feat: add 6 production-ready plugins

All plugins are stdlib-only Python with no external dependencies.

- auto-summarizer: extractive conversation summary for long context
  compression, persists per-agent summaries to disk
- conversation-logger: JSONL audit logs per agent with ISO 8601
  timestamps, auto-creates log directory tree
- guardrails: safety filter detecting PII (email, phone, SSN, CC),
  prompt injection patterns, and credential exposure via regex
- keyword-memory: extracts entities (emails, URLs, dates, technical
  terms like camelCase/snake_case/dotted identifiers) as memories
- sentiment-tracker: keyword-based sentiment scoring with intensifiers
  and negation handling, only injects context for non-neutral sentiment
- todo-tracker: detects action items via 7 task patterns, tracks
  completion, deduplicates, persists per-agent with 20-item FIFO limit

plugins/sentiment-tracker/hooks/README.md

@@ -0,0 +1,14 @@
+# sentiment-tracker hooks
+
+Python hook scripts for the sentiment-tracker plugin. Each script reads a JSON request from stdin and writes a JSON response to stdout.
+
+## Scripts
+
+| Script | Hook | Description |
+|--------|------|-------------|
+| `ingest.py` | ingest | Receives `{"message": "..."}`, analyzes sentiment, returns emotional context as a memory fragment |
+
+## Protocol
+
+- **Input**: JSON object on stdin (fields vary by hook type)
+- **Output**: JSON object on stdout (`ingest_result` with memories, empty for neutral sentiment)