feat(simplify): add code cleanup plugin

Add the simplify Claude command and matching Codex skill for changed-code review across reuse, quality, and efficiency.

Register the plugin in Claude and Codex marketplace metadata.

Co-Authored-By: duyetbot <duyetbot@users.noreply.github.com>

Author: duyet

.agents/plugins/marketplace.json

@@ -124,6 +124,18 @@
       },
       "category": "Productivity"
     },
+    {
+      "name": "simplify",
+      "source": {
+        "source": "local",
+        "path": "./simplify"
+      },
+      "policy": {
+        "installation": "AVAILABLE",
+        "authentication": "ON_INSTALL"
+      },
+      "category": "Productivity"
+    },
     {
       "name": "clickhouse",
       "source": {

.claude-plugin/marketplace.json

@@ -54,6 +54,11 @@
       "source": "./fix",
       "description": "Fix issues, tests, and CI failures with intelligent problem detection and resolution. Supports Python, Node/TS, Rust, and Go projects."
     },
+    {
+      "name": "simplify",
+      "source": "./simplify",
+      "description": "Review changed code for reuse, quality, and efficiency, then simplify issues found."
+    },
     {
       "name": "prompt-engineering",
       "source": "./prompt-engineering",

marketplace.json

@@ -91,6 +91,14 @@
       "type": "command",
       "category": "productivity"
     },
+    {
+      "name": "simplify",
+      "id": "simplify@duyet-claude-plugins",
+      "description": "Review changed code for reuse, quality, and efficiency, then simplify issues found",
+      "version": "1.0.0",
+      "type": "command",
+      "category": "productivity"
+    },
     {
       "name": "clickhouse",
       "id": "clickhouse@duyet-claude-plugins",
@@ -126,7 +134,7 @@
   ],
   "metadata": {
     "lastUpdated": "2026-03-05",
-    "totalPlugins": 14,
+    "totalPlugins": 15,
     "categories": ["agents", "git", "design", "productivity", "ui", "docs", "database", "monitoring", "ml"]
   }
 }

simplify/.claude-plugin/plugin.json

@@ -0,0 +1,8 @@
+{
+  "name": "simplify",
+  "description": "Review changed code for reuse, quality, and efficiency, then simplify issues found",
+  "version": "1.0.0",
+  "author": {
+    "name": "duyet"
+  }
+}

simplify/.codex-plugin/plugin.json

@@ -0,0 +1,19 @@
+{
+  "name": "simplify",
+  "version": "1.0.0",
+  "description": "Review changed code for reuse, quality, and efficiency, then simplify issues found",
+  "author": {
+    "name": "duyet"
+  },
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "Simplify",
+    "shortDescription": "Review changed code for reuse, quality, and efficiency, then simplify issues found",
+    "developerName": "duyet",
+    "category": "Productivity",
+    "capabilities": [
+      "Skill",
+      "Command"
+    ]
+  }
+}

simplify/README.md

@@ -0,0 +1,33 @@
+# Simplify Plugin
+
+Review changed code for reuse, quality, and efficiency, then simplify issues found.
+
+## Installation
+
+```bash
+/plugin install simplify@duyet-claude-plugins
+```
+
+## Usage
+
+```bash
+/simplify:simplify
+```
+
+The command inspects the current diff, reviews it from three angles, fixes actionable issues, and summarizes what changed.
+
+## Structure
+
+```
+simplify/
+├── .claude-plugin/
+│   └── plugin.json
+├── .codex-plugin/
+│   └── plugin.json
+├── commands/
+│   └── simplify.md
+├── skills/
+│   └── simplify/
+│       └── SKILL.md
+└── README.md
+```

