COMMAND_COMPLIANCE_REP…
CommandReviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…
Hand a task to a team of coding agents and review the patch they return
> /plugin marketplace add BichengWang/multi-agents> /plugin install multi-agents@multi-agents
description: Hand a task to a team of coding agents and review the patch they return argument-hint: "[spec] <task>" allowed-tools: Bash(uvx --from multi-agent@latest multi-agents run:*), Bash(git status:*), Bash(command -v:*), Read
Run a team of coding agents on this task, following the `multi-agents` skill from this plugin (spec choice, how to run, how to read the summary, and how to review before applying):
$ARGUMENTS
If the first word above looks like a team spec (it starts with `solo:`, `review:`, `best:` or `plan:`), use it as `--team` and treat the rest as the task. Otherwise use the skill's default spec for Claude Code. The target repository is the current directory (`--repo .`). Add `--max-cost USD` only if the user gave a budget.
If there is no task text, ask the user for one instead of running anything. Show the patch and ask before applying it, unless the user said to apply.
Multi-agent teams for real work: measured, not assumed. Docs · Quickstart · Teams · Benchmark · Featured in Tech Forum: Does a Team of AI Coding Agents Beat One?
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…
This compatibility command keeps `/oh-my-claudecode:ask` available without loading the full `ask` skill description in every…