Merge branch 'feature/wiki-structure-hardening' into develop

Makefile

@@ -3,10 +3,10 @@
 # Orchestrates the setup and management of the knowledge base.
 # =============================================================================
 
-include config.env
+include globals.env
-export $(shell sed 's/=.*//' config.env)
+export $(shell grep -v '^[#[:space:]]' globals.env | sed 's/=.*//')
 
-.PHONY: setup add-genome status lint clean help
+.PHONY: setup add-genome status lint lock doctor sync help
 
 help:
 	@echo "Available commands:"
@@ -14,6 +14,9 @@ help:
 	@echo "  make add-genome    - Register and scaffold a new genome"
 	@echo "  make status        - Check submodule and encryption status"
 	@echo "  make lint          - Verify schema, privacy flags, and metadata"
+	@echo "  make lock          - Lock all encrypted files across all genomes"
+	@echo "  make doctor        - Verify all required tools are installed"
+	@echo "  make sync          - Sync submodules and report unpushed commits"
 
 lint:
 	@bash scripts/lint-genomes.sh
@@ -34,3 +37,25 @@ status:
 	@git submodule status
 	@echo "--- Encryption Status (First 10 files) ---"
 	@git-crypt status | head -n 10
+
+doctor:
+	@echo "Checking required tools..."
+	@command -v git        >/dev/null 2>&1 || { echo "  MISSING: git";        exit 1; }
+	@command -v git-crypt  >/dev/null 2>&1 || { echo "  MISSING: git-crypt";  exit 1; }
+	@command -v curl       >/dev/null 2>&1 || { echo "  MISSING: curl";       exit 1; }
+	@command -v jq         >/dev/null 2>&1 || { echo "  MISSING: jq";         exit 1; }
+	@command -v bw         >/dev/null 2>&1 || echo "  OPTIONAL: bw (Bitwarden CLI) not found — key injection will be manual."
+	@echo "System ready."
+
+sync:
+	@echo "Syncing submodules..."
+	@git submodule update --init --recursive
+	@echo "--- Unpushed commits per genome ---"
+	@git submodule foreach 'git log --oneline @{u}.. 2>/dev/null | head -5 || true'
+
+lock:
+	@echo "Locking master repository..."
+	@git-crypt lock 2>/dev/null || true
+	@echo "Locking all submodules..."
+	@git submodule foreach 'git-crypt lock 2>/dev/null || true'
+	@echo "All genomes securely locked."

README.md

@@ -1,201 +1,200 @@
 # Knowledge Genome System
 
-> A distributed, modular, and secure personal knowledge base architecture.
+> A distributed, modular, and secure personal knowledge base — no vector database required.
 
-The **Knowledge Genome System** is a framework designed to manage personal knowledge using a "Master-Genome" architecture. It follows the LLM-Wiki patterns (Karpathy-style) while adding a robust security layer for sensitive data and automated quality control.
+The **Knowledge Genome System** implements the [LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)
+by Andrej Karpathy, extended with a multi-domain submodule architecture, git-crypt
+encryption for sensitive data, and a human-in-the-loop Git Flow for quality control.
 
 ---
 
-# Architecture
+## Core Philosophy
 
-This project is structured as a **Master Orchestrator** that manages multiple independent **Genomes** via Git Submodules.
+Most RAG systems make the LLM rediscover knowledge from scratch on every query.
+This system is different: the LLM **incrementally builds and maintains a persistent wiki**
+that sits between you and the raw sources. Knowledge is compiled once and kept current —
+not re-derived on every question.
 
-## Core Components
+**This means: no vector database, no embedding pipeline, no external retrieval server.**
+The `wiki/index.md` of each genome is the retrieval layer. At moderate scale
+(~100 sources, hundreds of pages) this works better than RAG because cross-references,
+contradictions, and syntheses are already resolved — the LLM doesn't have to piece
+them together at query time.
 
-### Master Repository
+If the wiki grows beyond what the index can navigate efficiently, the only recommended
-
+search extension is [`qmd`](https://github.com/tobi/qmd) — a local, on-device
-Contains:
+BM25 + vector search engine for markdown files with an MCP server interface.
-
+No external infrastructure required.
-* Orchestration scripts
-* Global configuration (`config.env`)
-* Security templates
-
-### Genomes
-
-Individual specialized repositories (e.g. `genome-dev`, `genome-finance`) that act as standalone units of knowledge.
-
-### Security Layers
-
-#### Physical Security
-
-`git-crypt` encrypts `private/` directories at rest.
-
-#### Logical Security
-
-YAML frontmatter (`private: true`) prevents AI agents from leaking sensitive data during public sessions.
-
-#### Validation Layer
-
-A custom linting engine ensures metadata consistency.
 
 ---
 
-# Quick Start
+## Architecture
+
+```text
+master-knowledge-genome/          ← Root orchestrator
+├── core-karpathy/                ← LLM Wiki reference pattern (read-only submodule)
+├── genome-dev/                   ← Submodule: web dev, Angular, TUI
+├── genome-finance/               ← Submodule: personal finance
+├── genome-homelab/               ← Submodule: Keru infrastructure
+└── AGENTS.md                     ← Global coordination schema
+```
+
+Each genome is an independent repository with this structure:
+```text
+genome-{name}/
+├── raw/
+│   ├── articles/ transcripts/ code-packs/ assets/   ← Plaintext, open to collaborators
+│   └── private/                                      ← AES-256-CTR encrypted (git-crypt)
+├── wiki/
+│   ├── index.md  log.md                              ← Navigation and audit trail
+│   ├── sources/ entities/ concepts/ queries/         ← Agent-maintained knowledge
+│   └── private/                                      ← AES-256-CTR encrypted (git-crypt)
+└── AGENTS.md                                         ← Per-genome agent contract
+```
+
+---
 
 ## Prerequisites
 
-Required dependencies:
+**Required:**
+- `git`
+- `git-crypt`
+- `curl`
+- `jq`
 
-* `git`
+**Optional:**
-* `git-crypt`
+- `bw` (Bitwarden CLI) — for runtime key injection from Vaultwarden without writing keys to disk
-* `curl`
-* `jq`
 
