agenticnotetaking · GFrierson · Feb 23, 2026
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
@@ -12,7 +12,7 @@
   "plugins": [
     {
       "name": "arscontexta",
-      "description": "Generate research-backed knowledge systems from natural conversation. 15 kernel primitives, 26 commands, 249 research claims, 3 presets.",
+      "description": "Generate research-backed knowledge systems from natural conversation. 16 kernel primitives, 26 commands, 244 research claims, 3 presets.",
       "version": "0.8.0",
       "source": "./",
       "strict": false,

diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "arscontexta",
   "version": "0.8.0",
-  "description": "Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.",
+  "description": "Conversational derivation engine — generate agent-native memory architecture from natural conversation. 16 kernel primitives, 26 commands, 17 feature blocks, 3 presets.",
   "author": {
     "name": "Heinrich",
     "url": "https://arscontexta.org"

diff --git a/README.md b/README.md
@@ -5,7 +5,7 @@
 A Claude Code plugin that generates complete knowledge systems from conversation.
 You describe how you think and work. The engine derives a cognitive architecture
 -- folder structure, context files, processing pipeline, hooks, navigation maps,
-and note templates -- tailored to your domain and backed by 249 research claims.
+and note templates -- tailored to your domain and backed by 244 research claims.
 
 No templates. No configuration. Just conversation.
 
@@ -74,7 +74,7 @@ domain needs and why.
 | **Derivation** | Maps signals to eight configuration dimensions with confidence scoring |
 | **Proposal** | Shows what will be generated and why, in your vocabulary |
 | **Generation** | Produces all files: context file, folders, templates, skills, hooks, manual |
-| **Validation** | Checks all 15 kernel primitives, runs pipeline smoke test |
+| **Validation** | Checks all 16 kernel primitives, runs pipeline smoke test |
 
 The whole process takes about 20 minutes. It's token-intensive because the engine
 reads research claims, reasons about your domain, and generates substantial output.
@@ -180,13 +180,13 @@ Four hooks automate quality enforcement:
 | **Session Orient** | `SessionStart` | Injects workspace tree, loads identity, surfaces maintenance signals |
 | **Write Validate** | `PostToolUse` (Write) | Schema enforcement on every note write |
 | **Auto Commit** | `PostToolUse` (Write, async) | Git auto-commit, non-blocking |
-| **Session Capture** | `Stop` | Persists session state to `ops/sessions/` |
+| **Session Capture** | `Stop` | Persists session state to `ops/sessions/` (generated during `/setup`) |
 
 ---
 
 ## The Research Graph
 
-The `methodology/` directory contains **249 interconnected research claims**
+The `methodology/` directory contains **244 interconnected research claims**
 about tools for thought, knowledge management, and agent-native cognitive
 architecture. These claims back every configuration decision.
 
@@ -297,9 +297,9 @@ arscontexta/
 |-- generators/
 |   |-- claude-md.md             # CLAUDE.md template
 |   +-- features/                # 17 composable feature blocks
-|-- methodology/                 # 249 research claims
+|-- methodology/                 # 244 research claims
 |-- reference/                   # Core reference documents
-|   |-- kernel.yaml              # 15 kernel primitives
+|   |-- kernel.yaml              # 16 kernel primitives
 |   |-- three-spaces.md          # Architecture spec
 |   +-- use-case-presets.md      # Pre-validated configs
 |-- platforms/                   # Platform-specific adapters

diff --git a/generators/features/methodology-knowledge.md b/generators/features/methodology-knowledge.md
@@ -51,7 +51,7 @@ cat ops/methodology/derivation-rationale.md
 
 ### The Research Foundation
 
-Your system's design choices are backed by a knowledge base of 249 interconnected methodology notes — research claims, guidance documents, and domain examples — covering knowledge systems, cognitive science, and agent cognition. Access it through:
+Your system's design choices are backed by a knowledge base of 244 interconnected methodology notes — research claims, guidance documents, and domain examples — covering knowledge systems, cognitive science, and agent cognition. Access it through:
 
 ```
 /ask "why does my system use atomic notes?"
@@ -61,7 +61,7 @@ Your system's design choices are backed by a knowledge base of 249 interconnecte
 
 The /ask command consults two knowledge layers:
 - **Local methodology** (ops/methodology/) — "How does MY system work?" questions
-- **Research graph** (249 bundled methodology notes) — "Why is this a good idea in general?" questions
+- **Research graph** (244 bundled methodology notes) — "Why is this a good idea in general?" questions
 
 When you need to understand a design choice: check ops/methodology/ for the specific rationale, then /ask for the theoretical backing.
 ```

diff --git a/reference/derivation-validation.md b/reference/derivation-validation.md
@@ -265,7 +265,7 @@ _schema:
 
 ## Test 5: Minimal Platform (Convention-Only)
 
-**Question:** Can all 15 kernel primitives be satisfied on a platform with no hooks, no skills, and no subagent support — using only a context file and filesystem access?
+**Question:** Can all 16 kernel primitives be satisfied on a platform with no hooks, no skills, and no subagent support — using only a context file and filesystem access?
 
