Skip to content

Agents

Agents are autonomous sub-agents that Claude Code spawns to handle specific tasks. Each agent has its own model, tools, and protocol.

AgentModelPurpose
rn-testerSonnet7-step test verification protocol
rn-debuggerParallel evidence gathering + targeted fix
rn-code-explorerSonnetCodebase mapping: screens, store, navigation, testIDs
rn-code-architectOpusArchitecture design with E2E proof flow
rn-code-reviewerCorrectness, RN conventions, project patterns

In the rn-feature-dev pipeline:

  • Phase 2 (Exploration): 2-3 rn-code-explorer agents run in parallel
  • Phase 4 (Architecture): rn-code-architect designs the blueprint
  • Phase 5.5 (Verification): rn-tester verifies live on simulator
  • Phase 6 (Review): 3 rn-code-reviewer agents check different aspects

Standalone:

  • /debug-screen spawns rn-debugger
  • /test-feature spawns rn-tester