From hugin-v0
Automatic semantic code review triggered after file modifications. Hook-driven skill that logs file changes via PostToolUse and runs the automatic-code-reviewer agent on Stop. Not user-invocable — triggered automatically by lifecycle hooks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hugin-v0:automatic-code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Hook-driven skill that performs semantic code review after Claude finishes modifying files.
Hook-driven skill that performs semantic code review after Claude finishes modifying files.
Write, Edit, or MultiEdit operation to /tmp/event-log-{SESSION_ID}.jsonlautomatic-code-reviewer agentrulesFile and reviews only the changed filesSettings in .claude/settings.json:
{
"automaticCodeReview": {
"enabled": true,
"fileExtensions": ["ts", "tsx"],
"rulesFile": ".claude/automatic-code-review/rules.md"
}
}
Set "enabled": false to disable for a project.
../../agents/automatic-code-reviewer.md — Review agent (model: haiku, tools: Read, Grep, Glob) — lives at plugin root agents/../../hooks/hooks.json — Hook manifest (PostToolUse + Stop) — merged into plugin root hooks/../../scripts/automatic-code-review-plugin.sh — Shell script for logging and review triggering — lives at plugin root scripts/default-rules.md — Default semantic review rules (stays with skill)npx claudepluginhub michelve/hugin-marketplace --plugin hugin-v0Whole-repo audit for over-engineering: finds dead code, unnecessary abstractions, stdlib-replaceable dependencies. Outputs ranked findings and net line/dep savings.