-Optional:
+Install on Ubuntu/Debian:
-
+```bash
-* `bw` (Bitwarden CLI) — used for runtime key injection
+sudo apt update && sudo apt install -y git git-crypt curl jq
+```
 
 ---
 
-## Initialization
+## Quick Start
 
 ```bash
-# 1. Clone the master repository
+# 1. Clone this setup repository
-git clone <master-repo-url> && cd master-knowledge-genome
+git clone <setup-repo-url> knowledge-genome-setup
+cd knowledge-genome-setup
 
-# 2. Run the full setup
+# 2. Export your Forgejo token
-#    (checks dependencies, creates master scaffold,
+export FORGEJO_TOKEN="your_token_here"
-#    initializes genomes)
+
+# 3. Run full setup
 make setup
 ```
 
-# Management Commands
+`make setup` will:
+- Check all dependencies
+- Create the master and genome repositories on Forgejo
+- Scaffold the local directory structure with git-crypt active on `private/`
+- Install the pre-commit security hook in each genome
+- Export the symmetric git-crypt keys to `keys/`
 
-The system is controlled through a centralized Makefile.
+---
+
+## Management Commands
 
 | Command | Description |
-| ----------------- | -------------------------------------------------------------- |
+|---------|-------------|
-| `make setup`      | Full system initialization (Master + Registry Genomes).        |
+| `make setup` | Full system initialisation (master + all genomes defined in `config.env`) |
-| `make add-genome` | Scaffolds and registers a new genome (requires NAME and DESC). |
+| `make add-genome NAME=x DESC="y"` | Scaffold and register a new genome |
-| `make lint`       | Runs the validation suite across all genomes.                  |
+| `make lint` | Validate schema, privacy flags, and metadata across all genomes |
-| `make status`     | Checks Git status and encryption state for all submodules.     |
+| `make status` | Show git submodule status and first 10 git-crypt encryption states |
+| `make help` | Show all available targets |
 
-# Validation & Linting (`make lint`)
+**Adding a new genome example:**
-
+```bash
-The built-in linter ensures that the knowledge base remains machine-readable and secure.
+make add-genome NAME=genome-research DESC="Academic papers, deep-dives, open research"
-
-It automatically validates:
-
-## Frontmatter Integrity
-
-Every `.md` file must contain valid YAML headers.
-
-## Domain Consistency
-
-Ensures that a file's domain metadata matches its parent genome.
-
-## Privacy Leak Detection
-
-Critical validation step.
-
-Verifies that any file located in a `/private/` directory contains the flag:
-
-```yaml
-private: true
 ```
 
-This prevents accidental exposure during AI sessions.
+---
 
-## Broken Wiki-Links
+## Security Model
 
-Detects dead `[[internal-links]]`.
+### Hybrid Privacy Architecture
 
-# Security Model
+Each genome has two layers:
 
-## Hybrid Privacy Architecture
+| Layer | Directories | Access |
+|-------|-------------|--------|
+| Public | `raw/articles/`, `raw/transcripts/`, `wiki/sources/`, `wiki/concepts/` | Plaintext — safe for collaborators |
+| Private | `raw/private/`, `wiki/private/` | AES-256-CTR via git-crypt — owner only |
 
-Each genome is divided into two layers.
+On the remote (Forgejo), private files are opaque binary blobs.
+Collaborators without the key can contribute normally to public directories
+— git handles the encrypted files transparently with no errors.
 
-### Public Layer
+### Runtime Key Injection
 
-Directories:
+Encryption keys are never stored as persistent files on the AI server.
-
+They are injected at session start via the Bitwarden CLI (`bw`) against
-```text
+your self-hosted Vaultwarden instance, using process substitution:
-raw/public/
-wiki/public/
-```
-
-Characteristics:
-
-* Plaintext
-* Shareable with collaborators
-
-### Private Layer
-
-Directories:
-
-```text
-raw/private/
-wiki/private/
-```
-
-Characteristics:
-
-* Encrypted using AES-256 via `git-crypt`
-
-## Runtime Key Injection
-
-To keep the AI environment secure, encryption keys are never stored on the VM disk.
-
-Instead, the system uses Bitwarden (`bw`) / Vaultwarden for runtime injection.
-
-### Example
 
 ```bash
-# Unlock a genome using a key stored in Vaultwarden
+# Key lives only in a kernel file descriptor — never touches disk
 git-crypt unlock <(
-  bw get notes "genome-dev key" \
+  bw get notes "genome-dev key" --session "$BW_SESSION" | base64 -d
-    --session "$BW_SESSION" | base64 -d
 )
 ```
 
-# Genome Schema
+**Use `bw` (standard Bitwarden CLI), not `bws`.**
+`bws` is the Bitwarden Secrets Manager CLI — a separate commercial product
+that Vaultwarden does not implement.
 
-All wiki documents follow a strict schema to support AI ingestion.
+### Pre-commit Hook
 
-## YAML Frontmatter Schema
+A security hook is installed in every genome's `.git/hooks/pre-commit`.
+It inspects every staged file: if any file in `raw/private/` or `wiki/private/`
+is not encrypted by git-crypt, the commit is blocked with a clear error message
+explaining how to fix the issue.
 
-```yaml
+### Key Rotation
----
+
-title: "Document Title"
+If a key is lost or compromised:
-type: entity | concept | source | log
+```bash
-domain: genome-name
+source lib/git-crypt.sh
-private: true/false
+cd ~/knowledge-genome-setup/genome-dev
-last_updated: YYYY-MM-DD
+gcrypt_rotate_key "genome-dev"
----
 ```
+The function decrypts all private files, generates a new key, re-encrypts,
+and prints instructions for updating Vaultwarden.
 
-# Agent Interaction
+---
 
-When starting a session with an AI agent, always declare the privacy context.
+## Agent Interaction
 
-## Public Context
+At the start of every AI session, declare the privacy context explicitly:
 
 ```text
 PRIVATE_CONTEXT: disabled
 ```
-
+The agent ignores all `private/` directories. Outputs are safe to share.
-Behavior:
-
-* The agent ignores all private folders.
-
-## Private Context
 
 ```text
 PRIVATE_CONTEXT: enabled
 ```
+The agent processes encrypted data. Requires the genome to be unlocked.
+All outputs referencing private data are prefixed with `[PRIVATE DATA INCLUDED]`.
 
