Review uncommitted changes by spawning a subagent to look for bugs and assess if the approach is principled or hacky. Use before committing to get a code review.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add nmamano/isomux --skill subagent-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Subagent Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nmamano-subagent-review)More formats (shields.io, HTML) on the badges page.
---
name: subagent-review
description: Review uncommitted changes by spawning a subagent to look for bugs and assess if the approach is principled or hacky. Use before committing to get a code review.
---
Spawn a subagent (smartest model available) to review the diff of uncommitted changes (both staged and unstaged). Explain to the subagent only the goal of the changes, not the rationale for the approach chosen. Ask the subagent to look for bugs and analyze if the changes are principled or hacky. It must either approve the changes for commit or surface a list of blockers, plus any smaller nits it noticed along the way. Let the user see the feedback before committing.
Then fix what came back - nits as well as blockers. Judge each point on whether acting on it makes the change better, not on whether it stands between you and the commit: the goal is quality, not reaching the finish line. If you think a point is wrong, say so and explain why rather than skipping it silently.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
