Simplify: Code Review and Cleanup
Review all changed files for reuse, quality, and efficiency. Fix any issues found.
Phase 1: Identify Changes
Run diffs (or diffs --commit HEAD when you need a specific commit baseline) to see what changed. Fallback to git diff only if diffs cannot express the needed flag/output. 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: Review Three Vectors
Review all three vectors. When the user has authorized delegation and the runtime supports it, run them concurrently with the same full diff. Otherwise review them sequentially in the current agent.
Agent 1: Code Reuse Review
For each change:
- Search for existing utilities and helpers that could replace newly written code. Use grep/search to find similar patterns elsewhere in the codebase — common locations are utility directories, shared modules, and files adjacent to the changed ones.
- Flag any new function that duplicates existing functionality. Suggest the existing function to use instead.
- Flag any inline logic that could use an existing utility — hand-rolled string manipulation, manual path handling, custom environment checks, ad-hoc type guards, and similar patterns are common candidates.
Agent 2: Code Quality Review
Review the same changes for hacky patterns:
- Redundant state: state that duplicates existing state, cached values that could be derived, observers/effects that could be direct calls
- Parameter sprawl: adding new parameters to a function instead of generalizing or restructuring existing ones
- Copy-paste with slight variation: near-duplicate code blocks that should be unified with a shared abstraction
- Leaky abstractions: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries
- Stringly-typed code: using raw strings where constants, enums (string unions), or branded types already exist in the codebase
Agent 3: Efficiency Review
Review the same changes for efficiency:
- Unnecessary work: redundant computations, repeated file reads, duplicate network/API calls, N+1 patterns
- Missed concurrency: independent operations run sequentially when they could run in parallel
- Hot-path bloat: new blocking work added to startup or per-request/per-render hot paths
- Unnecessary existence checks: pre-checking file/resource existence before operating (TOCTOU anti-pattern) — operate directly and handle the error
- Memory: unbounded data structures, missing cleanup, event listener leaks
- Overly broad operations: reading entire files when only a portion is needed, loading all items when filtering for one
Phase 3: Fix Issues
Aggregate the three reviews and fix worthwhile issues directly. If a finding is a false positive or out of scope, note it and move on.
When done, briefly summarize what was fixed (or confirm the code was already clean).
1---2name: simplify3description: Review changed code for reuse, quality, and efficiency, then fix worthwhile issues.4---56# Simplify: Code Review and Cleanup78Review all changed files for reuse, quality, and efficiency. Fix any issues found.910## Phase 1: Identify Changes1112Run `diffs` (or `diffs --commit HEAD` when you need a specific commit baseline) to see what changed. Fallback to `git diff` only if diffs cannot express the needed flag/output. If there are no git changes, review the most recently modified files that the user mentioned or that you edited earlier in this conversation.1314## Phase 2: Review Three Vectors1516Review all three vectors. When the user has authorized delegation and the runtime supports it, run them concurrently with the same full diff. Otherwise review them sequentially in the current agent.1718### Agent 1: Code Reuse Review1920For each change:21221. **Search for existing utilities and helpers** that could replace newly written code. Use grep/search to find similar patterns elsewhere in the codebase — common locations are utility directories, shared modules, and files adjacent to the changed ones.232. **Flag any new function that duplicates existing functionality.** Suggest the existing function to use instead.243. **Flag any inline logic that could use an existing utility** — hand-rolled string manipulation, manual path handling, custom environment checks, ad-hoc type guards, and similar patterns are common candidates.2526### Agent 2: Code Quality Review2728Review the same changes for hacky patterns:29301. **Redundant state**: state that duplicates existing state, cached values that could be derived, observers/effects that could be direct calls312. **Parameter sprawl**: adding new parameters to a function instead of generalizing or restructuring existing ones323. **Copy-paste with slight variation**: near-duplicate code blocks that should be unified with a shared abstraction334. **Leaky abstractions**: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries345. **Stringly-typed code**: using raw strings where constants, enums (string unions), or branded types already exist in the codebase3536### Agent 3: Efficiency Review3738Review the same changes for efficiency:39401. **Unnecessary work**: redundant computations, repeated file reads, duplicate network/API calls, N+1 patterns412. **Missed concurrency**: independent operations run sequentially when they could run in parallel423. **Hot-path bloat**: new blocking work added to startup or per-request/per-render hot paths434. **Unnecessary existence checks**: pre-checking file/resource existence before operating (TOCTOU anti-pattern) — operate directly and handle the error445. **Memory**: unbounded data structures, missing cleanup, event listener leaks456. **Overly broad operations**: reading entire files when only a portion is needed, loading all items when filtering for one4647## Phase 3: Fix Issues4849Aggregate the three reviews and fix worthwhile issues directly. If a finding is a false positive or out of scope, note it and move on.5051When done, briefly summarize what was fixed (or confirm the code was already clean).
edmundmiller