-Behavior:
+---
 
-* The agent processes encrypted data.
+## Knowledge Quality
-* Requires the repository to be unlocked.
+
+The system includes three quality mechanisms drawn directly from the LLM Wiki pattern:
+
+**Conflict Resolution** — when new evidence contradicts existing wiki content,
+the agent creates a `wiki/queries/conflict-*.md` node instead of silently overwriting.
+Human review required before merging.
+
+**Knowledge Decay** — pages with `maturity: stable` not updated in 6 months,
+and `maturity: draft` pages not updated in 3 months, are flagged during lint passes
+with a `⚠️ STALE` callout. The agent proposes re-validation but does not change
+maturity without new source evidence.
+
+**Cross-Genome Lint** — once a month, a manual session passes the aggregated index
+of all genomes to the agent to detect concept duplication and missing cross-references.
+No automated LLM controller in CI/CD — the cost in tokens and complexity is not
+justified at this scale.

config.env

@@ -1,39 +0,0 @@
-#!/usr/bin/env bash
-# =============================================================================
-# config.env
-# Single Source of Truth for the Knowledge Genome Framework.
-# =============================================================================
-
-# --- PROVIDER SELECTION ---
-PROVIDER="forgejo"  # Options: "forgejo", "github"
-
-# --- FORGEJO CONFIGURATION ---
-FORGEJO_URL="https://git.keruhomelab.com"
-FORGEJO_USER="keru"
-# Note: FORGEJO_TOKEN must be exported in your shell for security.
-
-# --- VAULTWARDEN CONFIGURATION ---
-# Used for rendering template instructions
-VAULTWARDEN_URL="https://vault.keruhomelab.com"
-
-# --- MASTER REPOSITORY ---
-MASTER_REPO="master-knowledge-genome"
-GIST_URL="https://gist.github.com/442a6bf555914893e9891c11519de94f.git"
-
-# --- GENOME REGISTRY ---
-# Format: "name|description"
-GENOMES=(
-  "genome-dev|Web development, TUI, Angular, software architecture"
-  "genome-finance|Personal finance, investments, market analysis"
-  "genome-homelab|Keru infrastructure, network configs, architecture logs"
-)
-
-# --- SYSTEM PATHS ---
-WORK_DIR="${HOME}/knowledge-genome-setup"
-KEYS_DIR="${WORK_DIR}/keys"
-
-# Core directory resolution (DO NOT CHANGE)
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-TEMPLATES_DIR="${SCRIPT_DIR}/templates"
-LIB_DIR="${SCRIPT_DIR}/lib"
-PROVIDERS_DIR="${SCRIPT_DIR}/providers"

globals.env

@@ -0,0 +1,25 @@
+# =============================================================================
+# globals.env
+# Static configuration — pure KEY=VALUE.
+# Safe to: make include, docker-compose, env parsers, shell source.
+# =============================================================================
+
+# --- PROVIDER SELECTION ---
+PROVIDER=forgejo
+
+# --- FORGEJO ---
+FORGEJO_URL=https://git.keruhomelab.com
+FORGEJO_USER=keru
+FORGEJO_SSH_PORT=222
+
+# --- GITHUB (used when PROVIDER=github) ---
+# GITHUB_USER=your-username
+# GITHUB_ORG=your-org       # Optional: set only for org repos; overrides GITHUB_USER
+# Note: GITHUB_TOKEN must be exported in your shell for security.
+
+# --- VAULTWARDEN ---
+VAULTWARDEN_URL=https://vault.keruhomelab.com
+
+# --- MASTER REPOSITORY ---
+MASTER_REPO=master-knowledge-genome
+GIST_URL=https://gist.github.com/442a6bf555914893e9891c11519de94f.git

lib/deps.sh

@@ -16,10 +16,10 @@ check_deps() {
 
   if [[ ${#missing[@]} -gt 0 ]]; then
     error "Missing required tools: ${missing[*]}"
-    echo -e "\nInstall them using your package manager:"
+    printf "\nInstall them using your package manager:\n"
-    echo "  Debian/Ubuntu: sudo apt install ${missing[*]}"
+    printf "  Debian/Ubuntu: sudo apt install %s\n" "${missing[*]}"
-    echo "  MacOS:         brew install ${missing[*]}"
+    printf "  MacOS:         brew install %s\n"     "${missing[*]}"
-    exit 1
+    return 1
   fi
 
   success "Environment check passed: all required tools found."

lib/git-crypt.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 # =============================================================================
 # lib/git-crypt.sh
-# git-crypt lifecycle management (init, export, verify).
+# git-crypt lifecycle management (init, export, verify, rotate).
 # =============================================================================
 
 gcrypt_init() {
@@ -16,7 +16,7 @@ gcrypt_export_key() {
   mkdir -p "${KEYS_DIR}"
   git-crypt export-key "$key_path"
   success "Symmetric key exported to: $key_path"
-  warn "Action required: Store this key in Vaultwarden and remove it from local disk."
+  warn "SECURITY ALERT: Move this key to Vaultwarden and delete it from disk immediately."
 }
 
 gcrypt_verify() {
@@ -26,21 +26,135 @@ gcrypt_verify() {
   info "Verifying git-crypt status for ${genome_name}..."
   git-crypt lock
 
-  # Checking if the private marker is still encrypted (binary check)
   if file "raw/private/.gitkeep" 2>/dev/null | grep -q "data"; then
     success "Encryption verified: private/ directory is protected."
   else
-    warn "Encryption check inconclusive. Please run 'git-crypt status' manually."
+    warn "Encryption check inconclusive. Run 'git-crypt status' manually."
   fi
 
