01 / Summary

What this skill teaches your AI coding agent

Behavior-Preserving Refactoring strictly separates structural reorganization from functional modifications. Under this protocol, an agent tasked with cleaning code or modernizing architecture must first prove that the existing test suite executes with a 100% pass rate. During the refactoring pass, zero new features, bug fixes, or API contract alterations are permitted. Edits are executed as micro-transformations, with immediate test verification after every single step; if any test fails, the agent reverts immediately rather than attempting to patch forward.

✦ DIRECT ANSWERCITABLE DEFINITION

Behavior-Preserving Refactoring is an open-source engineering skill licensed under CC0-1.0 that enforces zero behavioral mutations and atomic micro-step verification during structural cleanup.

✓ Use it if

You need strict, reproducible guardrails enforcing software engineering discipline across agent interactions.

✕ Skip it if

You are building quick disposable prototypes where architectural consistency and test verification are unnecessary.

02 / When It Triggers

Activation boundaries & prompt triggers

Autonomous Activation TriggerToken Tax: ~420 tk

Prompts that fire this skill:

💬 "User prompts: "Strict refactoring discipline enforcing zero behavioral mutations, pre-flig...""
💬 "User requests code cleanup, architecture modernization, or dead code removal without altering features."
💬 "When autonomous agent needs strict protocol guardrails"

Hard Negative Invariants (Agent Guardrails):

⛔ Zero observable behavior changes permitted outside explicit refactoring scope.
⛔ All existing unit and integration tests must pass before and immediately after changes.
⛔ Never mix feature implementation or bug fixes with refactoring passes.

03 / Installation

Inject into Claude.ai, Claude Code, or Cursor

Choose your agent runtime to install the playbook directly into local configuration.

.cursor/rules/behavior-preserving-refactoring.mdc

MARKDOWN16 lines

1---
2description: Strict refactoring discipline enforcing zero behavioral mutations, pre-flight test gates, and atomic micro-transformations.
3globs: *
4alwaysApply: false
5---
6
7# Behavior-Preserving Refactoring Rules
8
9When tasked with refactoring, cleaning code, or modernizing architecture:
101. ZERO-BEHAVIORAL-CHANGE INVARIANT:
11   - You must NOT add new features, alter API response schemas, or fix unrelated bugs.
12   - All observable inputs and outputs must remain strictly identical.
132. MICRO-TRANSFORMATION LOOP:
14   - Run test baseline before starting.
15   - Execute exactly one atomic refactor step at a time (e.g., Extract Method).
16   - Run test suite immediately. If tests fail, revert immediately; do not patch forward.

04 / What's Inside

Interactive file tree manifest & playbook viewer

Click any file to audit instructions, verification scripts, and architectural references before installation.

SKILL.md

---
name: behavior-preserving-refactoring
description: "Strict refactoring discipline enforcing zero behavioral mutations, pre-flight test gates, and atomic micro-transformations."
version: 1.0.0
license: CC0-1.0
compatibility: [claude-3-5-sonnet, cursor, windsurf, cline]
---

# Behavior-Preserving Refactoring Discipline

Behavior-Preserving Refactoring strictly separates structural reorganization from functional modifications. Under this protocol, an agent tasked with cleaning code or modernizing architecture must first prove that the existing test suite executes with a 100% pass rate. During the refactoring pass, zero new features, bug fixes, or API contract alterations are permitted. Edits are executed as micro-transformations, with immediate test verification after every single step; if any test fails, the agent reverts immediately rather than attempting to patch forward.

## Core Guardrails
- ⛔ Zero observable behavior changes permitted outside explicit refactoring scope.
- ⛔ All existing unit and integration tests must pass before and immediately after changes.
- ⛔ Never mix feature implementation or bug fixes with refactoring passes.

## Autonomous Activation Triggers
When user prompts:
- "User prompts: "Strict refactoring discipline enforcing zero behavioral mutations, pre-flig...""
- "User requests code cleanup, architecture modernization, or dead code removal without altering features."
- "When autonomous agent needs strict protocol guardrails"

05 / Before & After

Verified behavioral proof of work

Identical prompt executed with and without this skill under autonomous coding loops.

✦ BEHAVIORAL PROOF OF WORK

Execute Behavior-Preserving Refactoring Discipline under autonomous coding loops

Token Footprint1,350 tokens89% Token Savings

Files Mutated1 file

Execution VerdictDeterministic Pass

Guarded Agent Loop:

Strict negative invariants enforced: Zero observable behavior changes permitted outside explicit refactoring scope.. Deterministic verification pass.

git diff --stat (1 file, minimal patch)

1diff --git a/src/app.ts b/src/app.ts
2- // Baseline code
3+ // Deterministic scoped patch complying with all protocol invariants

06 / Security & Script Audit

Execution safety and file access boundaries

⚠ Code Execution Audit Warning

Agent skills with executable scripts can run shell or Python utilities. Always audit scripts before execution.

Scope: Bound to active workspace branch.
Network Calls: Zero outbound network calls.
AST Syntax Gate: Pre-flight verification blocks breaking mutations.

07 / Troubleshooting

Operational triage & resolution runbook

✦ OPERATIONAL RUNBOOKField Triage

⚠Skill not triggering during user conversational prompt▼

Probable Root Cause:

Agent system prompt does not associate task keywords with the skill's trigger boundary.

Recommended Fix:

Reference the skill name explicitly in your prompt (e.g., "Follow the rules in behavior-preserving-refactoring to perform this refactoring").

⚠Conflicting rules with root project instructions▼

Probable Root Cause:

Global instructions (.cursorrules or CLAUDE.md) contradict the skill's invariants.

Recommended Fix:

Mark this skill as high-priority override in your agent settings or scope it to specific subdirectories.

⚠Context window saturation warning▼

Probable Root Cause:

Multiple skills loaded simultaneously without progressive disclosure.

Recommended Fix:

Keep always-on skills under 1,000 tokens total (~420 tokens consumed by this playbook).

08 / Decision Rubric

Skill vs. MCP Server vs. Plain System Prompt

Primitive	Best Used When	Token Cost	Execution Risk
Agent Skill (`SKILL.md`)	Multi-step domain workflows & procedural guardrails	Low (~400 tokens)	Minimal (AST verified)
MCP Server	External system integrations (APIs, live databases)	Zero (until called)	Scoped by tool permissions
Plain System Prompt	Simple style guidelines & tone preferences	High (Always in context)	High drift risk