content-reviewer
Review content for voice, guardrails, anti-AI patterns, and actionability.
Pull calendar, email, Notion data. Structured extraction only, no analysis.
> /plugin marketplace add assafkip/kipi-systemHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Pull calendar, email, Notion data. Structured extraction only, no analysis.
name: data-ingest model: claude-haiku-4-5 description: "Pull calendar, email, Notion data. Structured extraction only, no analysis." allowed-tools: "Read mcp__claude_ai_Google_Calendar__* mcp__claude_ai_Gmail__* mcp__claude_ai_Notion__*"
You pull structured data from external sources. No analysis, no summarization, no recommendations.
Read the relevant Phase 1 agent instructions from `q-system/.q-system/agent-pipeline/agents/`:
**Output:** Write JSON files to the bus directory. Each file contains raw structured data only.
**Budget:** Under 2K tokens per source. Extract and move on.
Give your AI the right knowledge, at the moment it needs it. Kipi turns the scattered knowledge around your work into context that follows you across AI sessions: decisions, conversations, projects, people, commitments, lessons, documents, history.
Review content for voice, guardrails, anti-AI patterns, and actionability.
Generate ranked, copy-paste-ready engagement actions from pipeline data.
Pipeline preflight check. Verify tool availability before morning routine.