   [[ -f "$key_path" ]] && git-crypt unlock "$key_path"
 }
 
+# ---------------------------------------------------------------------------
+# gcrypt_rotate_key <genome_name>
+# Rotates the git-crypt symmetric key for the current genome directory.
+#
+# WHAT THIS DOES:
+#   1. Unlocks the repo with the existing key (working tree is decrypted).
+#   2. Removes the old key material from .git/git-crypt/keys/.
+#   3. Runs git-crypt init to generate a new symmetric key.
+#   4. Stages and commits private files — they are re-encrypted with the new key.
+#   5. Exports the new key to KEYS_DIR for Vaultwarden upload.
+#
+# WHAT THIS DOES NOT DO (limitation):
+#   Git history still contains blobs encrypted with the OLD key. Anyone who
+#   has the old key and access to the git history can still decrypt those blobs.
+#   To purge old encrypted blobs from history entirely, run git-filter-repo
+#   separately after this function completes (manual step — not automated here
+#   because it rewrites all commit hashes and requires force-pushing).
+#
+# USAGE:
+#   source lib/git-crypt.sh
+#   cd ~/knowledge-genome-setup/genome-dev
+#   gcrypt_rotate_key "genome-dev"
+#
+# REQUIRES:
+#   - The old key file at KEYS_DIR/<genome_name>.key  OR  the repo is already unlocked.
+#   - Clean working tree (no uncommitted changes outside private/).
+# ---------------------------------------------------------------------------
+gcrypt_rotate_key() {
+  local genome_name="$1"
+  local old_key_path="${KEYS_DIR}/${genome_name}.key"
+  local new_key_name="${genome_name}-rotated-$(date +%Y%m%d)"
+
+  step "Key rotation: ${genome_name}"
+
+  warn "SCOPE: this rotates the key for future commits only."
+  warn "       Old git history retains blobs encrypted with the previous key."
+  warn "       See function header in git-crypt.sh for full purge instructions."
+  echo ""
+
+  # 1. Unlock with old key (if not already unlocked)
+  if git-crypt status 2>/dev/null | grep -q "encrypted"; then
+    info "Repository appears to be locked. Attempting unlock..."
+    if [[ -f "$old_key_path" ]]; then
+      git-crypt unlock "$old_key_path"
+      success "Unlocked with existing key."
+    else
+      error "Old key not found at: ${old_key_path}"
+      error "Unlock manually before rotating: git-crypt unlock /path/to/${genome_name}.key"
+      return 1
+    fi
+  else
+    info "Repository is already unlocked — proceeding."
+  fi
+
+  # 2. Ensure working tree is clean (private files excluded — they will be re-staged)
+  if ! git diff --quiet -- ':!raw/private' ':!wiki/private' 2>/dev/null; then
+    error "Working tree has uncommitted changes outside private/. Commit or stash them first."
+    return 1
+  fi
+
+  # 3. Remove old key material only (preserves .git/git-crypt/ structure)
+  info "Removing old key material..."
+  rm -rf .git/git-crypt/keys
+  success "Old key material removed."
+
+  # 4. Re-initialize git-crypt (generates a new symmetric key)
+  info "Initializing new symmetric key..."
+  git-crypt init
+  success "New key generated."
+
+  # 5. Re-stage private files so they are committed encrypted with the new key
+  local staged=0
+  if compgen -G "raw/private/*" > /dev/null 2>&1; then
+    git add raw/private/
+    staged=1
+  fi
+  if compgen -G "wiki/private/*" > /dev/null 2>&1; then
+    git add wiki/private/
+    staged=1
+  fi
+
+  if [[ $staged -eq 1 ]]; then
+    # Exclude .gitkeep-only commits — only commit if real content exists
+    if ! git diff --cached --quiet; then
+      git commit -m "security: rotate git-crypt key for ${genome_name}"
+      success "Private files re-committed with new key."
+    else
+      info "Only .gitkeep files in private/ — no content commit needed."
+    fi
+  else
+    info "No private files found to re-encrypt."
+  fi
+
+  # 6. Export new key
+  gcrypt_export_key "$new_key_name"
+
+  echo ""
+  success "Key rotation complete for: ${genome_name}"
+  echo ""
+  warn "NEXT STEPS:"
+  echo "  1. Push the new commit:  git push origin main"
+  echo "  2. Upload the new key to Vaultwarden:"
+  echo "       base64 < ${KEYS_DIR}/${new_key_name}.key"
+  echo "       → Secure Note name: \"${genome_name} key\"  (replace existing)"
+  echo "  3. Delete both key files from disk:"
+  echo "       rm ${KEYS_DIR}/${genome_name}.key"
+  echo "       rm ${KEYS_DIR}/${new_key_name}.key"
+  echo "  4. Revoke access from any previous key holders."
+  echo "  5. For full history purge (removes old encrypted blobs from git history):"
+  echo "       git filter-repo --invert-paths --path raw/private --path wiki/private"
+  echo "       git push --force origin main"
+  echo "       (⚠ rewrites all commit hashes — coordinate with any collaborators)"
+  echo ""
+}
+
 gcrypt_print_key_instructions() {
   local genome_name="$1"
   local v_url="${VAULTWARDEN_URL:-https://your-vaultwarden.com}"
 
-  echo -e "\n  ── ${BOLD}Key Management: ${genome_name}${NC} ──\n"
+  printf "\n  ── %b ──\n\n" "${BOLD}Key Management: ${genome_name}${NC}"
   echo "  1. Encode the key to base64:"
   echo "       base64 < ${KEYS_DIR}/${genome_name}.key"
   echo ""
@@ -48,9 +162,16 @@ gcrypt_print_key_instructions() {
   echo "       Name: \"${genome_name} key\""
   echo "       Note: <paste the base64 string>"
   echo ""
-  echo "  3. For AI Server / Runtime Injection:"
+  echo "  3. Delete from disk:"
-  echo "       export BW_SESSION=\$(bw unlock --raw)"
+  echo "       rm ${KEYS_DIR}/${genome_name}.key"
+  echo ""
+  echo "  4. Runtime injection on AI server (no key on disk):"
+  echo "       bw config server ${v_url}"
+  echo "       export BW_SESSION=\$(bw unlock --passwordenv BW_MASTER_PASSWORD --raw)"
   echo "       git-crypt unlock <(bw get notes \"${genome_name} key\" --session \"\$BW_SESSION\" | base64 -d)"
+  echo ""
+  echo "     NOTE: use 'bw' (standard Bitwarden CLI), NOT 'bws'."
+  echo "     'bws' is the Secrets Manager CLI and does not work with Vaultwarden."
 }
 
