ClaudeSuperPower

architecture-critic

Subagent

Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.

When Claude delegates to this

Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.

Model unspecified

No model pin — runs on your session's model.

Default effort

No reasoning budget declared.

Separate context

Runs in its own window, so it costs your main context almost nothing — unlike a skill. Scoped to 4 tools.

Its system prompt

57 lines

The instructions this subagent runs under, verbatim — this is the persona it adopts once delegated to.

Shipped by 1 plugin

Installing any of these installs this subagent.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Run shell commands

Declares Bash

~44 tokens of context used while enabled, before you invoke anything

All declared tools (4)
BashGlobGrepRead

Trust

94/100 · Excellent

1 factor scored below maximum

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just subagents.