team-review — Claude Code command: parallel multi-reviewer code review
Spawns several reviewers at once, each on its own quality dimension, and returns one report sorted by severity.
/plugin marketplace add wshobson/agents
/plugin install agent-teams@claude-code-workflowsWhat team-review does
team-review builds a team of subagents and hands them a single job: review the code along the dimensions you pick. The default set is security, performance and architecture; add testing or accessibility with the --reviewers flag.
The target can be a file, a directory, a git diff range like main...HEAD, or a PR number such as #123. PR targets go through gh pr diff, diff ranges through git diff, so an authenticated GitHub CLI has to be on the machine. Each reviewer gets its own file list and checklist, runs in parallel, and the findings come back together.
One pre-flight check gates the whole run: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 must be set. Miss it and nothing starts, so set it in your environment first. Findings are then deduplicated by file:line, severity conflicts resolve to the higher rating, and the command shuts the reviewers down and deletes the team resources when the report is out.
What it helps with
- run security and performance review in one pass
- merge findings from several reviewers without duplicates
- check a diff across multiple dimensions before merging
- sort findings into critical, high, medium and low
- add an accessibility pass to a normal review
Example prompts for the agent
- Run team-review on the main...HEAD range
- Review PR #123 with reviewers security,performance,testing
- Run team-review over src/api with base branch develop
How to install team-review
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install agent-teams@claude-code-workflows2Manually: put the files in place
.claude/commands/team-review.mdCall it with /team-review. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/team-review.mdCall it with /prompts:team-review. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/team-review.prompt.mdManually: put the files in place
.gemini/commands/team-review.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about team-review
How do I install team-review in Claude?
Add the marketplace with /plugin marketplace add wshobson/agents, then install the plugin: /plugin install agent-teams@claude-code-workflows. The command file lives at .claude/commands/team-review.md.
What does team-review do?
It runs a parallel code review with several subagents, one per quality dimension, and consolidates their findings into a single report grouped by severity.
What does team-review need to run?
The environment variable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. PR targets also need an authenticated gh, and diff ranges need git.
Source text
team-review.md · MIT
---
description: "Launch a multi-reviewer parallel code review with specialized review dimensions"
argument-hint: "<target> [--reviewers security,performance,architecture,testing,accessibility] [--base-branch main]"
---
# Team Review
Orchestrate a multi-reviewer parallel code review where each reviewer focuses on a specific quality dimension. Produces a consolidated, deduplicated report organized by severity.
## Pre-flight Checks
1. Verify `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set
2. Parse `$ARGUMENTS`:
- `<target>`: file path, directory, git diff range (e.g., `main...HEAD`), or PR number (e.g., `#123`)
- `--reviewers`: comma-separated dimensions (default: `security,performance,architecture`)
- `--base-branch`: base branch for diff comparison (default: `main`)
## Phase 1: Target Resolution
1. Determine target type:
- **File/Directory**: Use as-is for review scope
- **Git diff range**: Use Bash to run `git diff {range} --name-only` to get changed files
- **PR number**: Use Bash to run `gh pr diff {number} --name-only` to get changed files
2. Collect the full diff content for distribution to reviewers
3. Display review scope to user: "{N} files to review across {M} dimensions"
## Phase 2: Team Spawn
1. Use `TeamCreate` tool to create the team with `team_name: "review-{timestamp}"` and `description`
2. For each requested dimension, use `Agent` tool to spawn a teammate:
- `name`: `{dimension}-reviewer` (e.g., "security-reviewer")
- `subagent_type`: "agent-teams:team-reviewer"
- `prompt`: Include the dimension assignment, target files, and diff content
3. Use `TaskCreate` for each reviewer's task:
- Subject: "Review {target} for {dimension} issues"
- Description: Include file list, diff content, and dimension-specific checklist
## Phase 3: Monitor and Collect
1. Wait for all review tasks to complete (check `TaskList` periodically)
2. As each reviewer completes, collect their structured findings
3. Track progress: "{completed}/{total} reviews complete"
## Phase 4: Consolidation
1. **Deduplicate**: Merge findings that reference the same file:line location
2. **Resolve conflicts**: If reviewers disagree on severity, use the higher rating
3. **Organize by severity**: Group findings as Critical, High, Medium, Low
4. **Cross-reference**: Note findings that appear in multiple dimensions
## Phase 5: Report and Cleanup
1. Present consolidated report:
```
## Code Review Report: {target}
Reviewed by: {dimensions}
Files reviewed: {count}
### Critical ({count})
[findings...]
### High ({count})
[findings...]
### Medium ({count})
[findings...]
### Low ({count})
[findings...]
### Summary
Total findings: {count} (Critical: N, High: N, Medium: N, Low: N)
```
2. Send `shutdown_request` to all reviewers
3. Call `TeamDelete` to remove team resources
© Seth Hobson · MIT · wshobson/agents