 **Input:**
 - Use case: Personal journal — regular reflections, goal tracking, occasional pattern review
@@ -646,4 +646,4 @@ Observe (create observation/tension)
 
 7. **Feature disabling is safe and reversible.** The progressive configuration test (Test 8) confirms that disabling optional features does not break the system. Each optional feature has a fallback path. INVARIANT primitives cannot be disabled, ensuring the structural foundation is always present. The system ships complete and users opt down — the reverse of the former tier-based approach.
 
-**Derivation engine confidence: HIGH.** The 15 kernel primitives provide a universal base. The 8 configuration dimensions parameterize the variation space. Interaction constraints prevent incoherent combinations. The 3 presets (Research, Personal Assistant, Experimental) provide pre-validated starting points. The system derives working configurations for research, therapy, competitive gaming, multi-domain composition, minimal platforms, constraint recovery, vocabulary-verified domains, progressive configuration, and self-improving operational loops.
+**Derivation engine confidence: HIGH.** The 16 kernel primitives provide a universal base. The 8 configuration dimensions parameterize the variation space. Interaction constraints prevent incoherent combinations. The 3 presets (Research, Personal Assistant, Experimental) provide pre-validated starting points. The system derives working configurations for research, therapy, competitive gaming, multi-domain composition, minimal platforms, constraint recovery, vocabulary-verified domains, progressive configuration, and self-improving operational loops.
diff --git a/reference/evolution-lifecycle.md b/reference/evolution-lifecycle.md
@@ -219,9 +219,9 @@ Questions the engine must answer when generating evolution-ready systems:
 
 #### The kernel is invariant across all evolution
 
-**Summary:** The 15 kernel primitives (markdown-yaml, wiki-links, moc-hierarchy, tree-injection, description-field, topics-footer, schema-enforcement, semantic-search, self-space, session-rhythm, unique-addresses, discovery-first, operational-learning-loop, task-stack, methodology-folder, session-capture) are the structural foundation. INVARIANT primitives (wiki links, schema enforcement, methodology folder, session capture) cannot be disabled. CONFIGURABLE primitives (self space, semantic search) can be toggled via /architect. Evolution adds on top of the kernel; it never removes or contradicts kernel primitives. A system that evolves away from prose-sentence titles, or stops requiring topics footers, or abandons self/ loading at session start has evolved into incoherence. The kernel is the stable core that makes everything above it interoperable.
+**Summary:** The 16 kernel primitives (markdown-yaml, wiki-links, moc-hierarchy, tree-injection, description-field, topics-footer, schema-enforcement, semantic-search, self-space, session-rhythm, unique-addresses, discovery-first, operational-learning-loop, task-stack, methodology-folder, session-capture) are the structural foundation. INVARIANT primitives (wiki links, schema enforcement, methodology folder, session capture) cannot be disabled. CONFIGURABLE primitives (self space, semantic search) can be toggled via /architect. Evolution adds on top of the kernel; it never removes or contradicts kernel primitives. A system that evolves away from prose-sentence titles, or stops requiring topics footers, or abandons self/ loading at session start has evolved into incoherence. The kernel is the stable core that makes everything above it interoperable.
 
-**Derivation Implication:** The generated context file should mark kernel primitives as invariant (not subject to user override or evolution drift). The reseed process should validate that all 15 kernel primitives remain intact. Evolution guidance should explicitly state: "You can add schema fields, create new MOC types, build new skills, and modify session workflow — but these 15 primitives are foundational and must not be removed."
+**Derivation Implication:** The generated context file should mark kernel primitives as invariant (not subject to user override or evolution drift). The reseed process should validate that all 16 kernel primitives remain intact. Evolution guidance should explicitly state: "You can add schema fields, create new MOC types, build new skills, and modify session workflow — but these 16 primitives are foundational and must not be removed."
 
 **Source:** kernel.yaml specification. The kernel was distilled from the vault's operational experience — these are the primitives that remained constant while everything else evolved.
 

diff --git a/reference/interaction-constraints.md b/reference/interaction-constraints.md
@@ -139,7 +139,7 @@ These produce friction but can work with compensating mechanisms:
 
 ### Kernel Primitive Constraints
 
-These constraints apply to the 15 kernel primitives and their INVARIANT/CONFIGURABLE status:
+These constraints apply to the 16 kernel primitives and their INVARIANT/CONFIGURABLE status:
 
 **INVARIANT primitives (always present, cannot be disabled):**
 

diff --git a/reference/kernel.yaml b/reference/kernel.yaml
@@ -1,4 +1,4 @@
-# Universal Kernel — Fifteen Universal Primitives
+# Universal Kernel — Sixteen Universal Primitives
 # Every system generated by arscontexta includes these.
 # The kernel is constant. The derivation engine varies everything above it.
 # Full automation is the default — users may opt down.