simplify/commands/simplify.md

@@ -0,0 +1,55 @@
+---
+allowed-tools: [Read, Bash, Glob, Grep, TodoWrite, Edit, MultiEdit, Write, Task]
+description: "Review changed code for reuse, quality, and efficiency, then simplify issues found"
+---
+
+# /simplify:simplify - Code Review and Cleanup
+
+Review all changed files for reuse, quality, and efficiency. Fix any issues found.
+
+## Phase 1: Identify Changes
+
+Run `git diff` or `git diff HEAD` if there are staged changes to see what changed. If there are no git changes, review the most recently modified files that the user mentioned or that you edited earlier in this conversation.
+
+## Phase 2: Launch Three Review Agents in Parallel
+
+Use the Task tool to launch all three agents concurrently in a single message. Pass each agent the full diff so it has the complete context.
+
+### Agent 1: Code Reuse Review
+
+For each change:
+
+1. Search for existing utilities and helpers that could replace newly written code. Look for similar patterns elsewhere in the codebase. Common locations are utility directories, shared modules, and files adjacent to the changed ones.
+2. Flag any new function that duplicates existing functionality. Suggest the existing function to use instead.
+3. Flag any inline logic that could use an existing utility, such as hand-rolled string manipulation, manual path handling, custom environment checks, ad-hoc type guards, and similar patterns.
+
+### Agent 2: Code Quality Review
+
+Review the same changes for hacky patterns:
+
+1. Redundant state: state that duplicates existing state, cached values that could be derived, observers/effects that could be direct calls
+2. Parameter sprawl: adding new parameters to a function instead of generalizing or restructuring existing ones
+3. Copy-paste with slight variation: near-duplicate code blocks that should be unified with a shared abstraction
+4. Leaky abstractions: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries
+5. Stringly-typed code: using raw strings where constants, enums, string unions, or branded types already exist in the codebase
+6. Unnecessary JSX nesting: wrapper Boxes/elements that add no layout value. Check if inner component props such as `flexShrink` or `alignItems` already provide the needed behavior.
+7. Nested conditionals: ternary chains, nested if/else, or nested switch blocks 3+ levels deep. Flatten with early returns, guard clauses, a lookup table, or an if/else-if cascade.
+8. Unnecessary comments: comments explaining what the code does, narrating the change, or referencing the task/caller. Delete those. Keep only non-obvious why comments for hidden constraints, subtle invariants, or workarounds.
+
+### Agent 3: Efficiency Review
+
+Review the same changes for efficiency:
+
+1. Unnecessary work: redundant computations, repeated file reads, duplicate network/API calls, N+1 patterns
+2. Missed concurrency: independent operations run sequentially when they could run in parallel
+3. Hot-path bloat: new blocking work added to startup or per-request/per-render hot paths
+4. Recurring no-op updates: state/store updates inside polling loops, intervals, or event handlers that fire unconditionally. Add a change-detection guard so downstream consumers are not notified when nothing changed. If a wrapper function takes an updater/reducer callback, verify it honors same-reference returns or the local no-change signal.
+5. Unnecessary existence checks: pre-checking file/resource existence before operating. Operate directly and handle the error.
+6. Memory: unbounded data structures, missing cleanup, event listener leaks
+7. Overly broad operations: reading entire files when only a portion is needed, loading all items when filtering for one
+
+## Phase 3: Fix Issues
+
+Wait for all three agents to complete. Aggregate their findings and fix each issue directly. If a finding is a false positive or not worth addressing, note it and move on.
+
+When done, briefly summarize what was fixed, or confirm the code was already clean.

simplify/skills/simplify/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: simplify
+description: Use when reviewing changed code for reuse, quality, and efficiency, then directly simplifying or cleaning up issues found.
+---
+
+# Simplify: Code Review and Cleanup
+
+Review all changed files for reuse, quality, and efficiency. Fix any issues found.
+
+## Phase 1: Identify Changes
+
+Run `git diff`, or `git diff HEAD` if there are staged changes. If there are no git changes, review the most recently modified files that the user mentioned or that were edited earlier in the conversation.
+
+## Phase 2: Review in Three Passes
+
+If the active Codex instructions allow subagents, launch three review agents in parallel and pass each one the full diff. If subagents are unavailable or not allowed, perform the same three passes locally.
+
+### Pass 1: Code Reuse Review
+
+For each change:
+
+1. Search for existing utilities and helpers that could replace newly written code. Look for similar patterns elsewhere in the codebase. Common locations are utility directories, shared modules, and files adjacent to the changed ones.
+2. Flag any new function that duplicates existing functionality. Suggest the existing function to use instead.
+3. Flag any inline logic that could use an existing utility, such as hand-rolled string manipulation, manual path handling, custom environment checks, ad-hoc type guards, and similar patterns.
+
+### Pass 2: Code Quality Review
+
+Review the same changes for hacky patterns:
+
+1. Redundant state: state that duplicates existing state, cached values that could be derived, observers/effects that could be direct calls
+2. Parameter sprawl: adding new parameters to a function instead of generalizing or restructuring existing ones
+3. Copy-paste with slight variation: near-duplicate code blocks that should be unified with a shared abstraction
+4. Leaky abstractions: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries
+5. Stringly-typed code: using raw strings where constants, enums, string unions, or branded types already exist in the codebase
+6. Unnecessary JSX nesting: wrapper Boxes/elements that add no layout value. Check if inner component props such as `flexShrink` or `alignItems` already provide the needed behavior.
+7. Nested conditionals: ternary chains, nested if/else, or nested switch blocks 3+ levels deep. Flatten with early returns, guard clauses, a lookup table, or an if/else-if cascade.
+8. Unnecessary comments: comments explaining what the code does, narrating the change, or referencing the task/caller. Delete those. Keep only non-obvious why comments for hidden constraints, subtle invariants, or workarounds.
+
+### Pass 3: Efficiency Review
+
+Review the same changes for efficiency:
+
+1. Unnecessary work: redundant computations, repeated file reads, duplicate network/API calls, N+1 patterns
+2. Missed concurrency: independent operations run sequentially when they could run in parallel
+3. Hot-path bloat: new blocking work added to startup or per-request/per-render hot paths
+4. Recurring no-op updates: state/store updates inside polling loops, intervals, or event handlers that fire unconditionally. Add a change-detection guard so downstream consumers are not notified when nothing changed. If a wrapper function takes an updater/reducer callback, verify it honors same-reference returns or the local no-change signal.
+5. Unnecessary existence checks: pre-checking file/resource existence before operating. Operate directly and handle the error.
+6. Memory: unbounded data structures, missing cleanup, event listener leaks
+7. Overly broad operations: reading entire files when only a portion is needed, loading all items when filtering for one
+
+## Phase 3: Fix Issues
+
+Aggregate findings and fix each actionable issue directly. If a finding is a false positive or not worth addressing, note it and move on.
+
+When done, briefly summarize what was fixed, or confirm the code was already clean.