vanzan01/claude-code-sub-agent-collective

by vanzan01

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

Content Signals

Repo Health

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

Risk Assessment

• Multi-agent spawning system: Repository implements AgentSpawner, AgentLifecycleManager, and dynamic agent creation framework enabling autonomous sub-agent orchestration
• Install scripts with bootstrap automation: bin/install-collective.js and bin/claude-code-collective.js provide automated installation and initialization without explicit user approval gates per agent spawn
• Persistent configuration modification: .claude-collective directory structure with CLAUDE.md, agents.md, hooks.md templates enable persistent agent configuration and behavioral modification
• Autonomous operation without approval: AgentSpawnCommand and command-system architecture allow chained agent execution with command history but unclear human approval gates between agent spawns
• External code execution via templates: Templates directory contains 30+ agent markdown definitions that spawn specialized sub-agents for arbitrary tasks (devops-agent, infrastructure-implementation-agent, etc.)
• Bash/Shell execution capability: scripts/test-automated.sh, scripts/cleanup-tests.sh in bin directory enable shell command execution during installation and operation