 gcrypt_print_runtime_model() {
@@ -67,13 +188,13 @@ gcrypt_print_runtime_model() {
   echo "    smudge filter. Obsidian reads them as normal Markdown."
   echo ""
   echo "  On the AI VM:"
-  echo "    Same as laptop when unlocked. Use runtime injection (step 5"
+  echo "    Same as laptop when unlocked. Use runtime injection so the"
-  echo "    above) so the key is never written to disk."
+  echo "    key is never written to disk."
   echo ""
   echo "  Limitation:"
   echo "    Encryption does NOT protect against a full server compromise"
-  echo "    where an attacker has root access to a machine where the repo"
+  echo "    where an attacker has root access to an already-unlocked repo."
-  echo "    is already unlocked. Runtime injection mitigates this."
+  echo "    Runtime injection mitigates this risk."
   echo "  ─────────────────────────────────────────────────────────────"
   echo ""
 }

lib/lint.sh

@@ -4,20 +4,31 @@
 # Validation logic for Knowledge Genome files.
 # =============================================================================
 
-# Validates YAML frontmatter and mandatory fields
+# Valid values for the 'type' frontmatter field.
+# Must stay in sync with the type list in templates/agents-genome.md.
+# Note: 'index' and 'log' are wiki-level singleton files (wiki/index.md, wiki/log.md).
+#       'conflict' has no dedicated scaffold directory — it is a cross-cutting type
+#       that can live under any wiki/ subdirectory.
+VALID_TYPES=("source" "entity" "concept" "query" "conflict" "private" "index" "log")
+
+# ---------------------------------------------------------------------------
+# lint_markdown_file <file> <genome_name>
+# Validates YAML frontmatter: delimiters, mandatory fields, domain, type value.
+# Returns the number of errors found.
+# ---------------------------------------------------------------------------
 lint_markdown_file() {
   local file="$1"
   local genome_name="$2"
   local errors=0
 
-  # 1. Check Frontmatter delimiters
+  # 1. Check frontmatter delimiters
   if [[ $(head -n 1 "$file") != "---" ]]; then
     warn "Missing frontmatter start (---) in: $file"
     errors=$((errors + 1))
   fi
 
   # 2. Check mandatory fields
-  local mandatory_fields=("title:" "type:" "domain:")
+  local mandatory_fields=("title:" "type:" "domain:" "maturity:" "last_updated:")
   for field in "${mandatory_fields[@]}"; do
     if ! grep -q "^${field}" "$file"; then
       warn "Missing mandatory field '${field}' in: $file"
@@ -25,52 +36,165 @@ lint_markdown_file() {
     fi
   done
 
-  # 3. Check if domain matches the genome name
+  # 3. Check domain matches genome name
   if grep -q "^domain:" "$file" && ! grep -q "^domain: ${genome_name}" "$file"; then
-    warn "Domain mismatch in $file (expected ${genome_name})"
+    warn "Domain mismatch in $file (expected '${genome_name}')"
     errors=$((errors + 1))
   fi
 
+  # 4. Validate type value against allowed list
+  local type_errors
+  check_valid_type "$file"
+  type_errors=$?
+  errors=$((errors + type_errors))
+
   return $errors
 }
 
-# Ensures files in private/ directories have the 'private: true' flag
+# ---------------------------------------------------------------------------
+# check_valid_type <file>
+# Verifies that the 'type' field contains a value from VALID_TYPES.
+# Returns 1 if invalid, 0 if valid or field absent (absence caught by lint_markdown_file).
+# ---------------------------------------------------------------------------
+check_valid_type() {
+  local file="$1"
+
+  local type_value
+  type_value=$(grep "^type:" "$file" | head -1 | sed 's/^type:[[:space:]]*//' | tr -d '"')
+
+  [[ -z "$type_value" ]] && return 0   # absence is caught upstream
+
+  local valid=0
+  for t in "${VALID_TYPES[@]}"; do
+    [[ "$type_value" == "$t" ]] && valid=1 && break
+  done
+
+  if [[ $valid -eq 0 ]]; then
+    warn "Invalid type value '${type_value}' in: $file"
+    warn "  Valid types: ${VALID_TYPES[*]}"
+    return 1
+  fi
+
+  return 0
+}
+
+# ---------------------------------------------------------------------------
+# check_privacy_consistency <file>
+# Ensures files in private/ directories carry 'private: true'.
+# Warns if a public file is incorrectly marked private.
+# ---------------------------------------------------------------------------
 check_privacy_consistency() {
   local file="$1"
   local errors=0
 
   if [[ "$file" == *"/private/"* ]]; then
     if ! grep -q "^private: true" "$file"; then
-      error "Privacy Leak: $file is in a private folder but lacks 'private: true' metadata."
+      error "Privacy leak: $file is in a private/ directory but lacks 'private: true'."
       errors=$((errors + 1))
     fi
   else
     if grep -q "^private: true" "$file"; then
-      warn "Metadata Mismatch: $file is marked private but located in a public directory."
+      warn "Metadata mismatch: $file is marked 'private: true' but is in a public directory."
-      # We count this as a warning unless you want to force strict isolation
     fi
   fi
 
