Help us improve
Share bugs, ideas, or general feedback.
From agent-teams
Orchestrates a multi-reviewer parallel code review with specialized dimensions (security, performance, architecture, testing, accessibility). Accepts files, directories, git diffs, or PR numbers, and produces a consolidated, severity-organized report.
npx claudepluginhub meetsiddhu/wshobson-agents --plugin agent-teamsHow this command is triggered — by the user, by Claude, or both
Slash command
/agent-teams:team-review <target> [--reviewers security,performance,architecture,testing,accessibility] [--base-branch main]The summary Claude sees in its command listing — used to decide when to auto-load this command
# 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 `$ARGUMENTS`: - `<target>`: file path, directory, git diff range (e.g., `main...HEAD`), or PR number (e.g., `#123`) - `--reviewers`: comma-separated dimensions (default: `security,performance,architecture`) - `--base-branch`: base branch for diff comparison (default: `main`) ## Phase 1: Target Resoluti...
/team-reviewOrchestrates a multi-reviewer parallel code review with specialized dimensions (security, performance, architecture, testing, accessibility). Accepts files, directories, git diffs, or PR numbers, and produces a consolidated, severity-organized report.
/review-prReviews pull requests using 6-7 parallel specialized agents for code quality, security, tests, frontend, backend, and performance. Supports full, focused, or quick modes.
/code-reviewGenerates unified code review by having multiple AI models (Claude + externals) independently review code changes, compare findings, and converge on consensus.
/fire-7-reviewPerforms multi-perspective code review using 16 specialized reviewer personas on files, directories, PRs, or phases, producing a detailed report.
/review-waveLaunches 4 parallel specialist reviewers (security, performance, correctness, style) against code changes and merges findings into a unified severity-ranked report. Supports branch comparison and commit ranges.
/reviewOrchestrates 7 parallel specialist agents for standalone code review, analyzing hotspots, tech debt, quality, tests, coupling, practices, standards, and AI ergonomics.
Share bugs, ideas, or general feedback.
Orchestrate a multi-reviewer parallel code review where each reviewer focuses on a specific quality dimension. Produces a consolidated, deduplicated report organized by severity.
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set$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)git diff {range} --name-only to get changed filesgh pr diff {number} --name-only to get changed filesTeamCreate tool to create the team with team_name: "review-{timestamp}" and descriptionAgent 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 contentTaskCreate for each reviewer's task:
TaskList periodically)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)
Send shutdown_request to all reviewers
Call TeamDelete to remove team resources