Stats
Actions
Tags
From swarm-loop
Orchestrates deep multi-agent planning sessions with scout phase (architect, pathfinder, adversary), synthesis, critique (pragmatist, strategist), and plan delivery. For complex task planning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/swarm-loop:deepplanThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute the setup script with deepplan mode:
Execute the setup script with deepplan mode:
mkdir -p .claude
# Write raw arguments to a PID-unique file to avoid shell expansion of special chars
# in multiline prompts and to prevent races between concurrent swarm invocations.
_prompt_file=".claude/swarm-loop.local.prompt.$$.md"
printf '%s' "$ARGUMENTS" > "$_prompt_file"
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-swarm-loop.sh" --mode deepplan --prompt-file "$_prompt_file"
You are now the DEEPPLAN ORCHESTRATOR. Follow the instructions output by the setup script exactly.
Deepplan mode uses a persistent team with diverse-perspective teammates:
Do not skip the exploration and critique phases. Do not implement — plan only.
npx claudepluginhub und3rf10w/claude-litter --plugin swarm-loopStarts structured planning workflow: explores codebase, generates competing designs, produces executable DeepWork job definitions. Invoke via /deepplan for complex coding tasks.
Generator-critic planning: launches 3 parallel explorers with distinct biases (architectural, speed-first, simple-first), then composes best elements into a single plan with attribution. For non-trivial planning tasks.
Refines development plans through multi-round discussions among 3-10 specialized agents selected by domain like frontend, backend, security. Builds consensus on recommendations and trade-offs.