Get the FREE Ultimate OpenClaw Setup Guide →

Session Recovery

Scanned
npx machina-cli add skill a5c-ai/babysitter/session-recovery --openclaw
Files (1)
SKILL.md
944 B

Session Recovery

Detect and recover previous planning sessions, reconstructing lost context from persistent planning files.

Agent

Session Manager - pwf-session-manager

Workflow

  1. Check project path for existing planning files
  2. Check ~/.claude/projects/ for session data
  3. Find last planning file update timestamp
  4. Extract post-update conversation context (lost context)
  5. Build catchup report summarizing accomplished work
  6. Merge recovered state into current session

Inputs

  • projectPath - Root path for planning files
  • sessionId - Session identifier for recovery
  • previousSessionPath - Path to previous session (optional)

Outputs

  • Recovery report with completed phases and lost context estimate
  • Merged session state with preserved checkboxes
  • Catchup summary for manual sync

Process Files

  • planning-orchestrator.js - Session recovery at startup
  • planning-session.js - Full recovery pipeline

Source

git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/planning-with-files/skills/session-recovery/SKILL.mdView on GitHub

Overview

Session Recovery detects and restores previous planning sessions by reading persistent planning files, using the pwf-session-manager to orchestrate the process. It reconstructs lost context to help you resume work quickly, and it provides a catch-up summary while merging the recovered state into your current session.

How This Skill Works

It scans the projectPath for existing planning files and checks ~/.claude/projects/ for session data to locate the latest update. It extracts post-update context (lost context), builds a catchup report of what was accomplished, and merges the recovered state into the current session, preserving checklists and decisions. The process is driven by planning-orchestrator.js at startup and the full recovery pipeline in planning-session.js.

When to Use It

  • You reopened a project after a break and need to recover lost planning context.
  • A previous planning session's notes are dispersed across files and must be reconstructed.
  • Your environment crashed or restarted, and the live session state is unavailable.
  • You need a catch-up report to summarize what was accomplished before resuming.
  • You want to merge recovered state into the current session to preserve checklists and decisions.

Quick Start

  1. Step 1: Provide inputs: projectPath, sessionId, and optional previousSessionPath.
  2. Step 2: Run the recovery workflow (planning-orchestrator.js initializes recovery at startup).
  3. Step 3: Review the recovery report and merged session state, then resume work.

Best Practices

  • Provide accurate inputs: projectPath, sessionId, and optional previousSessionPath.
  • Verify the latest planning file timestamp before starting recovery.
  • Review the generated catchup report for critical decisions and next steps.
  • Ensure merged state preserves important checklists and decisions.
  • Use the startup-based recovery (planning-orchestrator.js) for automatic recovery when available.

Example Use Cases

  • Reopening a project after a long halt to regain lost context and continue planning.
  • Recovering after a system crash to reconstruct the last planning state.
  • Merging recovered notes with an active planning session in a Kanban-style board.
  • Generating a catch-up summary for stakeholders before resuming work.
  • Restoring post-update conversation context to resume dialogue with continuity.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers