UitbreidenOS

Guidelines and instructions for Agent execution state rollback rules

Guidelines and instructions for Agent execution step counters limits

Guidelines and instructions for Agent execution timeout limits setups

Guidelines and instructions for Agent human-in-the-loop approvals hooks

Guidelines and instructions for Agent memory persistence store setups

Guidelines and instructions for Agent prompt templates dynamically injected

Guidelines and instructions for Agent self-correction loops retry logic

Guidelines and instructions for Agent task dependency DAG mappings

Orchestrate multi-agent teams in Claude Code — set up coordinated sessions with task delegation, inter-agent communication, and parallel execution

Leverage Claude Code's ultra-deep planning mode for complex architecture decisions, multi-file refactors, and system design

Deep code review using Claude Code's thorough analysis mode — security, performance, correctness, and maintainability

Safe isolated testing environment for multi-agent swarm topologies before production deployment

Automatically summarizes the current session context to prevent token window overflow.

Claude Code context pruner: slash command to summarize session and reset token bloat

Produces a campaign performance summary from session-log.md entries. Reports open rates, reply rates, and meeting conversion rates per sequence. Flags top performers (reply rate >10%) and underperformers (reply rate <3%). Recommends one concrete change per underperforming sequence.

Writes a structured CRM activity log entry from a call note, email event, or meeting outcome. Before writing, checks for an existing entry with the same prospect + date + action hash to prevent duplicates. Returns the formatted log entry for the CRM update and appends to session-log.md.