   return $errors
 }
 
-# Basic check for internal wiki-links [[target]]
+# ---------------------------------------------------------------------------
+# check_knowledge_decay <file>
+# Reads 'maturity' and 'last_updated' from frontmatter and compares against
+# the staleness thresholds defined in agents-genome.md:
+#   maturity: stable  → flag if last_updated > 180 days ago
+#   maturity: draft   → flag if last_updated > 90 days ago
+#
+# Returns 1 if the file is stale, 0 otherwise.
+# Silently skips files with missing or unparseable date fields.
+# ---------------------------------------------------------------------------
+check_knowledge_decay() {
+  local file="$1"
+
+  local last_updated maturity
+  last_updated=$(grep "^last_updated:" "$file" | head -1 | sed 's/^last_updated:[[:space:]]*//' | tr -d '"')
+  maturity=$(grep "^maturity:" "$file" | head -1 | sed 's/^maturity:[[:space:]]*//' | tr -d '"')
+
+  # Skip if either field is absent or maturity is not decay-trackable
+  [[ -z "$last_updated" || -z "$maturity" ]] && return 0
+  [[ "$maturity" != "stable" && "$maturity" != "draft" ]] && return 0
+
+  # Parse date — handle both GNU date (Linux) and BSD date (macOS)
+  local updated_ts
+  if date --version >/dev/null 2>&1; then
+    # GNU date
+    updated_ts=$(date -d "$last_updated" +%s 2>/dev/null)
+  else
+    # BSD date (macOS)
+    updated_ts=$(date -j -f "%Y-%m-%d" "$last_updated" +%s 2>/dev/null)
+  fi
+
+  [[ -z "$updated_ts" ]] && return 0   # unparseable date — skip silently
+
+  local now days_old threshold
+  now=$(date +%s)
+  days_old=$(( (now - updated_ts) / 86400 ))
+
+  case "$maturity" in
+    stable) threshold=180 ;;
+    draft)  threshold=90  ;;
+  esac
+
+  if [[ $days_old -gt $threshold ]]; then
+    warn "STALE: $file"
+    warn "  maturity: ${maturity} | last_updated: ${last_updated} | ${days_old} days ago (threshold: ${threshold})"
+    return 1
+  fi
+
+  return 0
+}
+
+# ---------------------------------------------------------------------------
+# check_page_size <file>
+# Enforces the page length limits defined in agents-genome.md:
+#   soft cap: 400 lines  → warn
+#   hard cap: 800 lines  → error
+# These limits ensure pages fit within the LLM context window without
+# attention degradation and keep the wiki atomically navigable.
+# ---------------------------------------------------------------------------
+check_page_size() {
+  local file="$1"
+  local lines
+  lines=$(wc -l < "$file")
+
+  if [[ $lines -gt 800 ]]; then
+    error "Page too long (${lines} lines, hard cap 800): $file"
+    error "  Split this page into focused sub-pages and link them."
+    return 1
+  elif [[ $lines -gt 400 ]]; then
+    warn "Page approaching limit (${lines} lines, soft cap 400): $file"
+  fi
+
+  return 0
+}
+
+# ---------------------------------------------------------------------------
+# check_broken_links <file>
+# Basic check for internal [[wikilinks]] that cannot be resolved locally.
+# Only emits warnings — cross-genome links may legitimately not resolve here.
+# ---------------------------------------------------------------------------
 check_broken_links() {
   local file="$1"
   local base_dir
   base_dir=$(dirname "$file")
 
-  # Extract links, stripping aliases: [[Link|Alias]] -> Link
+  # Extract link targets, stripping aliases: [[Link|Alias]] -> Link
   local links
-  links=$(grep -oP '\[\[\K[^\]]+' "$file" | cut -d'|' -f1)
+  links=$(grep -oE '\[\[[^\]]+' "$file" 2>/dev/null | sed 's/^\[\[//' | cut -d'|' -f1)
 
   for link in $links; do
     local target="$link"
     [[ "$target" != *.md ]] && target="${target}.md"
 
-    # Simple relative check
     if [[ ! -f "${base_dir}/${target}" && ! -f "${base_dir}/../${target}" ]]; then
-      # Only a warning as links might point to other genomes or deep structures
       warn "Potential broken link: [[$link]] in $file"
     fi
   done

lib/output.sh

@@ -15,11 +15,12 @@ else
   GREEN='' YELLOW='' CYAN='' RED='' BOLD='' NC=''
 fi
 
-info()    { echo -e "${CYAN}[INFO]${NC}    $*"; }
+info()    { printf "%b\n"   "${CYAN}[INFO]${NC}    $*"; }
-success() { echo -e "${GREEN}[OK]${NC}      $*"; }
+success() { printf "%b\n"   "${GREEN}[OK]${NC}      $*"; }
-warn()    { echo -e "${YELLOW}[WARN]${NC}    $*"; }
+warn()    { printf "%b\n"   "${YELLOW}[WARN]${NC}    $*"; }
-error()   { echo -e "${RED}[ERROR]${NC}   $*" >&2; }
+error()   { printf "%b\n"   "${RED}[ERROR]${NC}   $*" >&2; }
-step()    { echo -e "\n${BOLD}${YELLOW}━━━ $* ━━━${NC}"; }
+die()     { error "$*"; exit 1; }
+step()    { printf "\n%b\n" "${BOLD}${YELLOW}━━━ $* ━━━${NC}"; }
 
 box() {
   local max_len=0
@@ -28,9 +29,9 @@ box() {
   done
   local border
   border=$(printf '─%.0s' $(seq 1 $((max_len + 2))))
-  echo -e "${CYAN}┌${border}┐${NC}"
+  printf "%b\n" "${CYAN}┌${border}┐${NC}"
   for line in "$@"; do
     printf "${CYAN}│${NC} %-${max_len}s ${CYAN}│${NC}\n" "$line"
   done
-  echo -e "${CYAN}└${border}┘${NC}"
+  printf "%b\n" "${CYAN}└${border}┘${NC}"
 }

lib/scaffold.sh

@@ -8,14 +8,17 @@ render_template() {
   local template_file="$1"
   local output_file="$2"
 
-  [[ ! -f "$template_file" ]] && { error "Template not found: ${template_file}"; exit 1; }
+  [[ ! -f "$template_file" ]] && { error "Template not found: ${template_file}"; return 1; }
 
   local content
-  content=$(cat "$template_file")
+  content=$(<"$template_file")
+
+  local genome_name_upper
+  genome_name_upper=$(tr '[:lower:]' '[:upper:]' <<< "${GENOME_NAME}")
 
   # Placeholder replacement
   content="${content//\{\{GENOME_NAME\}\}/${GENOME_NAME}}"
-  content="${content//\{\{GENOME_NAME_UPPER\}\}/${GENOME_NAME^^}}"
+  content="${content//\{\{GENOME_NAME_UPPER\}\}/${genome_name_upper}}"
   content="${content//\{\{GENOME_DESC\}\}/${GENOME_DESC}}"
   content="${content//\{\{FORGEJO_URL\}\}/${FORGEJO_URL}}"
   content="${content//\{\{FORGEJO_USER\}\}/${FORGEJO_USER}}"

providers/forgejo.sh

@@ -31,8 +31,8 @@ provider_create_repo() {
   case "$http_code" in
     201) success "Repository '${name}' created successfully." ;;
     409) info    "Repository '${name}' already exists - skipping." ;;
-    401) error   "Unauthorized. Check your FORGEJO_TOKEN."; exit 1 ;;
+    401) error   "Unauthorized. Check your FORGEJO_TOKEN."; return 1 ;;
-    *)   error   "Forgejo API returned HTTP ${http_code}. Check connectivity."; exit 1 ;;
+    *)   error   "Forgejo API returned HTTP ${http_code}. Check connectivity."; return 1 ;;
   esac
 }
 
