a5c-ai/babysitter / library/methodologies/gastown/skills/session-management
session-management
VerifiedManage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.
SKILL.md
View on GitHub---
name: session-management
description: Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion
graph:
domains: [domain:software-engineering]
skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop]
workflows: [workflow:feature-development]
topics: [topic:developer-experience]
roles: [role:tech-lead, role:backend-engineer]
---
- Handing off work between agents
- Reviving a dead or stuck agent session
- Managing Polecat identity persistence across sessions
## Session Operations
1. **Init**: Start new session with role and hook setup
2. **Attach**: Connect agent to Mayor for coordination
3. **Handoff**: Transfer work between agents with context
4. **Seance**: Revive a dead agent's session state
5. **Resume**: Continue from last checkpoint
## Agent Session Types
- **Crew**: Long-lived sessions, full state persistence
- **Polecat**: Ephemeral sessions, persistent identity, state via hooks
- **Dog**: Infrastructure sessions, minimal state
## Key Commands
- `gt mayor attach` - Attach to Mayor coordination
- `gt handoff` - Hand off work to another agent
- `gt seance` - Revive dead session
- `gt prime` - Prime agent with context
## Tool Use
Used within agent coordination and patrol monitoring processes.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |