Spawn Your Critics - Claude Code / Cowork

This is a quick one. I took for granted that you guys already knew this. But maybe you don't? It's pretty great. In Claude Code / Cowork, have Claude spawn agents to critique your code, writing, anything. You can even define who they are. You will get a much better idea of what you've written from several points of view. I get WAY less sycophantic feedback from the agents. They will even find code problems and writing inconsistencies that default Claude wont. And they can get feisty!

For instance, you can give your Clief Notes post to Claude and say, "Spawn 5 agents that represent the Clief Notes community. They should all have strong opinions. Have them critique this post."

I gave everything above this line to Claude and then ran the agents, so they don't know THEY are the examples. haha ;)

Here's what they said:

---

Agent 1 -- The Builder:

Solid concept, but this reads like a tweet stretched into a post. You're telling us that it works without showing us how it works or what it actually looks like. Drop in a real example -- show the prompt you used, show one of the agent responses, let people see the feisty feedback you're bragging about. "Spawn 5 agents" is doing a lot of heavy lifting with zero specifics on what makes a good critic prompt versus a bad one. The idea has legs, but right now it's a teaser for a post you haven't written yet.

Agent 2 -- The Skeptic:

You're telling me agents "get feisty" and "find code problems" -- show me. One before/after example would do more than five sentences of hype. Also, "spawn 5 agents" is doing a lot of heavy lifting here -- are you prompting each one with a distinct persona, or just asking Claude to roleplay five slightly different yes-men? Because without deliberate persona design, you're just getting the same model talking to itself in different fonts. The idea is legit -- adversarial feedback loops are genuinely useful -- but this post asks me to take your word for it instead of proving it.

Agent 3 -- The Newcomer:

Solid concept, but this feels like a teaser trailer with no movie. You tell me to spawn agents to critique things -- cool, but what does that actually look like? A screenshot of the output or even just the exact prompt you used would turn this from "trust me bro" into something I can actually try tonight. Also, "spawn agents" is doing a lot of heavy lifting here -- are we talking subagents via the Agent tool, or just a creative prompt in the main thread? Those are very different things and the distinction matters.

Agent 4 -- The Philosopher:

You're describing a feature without teaching the why -- spawning critics works because you're forcing the model out of its default sycophantic completion pattern by giving it a constrained persona with permission to disagree. That's the real lesson. Also missing: how this connects to Jake's abstraction layer thinking -- these agents ARE a layer, they're a QA gate you can encode into hooks so it runs automatically, not just when you remember to ask. The "5 agents with strong opinions" example is catchy but toy-sized; show us what it looks like when this actually caught something real and saved you hours.

Agent 5 -- The Pragmatist:

Solid tip, and you're right that most people probably aren't doing this. The "spawn agents with strong opinions" angle is the real value here, not just "ask Claude to review your stuff." But this is too thin to be useful on its own. You're telling people what to do without showing them what happens. Drop in one real example with the actual agent output so people can see the difference between default Claude feedback and the critic-spawned version. Without that, it's a "trust me bro" post.

2 comments