Aggressive session accountability via Obsidian timeline. PROACTIVELY log decisions, commits, ideas, and blockers AS THEY HAPPEN. Triggers on any significant action.
/plugin marketplace add cameronsjo/claude-marketplace/plugin install session-sync@cameronsjoThis skill inherits all available tools. When active, it can use any tool Claude has access to.
templates/timeline-init.mdMaintain context across Claude Code sessions using aggressive, real-time logging.
Don't wait for session end. Log as things happen:
You are accountable for maintaining context. The user may forget, the session may crash, context may compact. The timeline is the source of truth.
| Variable | Required | Description |
|---|---|---|
CLAUDE_TIMELINE_PATH | Yes | Path to timeline file |
Log immediately after any of these:
| Trigger | Format |
|---|---|
| Decision | - HH:MM **Decision**: Using X because Y |
| Commit | - HH:MM **Commit**: message (abc123) |
| Blocker | - HH:MM **Blocker**: description |
| Resolved | - HH:MM **Resolved**: how it was fixed |
| Idea | - HH:MM **Idea**: insight or suggestion |
| State | - HH:MM **State**: service on port, config changed |
Be aggressive. When in doubt, log it.
$CLAUDE_TIMELINE_PATHThe Inbox is for async capture from any device (phone, tablet, mobile Obsidian).
## Inbox
> Async capture from any device. Claude reviews at session start.
- [ ] Add Sonarr to Traefik routes
- [ ] Look into why n8n keeps disconnecting
At session start:
# Claude Code Timeline
## Inbox
> Async capture from any device. Claude reviews at session start.
## Work Log
### 2025-12-19
- 23:15 **Decision**: Using Traefik - better Docker integration
- 23:30 **Commit**: feat: add prometheus (abc123)
- 23:45 **Blocker**: OAuth not redirecting
- 00:10 **Resolved**: OAuth needed explicit redirect_uri
Prefer MCP if obsidian-mcp-server is available:
mcp__obsidian-mcp-server__obsidian_read_notemcp__obsidian-mcp-server__obsidian_update_note or obsidian_search_replaceFallback to native Read/Edit tools.
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 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 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.