Multi-round context exploration - scan, search, and load in one call (TEAM+ plan)
From sniparanpx claudepluginhub snipara/snipara-claude --plugin snipara/orchestrateDelegates to orchestration skills for parallel multi-agent workflows via tmux worktrees and persistent loops, producing merged reports, security summaries, and control-plane snapshots.
/orchestrateGenerates test orchestration configs for staged workflows with dependencies, parallel execution, smart selection of affected tests, retries, and CI/CD optimization.
/orchestrateDecomposes complex tasks into sub-tasks with dependency management, executes workflows sequentially or in parallel, tracks progress, and reports via table summary.
/orchestrateOrchestrates agent teams to execute complex requests: analyzes into steps, runs with verification, auto-retries failures up to 5x per step, escalates to user if needed, and reports outcomes.
/orchestrateOrchestrates parallel task execution from prompt_plan.md using Agent Teams API, analyzing dependencies and running domain-specific build/test/lint. Supports --type, --parallel, --dry-run flags.
/orchestrateRoutes arguments to workflow orchestration subcommands: interactive menu, help, docs, examples, templates, or inline syntax execution with visual feedback.
Orchestrating multi-round context exploration for: $ARGUMENTS
Using rlm_orchestrate(query="$ARGUMENTS")
This performs a 3-phase context exploration in a single call:
Plan required: TEAM or higher.
When to use:
rlm_context_query alone doesn't provide enough depthExample:
/snipara:orchestrate How does the authentication flow work end-to-end?
This will scan all files, find the most relevant sections about authentication, and load their full content - all in one call.