Menu
Automatically summarizes the current session context to prevent token window overflow.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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
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.
| name | auto-summarizer |
| description | Automatically summarizes the current session context to prevent token window overflow. |
When a conversation has grown very long (e.g., > 15 turns), or after completing a significant task milestone.
For very short tasks, quick questions, or when the conversation is just beginning.
SESSION_STATE.md in the root of the project.SESSION_STATE.md, record:
SESSION_STATE.md, use the /prune-context tool to clear the message history if available, and then read SESSION_STATE.md to resume work.If the user asks "continue where we left off", and the context is very long: "I notice this conversation is quite long. Let me update SESSION_STATE.md with our current progress and then prune the context to save tokens."