Use at start of new session to restore context from STATUS.json - loads previous state, displays session type, shows what to continue working on. Calculates session type (Continuation/Resume/Fresh Start) based on time gap. Do NOT use mid-session or when starting fresh work unrelated to previous session - just begin the new task directly.
/plugin marketplace add jrc1883/popkit-claude/plugin install popkit@popkit-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
checklists/resume-checklist.jsonscripts/restore_state.pyworkflows/resume-workflow.jsonRestore context from STATUS.json when starting a new Claude Code session.
Core principle: Start where you left off, not from scratch.
Trigger: Beginning of new conversation (via session-start hook or manual)
Based on time since last update:
| Time Gap | Session Type | Behavior |
|---|---|---|
| < 30 min | Continuation | Quick restore, assume full context |
| 30 min - 4 hours | Resume | Restore context, brief refresh |
| > 4 hours | Fresh Start | Full context load, verify state |
# Check for STATUS.json
if [ -f ".claude/STATUS.json" ]; then
cat .claude/STATUS.json
elif [ -f "STATUS.json" ]; then
cat STATUS.json
fi
const lastUpdate = new Date(status.lastUpdate);
const now = new Date();
const hoursSince = (now - lastUpdate) / (1000 * 60 * 60);
if (hoursSince < 0.5) return "Continuation";
if (hoursSince < 4) return "Resume";
return "Fresh Start";
Continuation (< 30 min):
ā” Continuation Session
Last: 15 minutes ago
Quick context:
- Branch: feature/auth
- Focus: Password reset flow
- Next: Add email template
Ready to continue.
Resume (30 min - 4 hours):
š Resume Session
Last: 2 hours ago
Context restore:
- Branch: feature/auth (2 uncommitted files)
- Last commit: feat: add login form
- In Progress: Implement password reset flow
- Focus: Authentication system
- Next: Add forgot password email template
Key decisions from last session:
- Using nodemailer for emails
- Password reset expires in 1 hour
Shall I continue with the next action?
Fresh Start (> 4 hours):
š
Fresh Start Session
Last activity: Yesterday at 2:30 PM
Full context load:
- Branch: feature/auth (2 uncommitted files)
- Last commit: feat: add login form
- Test status: 45 passing
- Build status: passing
Tasks in progress:
- [ ] Implement password reset flow
Last focus: Authentication system
Last blocker: None
Recommended: Review STATUS.json and verify current state before continuing.
For fresh starts, verify the saved state is still accurate:
# Verify branch
git branch --show-current
# Verify uncommitted count
git status --porcelain | wc -l
# Run tests
npm test
# Check services
curl -s http://localhost:3000/health
Report discrepancies if any.
After displaying context:
Ready to continue. Options:
1. Continue with: [nextAction from STATUS.json]
2. Review full context first
3. Start fresh (ignore previous session)
What would you like to do?
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā š Resume Session ā
ā Last: 2 hours ago ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Branch: feature/auth ā
ā Uncommitted: 2 files ā
ā Tests: 45 passing ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā In Progress: ā
ā ⢠Implement password reset flow ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Next Action: ā
ā Add forgot password email template ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
Pairs with:
Hook integration:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.