@@ -44,8 +44,7 @@ provider_ssh_url() {
   local host
   # Extract hostname by removing protocol and trailing slashes
   host=$(echo "${FORGEJO_URL}" | sed -e 's|^[^/]*//||' -e 's|/*$||')
-  # Using port 222 as default for many homelab Forgejo/Gitea setups
+  echo "ssh://git@${host}:${FORGEJO_SSH_PORT:-222}/${FORGEJO_USER}/${1}.git"
-  echo "ssh://git@${host}:222/${FORGEJO_USER}/${1}.git"
 }
 
 provider_web_url() {

providers/github.sh

@@ -37,7 +37,7 @@ provider_create_repo() {
   case "$http_code" in
     201) success "Repository '${name}' created on GitHub." ;;
     422) info    "Repository '${name}' already exists - skipping." ;;
-    *)   error   "GitHub API returned HTTP ${http_code}. check token/permissions."; exit 1 ;;
+    *)   error   "GitHub API returned HTTP ${http_code}. Check token/permissions."; return 1 ;;
   esac
 }
 

registry.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+# =============================================================================
+# registry.sh - Knowledge Genome Registry
+# Dynamic paths and genome definitions.
+# =============================================================================
+
+# Guard against double sourcing
+[[ -n "${_REGISTRY_LOADED:-}" ]] && return
+_REGISTRY_LOADED=1
+
+# Resolve project root relative to this file
+PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Dynamic paths
+WORK_DIR="${HOME}/knowledge-genome-setup"
+KEYS_DIR="${WORK_DIR}/keys"
+TEMPLATES_DIR="${PROJECT_ROOT}/templates"
+LIB_DIR="${PROJECT_ROOT}/lib"
+PROVIDERS_DIR="${PROJECT_ROOT}/providers"
+
+# --- GENOME REGISTRY ---
+# Format: "name|description"
+GENOMES=(
+  "genome-dev|Web development, TUI, Angular, software architecture"
+  "genome-finance|Personal finance, investments, market analysis"
+  "genome-homelab|Keru infrastructure, network configs, architecture logs"
+)

scripts/add-genome.sh

@@ -2,12 +2,12 @@
 # =============================================================================
 # scripts/add-genome.sh
 # Helper to add a single new genome to the existing infrastructure.
-# Usage: make add-genome NAME=my-new-genome DESC="Description here"
 # =============================================================================
 
 set -euo pipefail
 source "lib/output.sh"
-source "config.env"
+source "globals.env"
+source "registry.sh"
 
 GENOME_NAME="${1:-}"
 GENOME_DESC="${2:-}"
@@ -20,10 +20,8 @@ fi
 
 step "Adding New Genome: ${GENOME_NAME}"
 
-# Overwrite the GENOMES array for this session to process only the new one
+GENOMES=("${GENOME_NAME}|${GENOME_DESC}")
-export GENOMES=("${GENOME_NAME}|${GENOME_DESC}")
 
-# Trigger the standard genome setup logic
+source "scripts/setup-genomes.sh"
-bash "scripts/setup-genomes.sh"
 
 success "Genome '${GENOME_NAME}' added and linked successfully!"

scripts/lint-genomes.sh

@@ -2,37 +2,56 @@
 # =============================================================================
 # scripts/lint-genomes.sh
 # Executes quality control across all registered genomes.
+# Iterates from the GENOMES registry in registry.sh — not from filesystem patterns —
+# so all genomes are covered regardless of their naming convention.
 # =============================================================================
 
 set -euo pipefail
 source "lib/output.sh"
-source "config.env"
+source "globals.env"
+source "registry.sh"
 source "lib/lint.sh"
 
 step "Starting Knowledge Genome Linting"
 
 TOTAL_ERRORS=0
+TOTAL_STALE=0
 
-# Iterate through genome submodules inside the Master repo
+for entry in "${GENOMES[@]}"; do
-for genome_dir in "${WORK_DIR}/${MASTER_REPO}"/genome-*/; do
+    IFS='|' read -r GENOME_NAME _ <<< "$entry"
-    [[ -d "$genome_dir" ]] || continue
+    genome_dir="${WORK_DIR}/${MASTER_REPO}/${GENOME_NAME}"
+
+    if [[ ! -d "$genome_dir" ]]; then
+        warn "Genome directory not found locally, skipping: ${genome_dir}"
+        continue
+    fi
 
-    GENOME_NAME=$(basename "$genome_dir")
     info "Auditing genome: ${GENOME_NAME}..."
 
-    # Find all .md files, excluding AGENTS.md and external references
+    # Lint all .md files except AGENTS.md and core-karpathy reference
     while IFS= read -r md_file; do
-        # Run validations
-        lint_markdown_file "$md_file" "$GENOME_NAME" || TOTAL_ERRORS=$((TOTAL_ERRORS + $?))
-        check_privacy_consistency "$md_file" || TOTAL_ERRORS=$((TOTAL_ERRORS + $?))
-        check_broken_links "$md_file"
 
-    done < <(find "$genome_dir" -name "*.md" ! -name "AGENTS.md" ! -path "*/core-karpathy/*")
+        lint_markdown_file "$md_file" "$GENOME_NAME" && fe=0   || fe=$?
+        check_privacy_consistency "$md_file"          && pce=0  || pce=$?
+        check_page_size "$md_file"                    && pse=0  || pse=$?
+        TOTAL_ERRORS=$((TOTAL_ERRORS + fe + pce + pse))
+
+        check_knowledge_decay "$md_file"              && stale=0 || stale=$?
+        TOTAL_STALE=$((TOTAL_STALE + stale))
+
+        check_broken_links "$md_file" || true   # warnings only, never contributes to errors
+
+    done < <(find "$genome_dir" -name "*.md" \
+                ! -name "AGENTS.md" \
+                ! -path "*/core-karpathy/*")
 done
 