diff --git a/scripts/sync-thinking.sh b/scripts/sync-thinking.sh
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 #
 # sync-thinking.sh
-# Syncs the research graph from the vault into the bundled thinking/ directory.
+# Syncs the research graph from the vault into the bundled methodology/ directory.
 # Tracks added/removed/changed files and records the vault's git hash.
 #
 # Usage:
@@ -15,9 +15,9 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 VAULT_PATH="${VAULT_PATH:?Set VAULT_PATH to the vault root directory}"
-SOURCE_DIR="$VAULT_PATH/01_thinking"
-DEST_DIR="$PROJECT_ROOT/thinking"
-HASH_FILE="$PROJECT_ROOT/thinking/.vault-sync-hash"
+SOURCE_DIR="$VAULT_PATH/methodology"
+DEST_DIR="$PROJECT_ROOT/methodology"
+HASH_FILE="$PROJECT_ROOT/methodology/.vault-sync-hash"
 DRY_RUN=false
 
 if [[ "${1:-}" == "--dry-run" ]]; then

diff --git a/skills/help/SKILL.md b/skills/help/SKILL.md
@@ -137,7 +137,7 @@ Your system also learns from experience:
   /remember             Capture when something goes wrong
                         (your system remembers corrections)
   /ask [question]       Ask about [domain] -- answers draw
-                        from 249 methodology notes AND your
+                        from 244 methodology notes AND your
                         system's own methodology notes
 
 Type /help anytime for guidance.
@@ -312,7 +312,7 @@ Related:
 **Special case for /help ask:** Expand the "What it does" section to mention both knowledge layers:
 ```
 What it does:
-  Queries the bundled methodology knowledge base (249
+  Queries the bundled methodology knowledge base (244
   research claims) AND your local methodology notes
   in ops/methodology/. Answers are grounded in
   specific claims and applied to your system's

diff --git a/skills/reseed/SKILL.md b/skills/reseed/SKILL.md
@@ -209,7 +209,7 @@ Using `${CLAUDE_PLUGIN_ROOT}/reference/three-spaces.md`, verify the re-derived a
 
 ### Pass 5: Kernel validation (15 primitives)
 
-Using `${CLAUDE_PLUGIN_ROOT}/reference/derivation-validation.md`, verify the re-derived system will pass all 15 kernel primitives.
+Using `${CLAUDE_PLUGIN_ROOT}/reference/derivation-validation.md`, verify the re-derived system will pass all 16 kernel primitives.
 
 ---
 

diff --git a/skills/setup/SKILL.md b/skills/setup/SKILL.md
@@ -1,8 +1,8 @@
 ---
 name: setup
-description: Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".
+description: Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 16 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".
 context: fork
-model: sonnet
+model: opus
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
 argument-hint: "[--advanced for upfront dimension configuration]"
 ---
@@ -16,7 +16,7 @@ The difference is derivation: understanding WHO this person is, WHAT they need,
 Read these files to understand the methodology and available components. Read them BEFORE starting any phase.
 
 **Core references (always read):**
-- `${CLAUDE_PLUGIN_ROOT}/reference/kernel.yaml` -- the 15 kernel primitives (with enforcement levels)
+- `${CLAUDE_PLUGIN_ROOT}/reference/kernel.yaml` -- the 16 kernel primitives (with enforcement levels)
 - `${CLAUDE_PLUGIN_ROOT}/reference/interaction-constraints.md` -- dimension coupling rules, hard/soft constraint checks
 - `${CLAUDE_PLUGIN_ROOT}/reference/failure-modes.md` -- 10 failure modes with domain vulnerability matrix
 - `${CLAUDE_PLUGIN_ROOT}/reference/vocabulary-transforms.md` -- domain-native vocabulary mappings (6 transformation levels)
@@ -450,7 +450,7 @@ Structure the proposal as:
 2. Folder structure with their domain-named directories
 3. How their notes work -- with a specific example from their domain using their vocabulary
 4. How processing works, described in their words
-5. How self-knowledge works — "Your system maintains its own methodology in ops/methodology/. Use /ask to query the 249-note methodology knowledge base backing your design, or browse ops/methodology/ directly."
+5. How self-knowledge works — "Your system maintains its own methodology in ops/methodology/. Use /ask to query the 244-note methodology knowledge base backing your design, or browse ops/methodology/ directly."
 6. Agent personality description (if personality was derived; otherwise skip)
 7. What was intentionally excluded and why
 8. Any high-risk failure modes flagged

diff --git a/skills/setup/skill.json b/skills/setup/skill.json
@@ -1,6 +1,6 @@
 {
   "name": "knowledge-setup",
-  "description": "Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives.",
+  "description": "Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 16 kernel primitives.",
   "version": "0.4.0",
   "author": "arscontexta",
   "tags": [
-Original file line number
+Diff line change
@@ Expand Up @@
     ### Pass 5: Kernel validation (15 primitives)
-    Using `${CLAUDE_PLUGIN_ROOT}/reference/derivation-validation.md`, verify the re-derived system will pass all 15 kernel primitives.
+    Using `${CLAUDE_PLUGIN_ROOT}/reference/derivation-validation.md`, verify the re-derived system will pass all 16 kernel primitives.
     ---
@@ Expand Down @@