Coordinate named agent teams on Grok Build using Ruflo MCP tools or a command-line message bus. Organize design, coding, testing, and review into ordered steps, with team-specific messages, status tracking, and shutdown.
Run Ruflo-style named Agent Teams on Grok Build using the host-agnostic team bus (scripts/grok-team-bus.mjs). Use when coordinating multi-agent pipelines, feature development with architect→coder→tester→reviewer, or replacing Claude SendMessage.
Run multiple agents as a team in Grok Build, giving each agent a name and role. The skill handles team creation, registration of work sequences, messages between agents, inbox and progress checks, and shutdown. It prefers Ruflo MCP team_* tools and uses the included grok-team-bus.mjs when those tools are unavailable.
Use it when you want separate agents to handle design, implementation, testing, and review, with work passed along in order. Messages are separated by team, so several teams can operate at the same time. The material also shows settings that use Git worktree to give development and testing agents separate working locations.
The procedure was checked with Grok Build 1.0.41. For newer versions, check the subagent specifications. The CLI requires Node.js. Registering an agent only returns a launch plan; the leader must launch it with spawn_subagent. Child agents cannot launch additional agents, and Claude SendMessage and TeammateTool are unavailable.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Claude SendMessage / TeammateTool are not available. Prefer Ruflo MCP team_* tools; CLI bus is the fallback.
| Tool | Purpose |
|---|---|
team_create | Create team + topology |
team_plan | Ordered pipeline steps |
team_spawn | Register agent; returns spawn plan for spawn_subagent |
team_send / team_broadcast | Handoff messages |
team_inbox | Drain/peek mailbox |
team_status / team_on_stop / team_shutdown | Lifecycle |
Discover: search_tool query team_create. Call via use_tool as ruflo__team_create etc.
# 1. Create team
node scripts/grok-team-bus.mjs create --name feature-x --topology hierarchical
# 2. Register plan
node scripts/grok-team-bus.mjs plan --team feature-x \
--steps '["architect","developer","tester","reviewer"]'
# 3. Register agents (prints spawnPlan JSON for spawn_subagent)
node scripts/grok-team-bus.mjs spawn --team feature-x --agent architect --role architect \
--prompt "Design <feature>. Handoff to developer." --next developer
node scripts/grok-team-bus.mjs spawn --team feature-x --agent developer --role developer \
--prompt "Implement from architect design." --next tester
node scripts/grok-team-bus.mjs spawn --team feature-x --agent tester --role tester \
--prompt "Test implementation." --next reviewer
node scripts/grok-team-bus.mjs spawn --team feature-x --agent reviewer --role reviewer \
--prompt "Review code and tests."
Checked against Grok Build 1.0.41. Pass only the live spawn arguments:
spawn_subagent({
prompt: spawnPlan.prompt,
description: spawnPlan.host.grok.spawn.description,
background: spawnPlan.host.grok.spawn.background,
isolation: spawnPlan.host.grok.spawn.isolation,
})
spawnPlan.host.grok.spawn (and prompt). Call spawn_subagent in one message for every agent (background: true).host.grok.advisory on the plan. capability_mode and subagent_type are not spawn arguments on this Grok. The prompt carries the read-only or worktree constraint. isolation is the knob Grok enforces..grok/agents/ruflo-* are session profiles (grok --agent-profile ruflo-coder or /agents). spawn_subagent does not select them. An omitted type is general-purpose.spawn_subagent. Nesting depth is 1. The lead spawns the whole pipeline.description unchanged (<role>:<agent>@<team>): the SubagentStop hook reads it to run on-stop for that team. Then spawn or resume the next step if needed.shutdown the team. A shut-down team refuses spawn and send; team_create --force reopens the name.Every call names its team: mail is per team, and several teams can run at once. team_spawn stops at the team's maxAgents.
If grok --version is newer than 1.0.41, re-read ~/.grok/docs/user-guide/16-subagents.md (Spawning Subagents) before forwarding extra keys. A key the schema dropped fails the spawn.
| Role | Prompt constraint (advisory.capability_mode) | isolation (passed through) |
|---|---|---|
| architect / reviewer | read-only | none |
| developer / tester | full tools | worktree |
node scripts/grok-team-bus.mjs send --team feature-x --to developer \
--from architect --summary "design" --message "..."
node scripts/grok-team-bus.mjs inbox --team feature-x --agent developer
node scripts/grok-team-bus.mjs status --team feature-x
memory_search / memory_store with namespace team:feature-xswarm_init for coordination records (then you still execute)swarm start to write codecapability_mode or subagent_type into spawn_subagent (they are advisory on Grok Build 1.0.41)spawn_subagent (depth limit is 1)No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.