/upgrade

Dependency and Framework Upgrade

Bump Next/React/Node/ORM. Tests stay green.

/upgrade Next 15 → 16, keep Playwright green, rollback note

Where it installs

# .claude/commands/upgrade.md
---
description: ...
argument-hint: [package or framework and target version]
allowed-tools: Read, Grep, Glob, Skill, TodoWrite, Edit, ...
---

What it does

/upgrade is a Cursor slash command. Type it in chat to run a saved workflow: Dependency and Framework Upgrade.

Reads changelogs, bumps lockfiles, fixes breaking APIs, writes a rollback note. No feature work mixed in.

Bump Next/React/Node/ORM. Tests stay green. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /upgrade for you.

Why it exists

Founders retype the same multi-step prompt until it rots. /upgrade exists so the pipeline, all 4 steps of it, is a file in .cursor/commands, versioned with the repo.

It ships in the Engineering Kit. It is wired to Upgrade & Migration Engineer (migration-engineer), Test Automation Engineer (test-automator), and DevOps & Deployment Pro (devops-engineer). Required skills: Dependency & Framework Upgrades; Vitest Unit & Integration Testing; Strict TypeScript Standards & Type Safety.

When to use it

  • Use for planned upgrades or a CI break from a dependency.
  • Use /upgrade when you want that pipeline, not a freeform chat. If you only need one step, use a narrower command or a single agent.
  • Start a new chat. Do not run this command in a thread that just wrote marketing copy.

When not to use it

  • Do not run /upgrade as a substitute for reading the diff. The command produces files; you still gate them.
  • Do not chain it into a 40-turn chat. Fresh context is part of the design.
  • Do not run it if you have not filled CURSOR.md. The pipeline will invent a stack.

Example workflow

  1. migration-engineer reads upstream breaking changes
  2. Bump versions and lockfile
  3. Fix compile and tests
  4. Write docs/engineering/upgrade-....md

Example usage

Type this in Cursor chat: /upgrade Next 15 → 16, keep Playwright green, rollback note

The command file tells the session which agents to adopt and which skills to read. You should see phase headers, not a single dump of code.

If a phase fails its gate, stop. Do not add 'just continue'.

Example output

  • Expected artifact: docs/engineering/upgrade-....md
  • Expected artifact: package.json
  • Expected artifact: package-lock.json

Best practices

  • Keep the prompt specific. /upgrade Next 15 → 16, keep Playwright green, rollback note is the shape: object, constraint, and outcome.
  • Let the listed agents work in order: migration-engineer → test-automator → devops-engineer.
  • Save outputs in the repo. Chat-only answers evaporate.
  • Engineering commands should leave tests or an audit note, not only implementation files.

Common mistakes

  • Typing /upgrade with no object ('do the thing'). The pipeline will guess.
  • Re-running the command in the same chat after a failed gate instead of fixing the failing file.
  • Editing the command file to skip review so it 'goes faster'.
  • Skipping the Dependency & Framework Upgrades skill that the command depends on.

Frequently asked questions

  • What does /upgrade do in Cursor?
    Reads changelogs, bumps lockfiles, fixes breaking APIs, writes a rollback note. No feature work mixed in.
  • When should I run /upgrade?
    Use for planned upgrades or a CI break from a dependency.
  • What is an example /upgrade prompt?
    /upgrade Next 15 → 16, keep Playwright green, rollback note
  • Which skills does /upgrade load?
    Dependency & Framework Upgrades; Vitest Unit & Integration Testing; Strict TypeScript Standards & Type Safety
  • Is /upgrade a Cursor skill?
    No. /upgrade is a slash command you type. Skills are playbooks the agent may load. Use both: the command runs the workflow, the skills constrain how it writes.

Run /upgrade from your own repo

AgenticKit installs 47 slash commands, 46 agents, and 61 skills. One command installation.