with one click
session-continuity
Cross-session state management and recovery
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.
Menu
Cross-session state management and recovery
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
| name | session-continuity |
| description | Cross-session state management and recovery |
| argument-hint | <session-context> |
| user-invocable | false |
Critical state is persisted to artifacts/memory/activeContext.md by hooks:
CLAUDE_ENV_FILE and logs session startartifacts/sessions/delegation-log.jsonl# Active Context
## Current Task
{One-line description of the active task}
## Phase
{Planning | Implementation Phase N | Review | Complete}
## Plan Progress
{completed} of {total} phases
## Last 3 Decisions
1. {Most recent decision}
2. {Previous decision}
3. {Earlier decision}
## Open Questions
- {Unresolved question 1}
- {Unresolved question 2}
## Active Files
- {path/to/file1}
- {path/to/file2}
## Model Tiers Active
- Heavy: {agent names using Opus}
- Default: {agent names using Sonnet}
- Fast: {agent names using Haiku}
## Next Action
{What should happen next}
## Updated
{ISO timestamp}
When starting a new session that continues previous work:
artifacts/memory/activeContext.mdartifacts/artifact-index.md for recent artifactsWhen starting unrelated work:
/clear to reset contextDemo pipeline state machine — 7-phase autonomous sequence with delegation context templates, phase transition logic, BLOCKED recovery strategies, and demo-state.json schema. Used exclusively by demo-conductor.
Cinematic narration style guide for demo-conductor — ANSI-coloured banner formats, live pipeline scoreboard, audience-facing language, phase summaries, and error narration patterns. Keeps the demo presentation-quality throughout.
Standardized completion and escalation protocol for subagent responses. Ensures the conductor can machine-parse every subagent return. Use when reporting completion status back to the orchestrator.
Cross-session learnings lifecycle — schema, storage, retrieval, and pruning of lessons learned during orchestrator sessions. Use when managing learnings via the /learn command.
Agent Teams assembly and task injection — selects appropriate team, validates prerequisites, estimates cost, injects tasks into the shared task list, and manages team lifecycle.
Token and cost tracking with model tier enforcement