Detect and recover previous planning sessions, reconstructing lost context from persistent planning files.
Scanned 5/29/2026
Install to Claude Code
Skills Directorynpx -y skills add a5c-ai/babysitter --skill session-recovery --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Session Recovery?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-session-recovery)More formats (shields.io, HTML) on the badges page.
# 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
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
