convex-agents
Builds AI agents on the Convex agent component: threads, messages, tools that call queries and mutations, streaming, RAG with…
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
$ npx -y skills add waynesutton/builder-skills --skill avoid-feature-creep --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/avoid-feature-creepContext preview
The summary Claude sees to decide when to auto-load this skill.
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
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'.
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.
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.
Stop when you notice any of these:
Each of these might be a good idea. None of them are in scope unless the user says so.
1. Finish the ask. Ship the smallest change that fully answers the request. 2. Collect the extras as you go. Do not act on them. 3. Put them in one place at the end:
4. 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.
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:
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:
If the first answer is no, it goes in suggestions.
Request: "Add a `deletedAt` field to tasks and hide deleted tasks from the list query."
Before, the creeping version:
After, the scoped version:
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.
A PRD earns each section by pointing back to its problem statement. When a PRD grows:
Agent skills for builders shipping Convex apps. By Wayne Sutton. Seventeen skills.
Builds AI agents on the Convex agent component: threads, messages, tools that call queries and mutations, streaming, RAG with…
Production patterns for Convex apps and the rules the @convex-dev/eslint-plugin enforces: validators, indexes, idempotent…
Creates reusable Convex components with defineComponent, a clean client wrapper, their own schema, and an npm publish setup. Use…
Schedules work in Convex: cron jobs in convex/crons.ts, one off scheduled functions with runAfter and runAt, batching large jobs,…
Handles files in Convex: upload URLs, storing blobs from actions, serving with getUrl or an HTTP action, metadata from the…
Writes Convex queries, mutations, actions, and internal functions in the object form with args and returns validators, correct…