avoid-feature-creep
waynesutton/builder-skills
Keeps changes scoped to what was asked; flags feature creep and moves extras to a suggestions list.
What is avoid-feature-creep?
This skill enforces scope discipline by ensuring every line of code traces back to the original request. Use it when a change is expanding beyond its stated problem, when a PRD grows past its problem statement, or when you need to ship the smallest version that fully answers the request.
- Identifies lines of code that don't trace back to the request (refactors, edge-case handling, second features, config options)
- Separates requested changes from suggestions so the user decides what happens next
- Provides a checklist to catch common creep patterns: 'while we're here' reasoning, adjacent refactors, generalizations, and undeclared scope
- Applies the same scope discipline to product PRDs and code changes
- Treats all stakeholders—including AI agents—the same way when evaluating out-of-scope requests
How to install avoid-feature-creep
npx skills add https://github.com/waynesutton/builder-skills --skill avoid-feature-creepHow to use avoid-feature-creep
- 1.State the scope clearly at the start of the session or in the request
- 2.As you build, collect any extras you notice but do not act on them
- 3.Before adding anything, ask: Does this solve the problem the request named? What is the smallest version that works?
- 4.Finish the ask and ship only what was requested
- 5.List all extras under a Suggestions heading (in chat or PR) or Out of scope section (in a PRD), one line each with reason
- 6.Let the user pick which suggestions to pursue next
Use cases
- A bug fix that's about to ship with a refactor of nearby code
- A small feature request where the agent wants to add error handling for cases the user hasn't hit
- A PRD that keeps growing with 'nice to have' sections that don't serve the problem statement
- A user saying 'just do what I asked' after seeing extra work in a diff
- A code review where suggestions are mixed into the change instead of listed separately
- Developers and agents who need to ship focused changes without scope creep
- Product managers writing or reviewing PRDs that keep expanding
- Teams doing code review who want to separate requested work from suggestions
- Anyone working with AI coding agents to keep their output scoped
avoid-feature-creep FAQ
Use it when a request is small and you notice the change expanding, when a PRD grows past its problem statement, or when the user explicitly says 'just do what I asked'. It's especially useful when working with AI agents that tend to add error handling, refactors, or tests without being asked.
Anything that doesn't trace back to a sentence in the original request: refactors of adjacent code, error handling for edge cases nobody hit, config options for hypothetical scenarios, second features to 'round out' the first, tests or docs for code outside the change, or generalizing a one-off into a reusable abstraction.
Yes. Suggestions are cheap to write and free to ignore. List them under Suggestions (in chat/PR) or Out of scope (in a PRD) with one-line reasons. This preserves ideas without cluttering the diff and lets the user decide what happens next.
Yes. A PRD that grows past its problem statement has the same disease as a bug fix that ships with a refactor. Reread the problem statement, cut anything that doesn't serve it, and move cut items to Out of scope with reasons. If cut items form a coherent feature, that's a second PRD, not a bigger first one.
Treat them like any other stakeholder. Catch yourself (if you are the agent) or state the scope at the start (if working with an agent). Move agent-driven extras like 'let me add error handling for edge cases' or 'you should add tests' to the suggestions list unless the user explicitly asked for them.
Full instructions (SKILL.md)
Source of truth, from waynesutton/builder-skills.
name: avoid-feature-creep description: Keeps a change scoped to what was asked. Flags extra features, refactors, and 'while we are here' edits, and moves them to a suggestions list instead of the diff. Use when a request is small and the agent is about to expand it, when a PRD grows beyond its problem statement, or when the user says 'just do what I asked'.
Avoid feature creep
The request sets the scope. Everything the diff contains should trace back to a sentence in the ask. Anything else is a suggestion, not a change.
The core rule
Build what was asked. Not what would be nice, not what a senior engineer would also do, not what the codebase "should" have. If a line of the diff cannot be justified by the request, it does not belong in the diff.
This applies to product scope and to code scope. A PRD that grows past its problem statement has the same disease as a bug fix that ships with a refactor.
