// Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative
| name | compute-lifecycle |
| description | Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative |
| allowed-tools | ["Bash","Read"] |
| user-invocable | true |
| automation | gated |
Computes lifecycle scores (0.0 reflective -> 1.0 generative) for all insight and framework notes based on behavioral signals: citation frequency, generative ratio, cross-domain reach, and temporal acceleration.
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Enrichments | resources/brain-graph/data/graph_enrichments.json | ✓ | ✓ | Updated lifecycle scores |
| LBS Graph | resources/local-brain-search/data/brain_graph.pkl | ✓ | NetworkX graph | |
| Brain files | Brain/**/*.md | ✓ | File mtimes for temporal signals |
cd "$(git rev-parse --show-toplevel)"/resources/brain-graph
../local-brain-search/venv/bin/python cli.py lifecycle
For JSON output:
../local-brain-search/venv/bin/python cli.py lifecycle --json
Focus on notes that crossed phase boundaries:
For promotable notes, suggest:
| Score Range | Phase | Meaning |
|---|---|---|
| 0.0 - 0.3 | Reflective | Tracks sources, sources win on conflict |
| 0.3 - 0.6 | Crystallizing | Generating own connections, authority contested |
| 0.6 - 1.0 | Generative | Drives downstream notes, this note wins on conflict |
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Autonomous research pipeline - discover, extract, and integrate cutting-edge insights into knowledge base
Detect productive contradictions between notes - high semantic similarity with opposing conclusions that represent synthesis opportunities
Autonomous perception layer - scans KB for new notes matching domain watch configs, checks gap resonance with the Thinking Registry, probes external signals via web search, and auto-activates HIGH/MEDIUM signals into the Thinking Registry for the incubation loop.
Extract insights from external documents (research papers, books, articles). Spawns document-insight-extractor subagent. Requires session name.
Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available.