workflow v1.0.0 · Updated Apr 15, 2026 · by Justin Adams

Scope Discipline

Prevents Claude Code from expanding scope mid-task — no drive-by refactors, no unrelated fixes, no editorial changes cascading into renames.

Claude Code
$ curl -fsSL https://www.cendis.ai/library/skill/scope-discipline/install | sh

What it does

Constrains Claude Code to the requested task and nothing more. When the agent notices adjacent issues — outdated comments, inconsistent naming, missing error handling in unrelated code — it flags them instead of fixing them. Scope stays tight, PRs stay reviewable.

When to use it

  • In any codebase where PRs are reviewed by humans
  • When working on bug fixes that shouldn’t balloon into refactors
  • In monorepos where a change in one package can ripple across boundaries
  • When your AI agent has a habit of “improving” things you didn’t ask about

How it works

Add to your CLAUDE.md:

## Scope Discipline

Before any change that touches more than 3 files or crosses package boundaries,
stop and list the proposed scope for confirmation. Do not let editorial/copy PRs
cascade into renames, or coverage fixes into unrelated refactors. When scope
grows mid-task, pause and re-confirm rather than pressing on.

The agent will:

  1. Stay within the boundaries of the original request
  2. Flag adjacent issues as separate follow-up items instead of fixing them inline
  3. Stop and ask before expanding beyond 3 files or crossing package boundaries
  4. Keep PRs focused on a single concern

Example

Without this skill: “Fix the login error message” → agent fixes the error message, then notices the error handler uses var instead of const, refactors the error handler, updates the test file, reformats imports in 4 adjacent files, and adds JSDoc to 3 functions. PR touches 9 files.

With this skill: “Fix the login error message” → agent fixes the error message in 1 file, updates the corresponding test. Notes in the response: “I noticed the error handler could use a refactor — want me to create a separate PR for that?” PR touches 2 files.

Why it matters

Scope creep is the #1 cause of unreviewed PRs. When an AI agent touches 15 files for what should have been a 2-file fix, the reviewer either rubber-stamps it or sends it back. Neither outcome is good. Tight scope means faster reviews, cleaner git history, and easier rollbacks.