web pages, call APIs, run commands or write files; the agent only reads the rule text.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers