PWV Portfolio Feed

/pr-comments does something equally important: it fetches all comments (both issue comments and inline review comments) and displays them in your terminal. then it pre-populates the next action to help you: "fix all review comments".

- potential edge cases you might have missed
- whether test coverage is adequate
- security implications of the changes

- returns a structured review with a quality score (1-5)
- respects your project's learned conventions (your taste of code/review)

it's semantic agentic analysis. it understands:
- whether your abstractions make sense
- if you're following project patterns

/review gives you structured code analysis without leaving the terminal. it:
- auto-detects your PR from your current branch (no manual lookup)
- fetches the diff and metadata via gh CLI
- analyzes the changes for quality, correctness, style, performance, security

each switch costs you. research shows context switching can cost 15-25 minutes of productive time per switch. if you do 3-4 reviews a day, that's an hour+ of pure overhead.

command code's /review and /pr-comments commands eliminate this entirely.

1. leave your terminal
2. navigate to github
3. parse the diff (often poorly formatted)
4. read comments from several agents/humans
5. come back to your terminal
6. context-switch back into the problem

# auto-detects PR from branch

$ cmd
/review 42
# explicit PR number

$ cmd
/pr-comments
# Fetch all PR comments for current branch

the problem with code review is that it's fundamentally a context-switching tax.

you're deep in the flow of your work, and suddenly you need to:

Introducing Taste Aware Agentic Review /𝚛𝚎𝚟𝚒𝚎𝚠
by Command Code

Stop paying the code review tax. 

Code review in your terminal. Slash commands that turn GitHub PRs into structured feedback. No browser, no context switching, no friction.

$ cmd
/review

$ cmd
/review

Coding agents are reshaping how we build software. Here is a simple way to use them well:

1. Start with a clear goal
2. Give context and constraints
3. Review outputs and refine

The secret is taste. Guide the agent with good judgment and it will amplify your skills.

You can also bring your whole team into it.

Developers stay in control of infrastructure and production. PMs, designers, and founders can build and iterate with agents inside the same Netlify account.

More people can build. The right people stay accountable.

And when you run the agent again, it modifies the same project in place.

Not a new generation. Not starting over. The same codebase, same infrastructure, updated incrementally.

Momentum compounds instead of restarting.

On Netlify, that infrastructure is already there from the first prompt.

→ Serverless functions → Forms → AI Gateway (OpenAI, Anthropic, Gemini) → Identity and auth → Blob storage

No separate signups. No env vars to track down. No CORS at 2am.

Most AI builders give you a prototype. Fast start, working UI, something to show.

Then the project gets real: auth, APIs, storage, model access. And suddenly you're looking at a migration before you can ship the actual thing.

The gap isn't in the generation. It's in everything that comes after.

Join the Vite ecosystem tomorrow to celebrate the Vite Team 5th Anniversary by rewatching together the Vite Documentary! Let's remember the stories of the people who connected to extend together our shared commons. And stay at 3:45 PM UTC to participate in the live stage after the movie 💜