Skip to main content

Let Copilot argue with you: the /spar slash command

As developer or architect, you make a lot of design decisions every day. You picked Redis for caching, or REST over GraphQL, ... . You move on after your decision was made, but in the back of your head a voice keeps asking "should I bother a colleague and ask for a second opinion?", "what if I forgot something?", "is this really the right choice?"

The GitHub Copilot app can help you out with a (new) slash command: /spar.

What /spar actually does

/spar switches Copilot from "help me build this" to "convince me this is a bad idea." Instead of accepting your plan and generating code, it starts poking at your assumptions, asks about edge cases, and points out tradeoffs you may have skipped past.

Remark: this is different from /plan, which helps you break a task down. /spar assumes you already have a plan and wants to stress-test it before you commit.

How to use it

Type /spar in the chat composer, followed by whatever you want challenged. A few examples from the documentation:

Validating an architecture choice:

/spar I'm planning to use Redis as a caching layer for our product API. Challenge my approach and point out any scalability or consistency concerns I may have missed.

Comparing implementation options:

/spar Help me decide between REST and GraphQL for a customer-facing API. Ask questions, challenge my assumptions, and recommend which approach fits best for an app with mobile clients.

Reviewing a migration plan:

/spar I'm migrating our database to a new managed service with minimal downtime. Poke holes in my migration plan and identify any risks or edge cases I should account for.

Or challenging a performance optimization you're about to ship:

/spar I'm planning to lazy load most of the components on my site to improve initial load time. Critique my approach and tell me where it could hurt user experience or introduce unnecessary complexity.

Tip: the more specific your prompt, the sharper the pushback. "Challenge my caching strategy" gets you generic caveats. Naming the actual tradeoff you're unsure about (invalidation strategy, consistency, scalability) gets you a real conversation.

Where it fits in your workflow

/spar lives in the GitHub Copilot app, not the CLI or VS Code chat — it's one of the app-specific slash commands built around the multi-session workflow, alongside /plan, /autopilot, /rubber-duck, and /orchestrate. A reasonable flow looks like: /plan to break the work down, /spar to pressure-test the plan before touching code, then /autopilot to implement it.

How does this compare to /grill-me?

If you've been following the skills ecosystem, Matt Pocock's /grill-me skill (one I can really recommend) sounds like it's doing the same thing. It isn't, and the difference is worth understanding before you reach for either.

/spar assumes you already have a decision or approach and wants to break it. You feed it something concrete, "I'm using Redis for caching" , and it argues back. It's an adversary for a plan you've already formed.

/grill-me assumes you don't have a decision yet. It takes a loose idea and interviews you in rounds until you can commit to something. There's no plan to attack yet. It's trying to force one out of you by asking questions, one frontier at a time, so you're never asked something that depends on an answer you haven't given.

A few more differences:

  • Stance: /spar is a critic. /grill-me is an interviewer.
  • Input: /spar wants a stated approach to attack. /grill-me wants only a vague direction. Precision is the output, not the input.
  • State: /grill-me is explicitly stateless. No files, no workspace, nothing left behind except a sharper idea in your head. /spar runs inside a session/workspace in the Copilot app, tied to whatever project context you're in.
  • Failure mode: with /spar, the risk is you dismiss the pushback and move on unchanged. With /grill-me, the documented risk is passivity. Answering "agreed, agreed, agreed" for forty questions and walking away with a plan the agent wrote and you nodded at.

Remark: Maybe the more interesting parallel isn't /spar vs /grill-me/it's /spar vs /rubber-duck. /rubber-duck also uses a second model to independently critique work you've already done, which is closer to what /grill-me is doing conceptually than /spar is. /spar argues with you live in the same conversation; /rubber-duck and /grill-me-style interviews both bring a more independent, structured second pass.

If I had to place them on one axis: /grill-me operates before you have a plan, /plan helps you build one, /spar challenges it once you do, and /rubber-duck gives it a final independent look before you ship.

It won't catch everything. It's still Copilot, arguing with itself through your keyboard. But having it explicitly voice the "have we thought about what happens when this goes wrong" question, before a teammate has to, is a simple, useful trick.

More information

Labels:

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
Read more

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...
Read more

The role of ActivitySource in OpenTelemetry for .NET

While doing some pair programming to integrate OpenTelemetry tracing to a .NET application, we had a discussion on how to use the ActivitySource . It looks simple. You new one up, give it a name, start an activity, done. The discussion started when we added a second ActivitySource with the exact same name in a different class. This made us wonder: "Are we duplicating traces now? Is this a memory leak? Do we need a singleton?" So we decided to dig deeper. This post is what we learned… What ActivitySource actually is ActivitySource is part of System.Diagnostics , not part of the OpenTelemetry NuGet packages. Microsoft built tracing primitives directly into the BCL, and OpenTelemetry's .NET SDK simply listens to them. This is why you can add distributed tracing to a library without taking a dependency on OpenTelemetry at all. An ActivitySource is a factory for Activity objects, and an Activity is .NET's name for what OpenTelemetry calls a span.(don’t ask m...
Read more