OpenSkillIndex← back to search
claude-codeopenclaw

Openclaw-superpowers subagent-driven-development

Parallel subagent execution for complex tasks. Use when a task has independent parallel workstreams.

install
source · Clone the upstream repo
git clone https://github.com/ArchieIndian/openclaw-superpowers
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/core/subagent-driven-development" ~/.claude/skills/archieindian-openclaw-superpowers-subagent-driven-development && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/core/subagent-driven-development" ~/.openclaw/skills/archieindian-openclaw-superpowers-subagent-driven-development && rm -rf "$T"
manifest: skills/core/subagent-driven-development/SKILL.md
source content

Subagent-Driven Development

When to Use

  • Task has 2+ independent workstreams
  • Each workstream takes >10 minutes
  • Workstreams do not share mutable state

The Pattern

  1. Decompose - break into independent subtasks
  2. Spec each subagent - clear, self-contained instructions
  3. Launch in parallel - use exec with background:true
  4. Monitor - check progress, do not micromanage
  5. Integrate - run full test suite after all complete

Launch Pattern

exec command:"claude --permission-mode bypassPermissions --print '[spec A]'" background:true
exec command:"claude --permission-mode bypassPermissions --print '[spec B]'" background:true