一键导入
incubation-loop
// Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs
// Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs
| name | incubation-loop |
| description | Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs |
| automation | autonomous |
| schedule | 0 7 * * * |
| allowed-tools | Read, Write, Grep, Glob, Bash |
| user-invocable | true |
| argument-hint | [topic-slug] (optional - processes all active topics if omitted) |
Autonomous thinking engine. Each scheduled run advances all active thinking topics by one analytical move, persisting reasoning state across runs until convergence.
Continuous intellectual iteration on open questions. Uses a rotating set of research-validated analytical moves (ACH, Bayesian updating, dialectical steelmanning, cross-domain bridging) to build toward well-grounded conclusions - without requiring human presence in each cycle.
Design principle: Each run does one move per topic. Depth accumulates across runs. No single run tries to "solve" the question.
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Thinking Registry | Brain/05-Meta/Thinking/THINKING-REGISTRY.md | ✓ | ✓ | Active topics + status |
| Thinking Files | Brain/05-Meta/Thinking/[topic-slug].md | ✓ | ✓ | Per-topic reasoning journal |
| Local Brain Search | resources/local-brain-search/ | ✓ | Semantic search for KB evidence | |
| Permanent Notes | Brain/02-Permanent/ | ✓ | Primary evidence source | |
| Session Changelogs | Brain/05-Meta/Changelogs/ | ✓ | Run log |
Brain/05-Meta/Thinking/THINKING-REGISTRY.mddate '+%Y-%m-%d'
Read Brain/05-Meta/Thinking/THINKING-REGISTRY.md. Parse all topics with status: active.
If registry does not exist, create it:
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
created_by: claude-sonnet-4-6
updated_by: claude-sonnet-4-6
agent_version: 01.25
---
# Thinking Registry
Active questions under continuous analysis.
| Topic Slug | Central Question | Status | Runs | Last Run |
|------------|-----------------|--------|------|----------|
If no active topics found, log to changelog and exit cleanly.
Read Brain/05-Meta/Thinking/[topic-slug].md.
Parse:
run_count - how many iterations completedmove_sequence - which moves have been applied (determines next move)current_hypotheses - list with confidence scoresstatus - active / converged / crystallizedRotate through this sequence. Position = run_count mod 6:
| Position | Move | Research Basis |
|---|---|---|
| 0 | ACH Audit | Heuer (CIA) - Analysis of Competing Hypotheses |
| 1 | Bayesian Update | Information theory - explicit confidence tracking |
| 2 | Steelman Opposition | Socratic dialectic - steel-man the opposite |
| 3 | Cross-Domain Bridge | Consilience method - what does an unrelated field say? |
| 4 | Implication Check | Falsificationism (Popper) - if true, what follows? Is that true? |
| 5 | Assumption Audit | Intelligence SAT - which premises are load-bearing and shakiest? |
Use Local Brain Search to find relevant notes:
cd "$(git rev-parse --show-toplevel)"
python3 resources/local-brain-search/search.py "[central question]" --limit 8 --mode spreading 2>/dev/null
python3 resources/local-brain-search/search.py "[leading hypothesis]" --limit 5 --mode spreading 2>/dev/null
Read the top 3-4 most relevant notes in full. These are the evidence base for this iteration.
Execute the move based on what was determined in Step 3. For each move:
Append to Brain/05-Meta/Thinking/[topic-slug].md:
### Run [N]: [Move Name] - [YYYY-MM-DD]
**KB Evidence Consulted:**
- [[Note A]] - [one line on relevance]
- [[Note B]] - [one line on relevance]
**Analysis:**
[2-4 paragraphs of actual reasoning from the move]
**Updated Hypotheses:**
| Hypothesis | Confidence | Change |
|-----------|------------|--------|
| H1: [statement] | X% | ↑/↓/→ from Y% |
| H2: [statement] | X% | ↑/↓/→ from Y% |
**Current Best Answer:** [1-2 sentences - the leading position after this run]
**Open Questions for Next Run:** [What remains unresolved or most worth probing]
Update the frontmatter: updated, updated_by, run_count, last_run.
A topic has converged when ALL of:
run_count >= 4 (minimum 4 cycles)If converged:
status: converged in the thinking file frontmatter**CONVERGED** - Ready for crystallization via /synthesize-insightsconvergedIf not converged: continue to next topic.
Update Brain/05-Meta/Thinking/THINKING-REGISTRY.md:
Write to Brain/05-Meta/Changelogs/CHANGELOG - Incubation Loop YYYY-MM-DD.md:
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
created_by: claude-sonnet-4-6
updated_by: claude-sonnet-4-6
agent_version: 01.25
---
# Incubation Loop Session: YYYY-MM-DD
## Topics Processed
| Topic | Move Applied | Confidence Shift | Status |
|-------|-------------|-----------------|--------|
| [slug] | [move name] | [leading H]: Y% → Z% | active/converged |
## Notable Shifts
[Any hypothesis revisions, convergences, or surprising KB evidence]
## Converged Topics (Ready for Crystallization)
[List any topics that reached convergence this run]
To add a topic to the loop, create Brain/05-Meta/Thinking/[topic-slug].md:
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
created_by: claude-sonnet-4-6
updated_by: claude-sonnet-4-6
agent_version: 01.25
topic: "[exact question being analyzed]"
run_count: 0
last_run: null
status: active
---
# Thinking: [Topic Title]
## Central Question
[The exact question. Precise framing matters - ambiguous questions stay ambiguous.]
## Why This Question Matters
[1-2 sentences on stakes or relevance]
## Initial Hypotheses
| Hypothesis | Initial Confidence | Basis |
|-----------|-------------------|-------|
| H1: [statement] | X% | [prior knowledge or intuition] |
| H2: [statement] | X% | [prior knowledge or intuition] |
## Known Evidence (Pre-Run)
[Any notes or sources already known to be relevant]
## Constraints and Assumptions
[What are you taking as given? What's out of scope?]
---
*[Analytical runs will be appended below by the incubation loop]*
Then add to THINKING-REGISTRY.md:
| [topic-slug] | [central question] | active | 0 | null |
When a topic reaches status: converged, the human should:
/synthesize-insights [topic-slug] to graduate conclusions to a permanent notestatus: crystallizedDo not automate crystallization - judgment calls about what conclusions deserve permanence belong to the human.
| Error | Recovery |
|---|---|
| Registry missing | Create empty registry, log, exit cleanly |
| No active topics | Log to changelog, exit cleanly |
| KB search returns empty | Try alternate search terms from hypothesis text; if still empty, note in run log and skip KB-grounding for this move |
| Thinking file missing for active topic | Log warning in registry, skip topic |
| Run exceeds 45 minutes | Process topics in order; skip remaining, log which were skipped |
Brain/05-Meta/Changelogs/After completing this skill's primary task, consider tactical improvements:
git add .claude/skills/incubation-loop/SKILL.mdgit commit -m "refactor(incubation-loop): <brief improvement>"Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative
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.