parallel-review — Claude Code command: parallel code review
parallel-review runs code review across multiple directories or files simultaneously, one subagent per target.
MIT ★ 1,424 updated 2026-10-06
.claude/commands/parallel-review.mdWhat parallel-review does
The command splits a list of targets (directories, files) into independent tasks and spawns a subagent for each with run_in_background: true. All calls must go out in a single message for true parallelism. Each subagent looks for bugs, vulnerabilities, performance issues, and test coverage gaps, then returns its result automatically. The command collects reports, sorts findings by severity, and outputs a prioritized summary with recommended actions.
You need .claude/commands/parallel-review.md in the project root for the command to work. Three parallel reviews take roughly a third of the time sequential ones would — noticeable for large PRs or pre-merge module checks.
What it helps with
- run reviews of several modules simultaneously instead of sequentially
- check code in different directories in parallel before merging
- collect findings from independent parts of a project in one report
Example prompts for the agent
- review
src/auth,src/api, andsrc/dbin parallel - run
/project-starter:parallel-review src/auth src/api src/db - do a review of all modules in
src/modulesat once
How to install parallel-review
Manually: put the files in place
.claude/commands/parallel-review.mdCall it with /parallel-review. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/parallel-review.mdCall it with /prompts:parallel-review. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/parallel-review.prompt.mdManually: put the files in place
.gemini/commands/parallel-review.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about parallel-review
How do I install parallel-review in Claude Code?
Place the command file at .claude/commands/parallel-review.md in the project root.
What does parallel-review do?
It runs code review across multiple directories or files simultaneously via subagents — each target is checked in parallel, results are collected into a prioritized summary.
How does the command run reviews in parallel?
It creates a subagent per target with run_in_background: true and sends all calls in one message — Claude Code then launches them simultaneously rather than sequentially.
Source text
parallel-review.md · MIT
--- description: Run parallel code review across multiple directories or files. Uses N subagents simultaneously for faster analysis. argument-hint: <directories or files to review in parallel, e.g., "src/auth src/api src/db"> --- # Parallel Code Review Review `$ARGUMENTS` using parallel subagents for maximum speed. ## Process 1. **Parse Targets**: Split arguments into independent review targets 2. **Spawn Parallel Reviewers**: Launch one subagent per target 3. **Collect Results**: Each subagent returns its review automatically on completion 4. **Synthesize**: Merge findings into prioritized report ## Execution Pattern **CRITICAL**: Launch ALL Task calls in a SINGLE message for true parallelism. For each independent target, spawn a subagent with `run_in_background: true`: ``` I'm launching N parallel code reviewers: [Task 1] description: "Review [target 1]" prompt: "You are a code reviewer. Analyze [target 1] for: - Code quality and best practices - Potential bugs and edge cases - Security vulnerabilities - Performance issues - Test coverage gaps Provide findings with file:line references and severity levels." run_in_background: true [Task 2] description: "Review [target 2]" prompt: "You are a code reviewer. Analyze [target 2] for..." run_in_background: true [Task 3] description: "Review [target 3]" prompt: "You are a code reviewer. Analyze [target 3] for..." run_in_background: true ``` Each subagent returns its result automatically when it completes — there is no separate retrieval step. Read each review as it returns. ## Output Format ```markdown ## Parallel Review Results ### Summary - **Targets reviewed**: N - **Total findings**: X - **Critical issues**: Y - **Execution time**: ~Zs (parallel) ### [Target 1] Findings #### Critical - [Issue] at file:line - [Description] #### Warnings - [Issue] at file:line - [Description] #### Suggestions - [Improvement] at file:line - [Description] ### [Target 2] Findings ... ### Combined Priority List 1. **Critical** - [Target X] - [Issue description] 2. **Critical** - [Target Y] - [Issue description] 3. **High** - [Target Z] - [Issue description] ... ### Recommended Actions 1. Fix critical issues in [Target X] first 2. Address security concerns in [Target Y] 3. Consider performance optimizations in [Target Z] ``` ## Example Usage ``` /project-starter:parallel-review src/auth src/api src/db ``` This spawns 3 parallel reviewers (one per directory), completing in ~1/3 the time of sequential review. ## When to Use - Reviewing multiple independent modules - Pre-merge comprehensive codebase review - Analyzing different areas of a large PR - Comparing implementation patterns across directories
© CloudAI-X · MIT · CloudAI-X/claude-workflow-v2