Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review...
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review...
Use this skill when you need review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review...
Review changed code for reuse, quality, efficiency, and clarity issues. Use Codex sub-agents to review in parallel, but keep those sub-agents read-only: they should only inspect code and send findings back to the main agent. Only the main agent may apply high-confidence, behavior-preserving fixes.
Modes
Choose the mode from the user's request:
review-only: user asks to review, audit, or check the changes
safe-fixes: user asks to simplify, clean up, or refactor the changes
fix-and-validate: same as safe-fixes, but also run the smallest relevant validation after edits
If the user does not specify, default to:
review-only for "review", "audit", or "check"
safe-fixes for "simplify", "clean up", or "refactor"
Step 1: Determine the Scope and Diff Command
Prefer this scope order:
Files or paths explicitly named by the user
Current git changes
Files edited earlier in the current Codex turn
Most recently modified tracked files, only if the user asked for a review but there is no diff
If there is no clear scope, stop and say so briefly.
When using git changes, determine the smallest correct diff command based on the repo state:
unstaged work: git diff
staged work: git diff --cached
branch or commit comparison explicitly requested by the user: use that exact diff target
mixed staged and unstaged work: review both
Do not assume git diff HEAD is the right default when a smaller diff is available.
Before reviewing standards or applying fixes, read the repo's local instruction files and relevant project docs for the touched area. Prefer the closest applicable guidance, such as:
AGENTS.md
repo workflow docs
architecture or style docs for the touched module
Use those instructions to distinguish real issues from intentional local patterns.
Step 2: Launch Four Read-Only Review Sub-Agents in Parallel
Use Codex sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.
When spawning sub-agents:
give each sub-agent the same scope
tell each sub-agent to inspect only its assigned review role
tell each sub-agent it is operating in a read-only review pass
do not let sub-agents edit files, run apply_patch, stage changes, commit, or perform other state-mutating actions
ask for concise, structured findings only
ask each sub-agent to report file, line or symbol, problem, recommended fix, and confidence
ask each sub-agent to return findings to the main agent only; they must not implement fixes themselves
Use four review roles.
Sub-Agent 1: Code Reuse Review
Review the changes for reuse opportunities:
Search for existing helpers, utilities, or shared abstractions that already solve the same problem.
Flag duplicated functions or near-duplicate logic introduced in the change.
Flag inline logic that should call an existing helper instead of re-implementing it.
This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.
Recommended sub-agent role: explorer for broad codebase lookup, or reviewer if a stronger review pass is more useful than wide search.
Sub-Agent 2: Code Quality Review
Review the same changes for code quality issues:
Redundant state, cached values, or derived values stored unnecessarily
Parameter sprawl caused by threading new arguments through existing call chains
Copy-paste with slight variation that should become a shared abstraction
Leaky abstractions or ownership violations across module boundaries
Stringly-typed values where existing typed contracts, enums, or constants already exist
This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.
Recommended sub-agent role: reviewer
Sub-Agent 3: Efficiency Review
Review the same changes for efficiency issues:
Repeated work, duplicate reads, duplicate API calls, or unnecessary recomputation
Sequential work that could safely run concurrently
New work added to startup, render, request, or other hot paths without clear need
Pre-checks for existence when the operation itself can be attempted directly and errors handled
Memory growth, missing cleanup, or listener/subscription leaks
Overly broad reads or scans when the code only needs a subset
This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.
Recommended sub-agent role: reviewer
Sub-Agent 4: Clarity and Standards Review
Review the same changes for clarity, local standards, and balance:
Violations of local project conventions or module patterns
Unnecessary complexity, deep nesting, weak names, or redundant comments
Overly compact or clever code that reduces readability
Over-simplification that collapses separate concerns into one unclear unit
Dead code, dead abstractions, or indirection without value
This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.
Recommended sub-agent role: reviewer
Only report issues that materially improve maintainability, correctness, or cost. Do not churn code just to make it look different.
Step 3: Aggregate Findings
Wait for all review sub-agents to complete, then merge their findings.
The main agent owns this step. Treat sub-agent output as review input only, not as permission to delegate code changes back out.
Normalize findings into this shape:
File and line or nearest symbol
Category: reuse, quality, efficiency, or clarity
Why it is a problem
Recommended fix
Confidence: high, medium, or low
Discard weak, duplicative, or instruction-conflicting findings before editing.
Step 4: Fix Issues Carefully
In review-only mode, stop after reporting findings.
In safe-fixes or fix-and-validate mode:
Only the main agent applies fixes for this skill
Apply only high-confidence, behavior-preserving fixes
Skip subjective refactors that need product or architectural judgment
Preserve local patterns when they are intentional or instruction-backed
Keep edits scoped to the reviewed files unless a small adjacent change is required to complete the fix correctly
Prefer fixes like:
replacing duplicated code with an existing helper
removing redundant state or dead code
simplifying control flow without changing behavior
narrowing overly broad operations
renaming unclear locals when the scope is contained
Do not stage, commit, or push changes as part of this skill.
Step 5: Validate When Required
In fix-and-validate mode, after the main agent finishes edits, run the smallest relevant validation for the touched scope.
Examples:
targeted tests for the touched module
typecheck or compile for the touched target
formatter or lint check if that is the project's real safety gate
Prefer fast, scoped validation over full-suite runs unless the change breadth justifies more.
If validation is skipped because the user asked not to run it, say so explicitly.
Step 6: Summarize Outcome
Close with a brief result:
what was reviewed
what was fixed, if anything
what was intentionally left alone
whether validation ran
If the code is already clean for this rubric, say that directly instead of manufacturing edits.
Limitations
Use this skill only when the task clearly matches its upstream source and local project context.
Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.