Signals that creep is starting
Stop when you notice any of these:
- "While we're here" or "might as well" appears in your reasoning
- Adding a config option, flag, or parameter for a case nobody asked about
- Refactoring code adjacent to the change because it looked untidy
- Adding a second feature to make the first one feel complete
- Adding error handling for edge cases the user has never hit
- Adding tests, types, or docs for code outside the change
- Generalizing a one off into a reusable abstraction
- Copying a competitor feature without a stated user need
- A PRD section titled "Future" or "Nice to have" that keeps getting longer
- The change touches a file the request never implied
Each of these might be a good idea. None of them are in scope unless the user says so.
What to do instead
- Finish the ask. Ship the smallest change that fully answers the request.
- Collect the extras as you go. Do not act on them.
- Put them in one place at the end:
- In a chat or PR summary, under a
Suggestionsheading, one line each - In a PRD, under
Out of scopewith a one line reason - In a repo with a
prds/folder, append to the relevant PRD'sOut of scopesection
- In a chat or PR summary, under a
- Let the user pick. "The agent thought so" is not approval.
Suggestions are cheap to write and free to ignore. Unrequested code costs review time, adds bugs, and blurs what the change was for.
Stakeholders, including agents
Every feature request has a source: a PM, an exec, a user, a developer scratching an itch, or an AI coding agent. Treat them all the same way. Log the request, weigh it against the current scope, and defer it unless it solves the problem the work was started for.
AI agents are stakeholders now. They have opinions and they push. Common agent driven creep:
- "Let me also add error handling for edge cases you haven't hit yet"
- "This would be cleaner with a refactor"
- "You should probably add tests for this"
- "I added types for these additional scenarios"
If you are the agent, catch yourself doing this and move it to the suggestions list. If you are working with an agent, state the scope at the start of the session and treat its extras like any other stakeholder ask.
Before adding anything, ask:
- Does this solve the problem the request named?
- What is the smallest version that works?
- What happens if we never build it?
If the first answer is no, it goes in suggestions.
Before and after
Request: "Add a deletedAt field to tasks and hide deleted tasks from the list query."
Before, the creeping version:
- Added
deletedAtto the schema - Added a
by_user_and_deletedindex - Rewrote
listto use the index - Added
softDelete,restore, andpurgeDeletedmutations - Added a cron to purge after 30 days
- Renamed
listtolistActiveand updated three call sites - Added a
showDeletedargument "for the admin view later"
After, the scoped version:
- Added
deletedAt: v.optional(v.number())to the schema - Added the index and pointed
listat it so deleted rows never load
Summary sent with the change:
Done: deletedAt field and list query now skips deleted tasks.
Suggestions
- A softDelete mutation to set deletedAt (nothing sets it yet)
- A restore mutation
- A cron to purge rows older than 30 days
- An admin flag on list to include deleted rows
Two lines of diff answered the request. Four lines of suggestions preserved every idea. The user decides what happens next.
PRDs
A PRD earns each section by pointing back to its problem statement. When a PRD grows:
- Reread the problem statement. Cut anything that does not serve it.
- Move cut items to
Out of scopewith one reason each. - If the cut items form a coherent feature, that is a second PRD, not a bigger first one.
Checklist
- Every changed file is implied by the request
- No new config options, flags, or parameters the request did not ask for
- No refactors of adjacent code
- No second feature added to round out the first
- No tests, types, or docs added for code outside the change
- Extras are listed under
Suggestionsin the summary orOut of scopein the PRD - The summary says what was done in one line before the suggestions
- If the user said "just do what I asked", the diff contains only that
Related skills
More from waynesutton/builder-skills and the wider catalog.

convex
Agent skill from waynesutton/builder-skills.

convex-agents
Agent skill from waynesutton/builder-skills.

convex-best-practices
Agent skill from waynesutton/builder-skills.

convex-cron-jobs
Agent skill from waynesutton/builder-skills.

convex-file-storage
Agent skill from waynesutton/builder-skills.

convex-functions
Write type-safe Convex queries, mutations, and actions with validators and proper error handling.