Session PersistCAUTION

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: session-persist
description: Persist and restore agent sessions across conversations with state snapshots
argument-hint: "[--save|--restore|--list]"
allowed-tools: mcp__plugin_ruflo-core_ruflo__session_save mcp__plugin_ruflo-core_ruflo__session_restore mcp__plugin_ruflo-core_ruflo__session_list mcp__plugin_ruflo-core_ruflo__session_info mcp__plugin_ruflo-core_ruflo__session_delete mcp__plugin_ruflo-core_ruflo__hooks_session-start mcp__plugin_ruflo-core_ruflo__hooks_session-end mcp__plugin_ruflo-core_ruflo__hooks_session-restore Bash
---

# Session Persistence

Save and restore complete agent sessions across conversations.

## When to use

When you need to pause work and resume later with full context, or when you want to checkpoint progress during long-running tasks.

## Steps

1. **Save session** — call `mcp__plugin_ruflo-core_ruflo__session_save` to snapshot current state
2. **List sessions** — call `mcp__plugin_ruflo-core_ruflo__session_list` to see all saved sessions
3. **Restore** — call `mcp__plugin_ruflo-core_ruflo__session_restore` to resume a previous session
4. **Info** — call `mcp__plugin_ruflo-core_ruflo__session_info` for session details and metadata
5. **Clean up** — call `mcp__plugin_ruflo-core_ruflo__session_delete` to remove old sessions

## Session hooks

- `hooks_session-start` — automatically restore context at conversation start
- `hooks_session-end` — automatically save state with metrics export
- `hooks_session-restore` — restore a specific session by ID

## What's persisted

- Agent state and configuration
- Memory entries and patterns
- Learning trajectories and metrics
- Task progress and todos

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (4)

crates

plugin/agents

plugin/commands

plugin/skills

Gates applied: no_behavioural_pass.