-if [[ $TOTAL_ERRORS -eq 0 ]]; then
+echo ""
-    success "Linting passed: All files are consistent and secure."
+if [[ $TOTAL_ERRORS -eq 0 && $TOTAL_STALE -eq 0 ]]; then
+    success "Linting passed: all files are consistent, secure, and current."
+elif [[ $TOTAL_ERRORS -eq 0 && $TOTAL_STALE -gt 0 ]]; then
+    warn "Linting passed with ${TOTAL_STALE} stale file(s). Review and re-validate flagged pages."
 else
-    error "Linting failed: Found ${TOTAL_ERRORS} critical issues."
+    error "Linting failed: ${TOTAL_ERRORS} critical issue(s), ${TOTAL_STALE} stale file(s)."
     exit 1
 fi

scripts/setup-genomes.sh

@@ -2,12 +2,16 @@
 # =============================================================================
 # scripts/setup-genomes.sh
 # Iterates through the GENOMES registry to provision remote and local repos.
-# Handles git-crypt initialization and submodule linking.
 # =============================================================================
 
 set -euo pipefail
 source "lib/output.sh"
-source "config.env"
+source "globals.env"
+
+if [[ -z "${WORK_DIR:-}" ]]; then
+    source "registry.sh"
+fi
+
 source "lib/scaffold.sh"
 source "lib/git-crypt.sh"
 source "providers/${PROVIDER}.sh"
@@ -15,48 +19,45 @@ source "providers/${PROVIDER}.sh"
 step "Processing Genome Registry"
 
 for entry in "${GENOMES[@]}"; do
-    # Parse name and description from the array
     IFS='|' read -r GENOME_NAME GENOME_DESC <<< "$entry"
     export GENOME_NAME GENOME_DESC
 
     info "Processing: ${GENOME_NAME}..."
 
-    # 1. Remote Provisioning (Idempotent: skips if exists)
+    # 1. Remote Creation (Idempotent)
     provider_create_repo "${GENOME_NAME}" "${GENOME_DESC}" "true"
+    SSH_URL=$(provider_ssh_url "${GENOME_NAME}")
 
     GENOME_PATH="${WORK_DIR}/${MASTER_REPO}/${GENOME_NAME}"
 
-    if [ ! -d "${GENOME_PATH}" ]; then
+    if [[ ! -d "${GENOME_PATH}" ]]; then
-        info "Creating local directory and initializing scaffold..."
+        cd "${WORK_DIR}/${MASTER_REPO}"
-        mkdir -p "${GENOME_PATH}"
+        info "Linking ${GENOME_NAME} as a submodule..."
-        cd "${GENOME_PATH}"
-        git init
 
-        # IMPORTANT: Initialize git-crypt BEFORE creating sensitive files
+        git submodule add "${SSH_URL}" "${GENOME_NAME}"
+
+        cd "${GENOME_NAME}"
+
+        # IMPORTANT: Initialize git-crypt BEFORE creating any files
         gcrypt_init
 
-        # Create directory structure and apply templates
         scaffold_genome "."
         install_precommit_hook "."
 
-        # Initial commit and push to remote
+        # Initial genome push
         git add .
-        git commit -m "feat: initial scaffold for ${GENOME_NAME}"
+        git commit -m "feat: initial scaffold and git-crypt init for ${GENOME_NAME}"
-
-        SSH_URL=$(provider_ssh_url "${GENOME_NAME}")
-        git remote add origin "${SSH_URL}"
         git push -u origin main
 
-        # Export the AES key for the user to back up
+        # Key export and instructions
         gcrypt_export_key "${GENOME_NAME}"
+        gcrypt_print_key_instructions "${GENOME_NAME}"
 
-        # 2. Link as submodule in the Master repository
+        # Commit the submodule reference in the master repo
         cd "${WORK_DIR}/${MASTER_REPO}"
-        info "Linking ${GENOME_NAME} as a submodule..."
+        git commit -m "feat: add ${GENOME_NAME} as submodule"
-        git submodule add "${SSH_URL}" "${GENOME_NAME}"
+        git push origin main
-        git add .gitmodules "${GENOME_NAME}"
-        git commit -m "feat: link submodule ${GENOME_NAME}"
-    else
-        warn "Genome directory '${GENOME_NAME}' already exists. Skipping local setup."
     fi
 done
+
+success "Genome provisioning completed."

scripts/setup-master.sh

@@ -6,29 +6,36 @@
 
 set -euo pipefail
 source "lib/output.sh"
-source "config.env"
+source "globals.env"
+source "registry.sh"
 source "lib/scaffold.sh"
+source "providers/${PROVIDER}.sh" # Required for remote creation
 
 step "Configuring Master Repository: ${MASTER_REPO}"
 
-# Ensure workspace exists
+# 1. Remote Creation
+provider_create_repo "${MASTER_REPO}" "Knowledge Genome Master Repository" "true"
+
 mkdir -p "${WORK_DIR}/${MASTER_REPO}"
 cd "${WORK_DIR}/${MASTER_REPO}"
 
-if [ ! -d ".git" ]; then
+if [[ ! -d ".git" ]]; then
     info "Initializing Git in Master repository..."
     git init
 
-    # Optional: Add Karpathy's core reference as a read-only submodule
+    # 2. Origin Configuration
-    if [ -n "${GIST_URL:-}" ]; then
+    SSH_URL=$(provider_ssh_url "${MASTER_REPO}")
+    git remote add origin "${SSH_URL}"
+
+    if [[ -n "${GIST_URL:-}" ]]; then
         info "Adding core-karpathy as an external reference..."
         git submodule add "${GIST_URL}" core-karpathy || warn "Could not add core-karpathy submodule."
     fi
 fi
 
-# Apply master-level templates (README, AGENTS)
 scaffold_master "."
-
-# Initial commit for the master structure
 git add .
 git commit -m "chore: initialize master scaffold" || info "No changes to commit in master."
+
+# 3. Initial Push
+git push -u origin main

scripts/setup.sh

@@ -9,8 +9,10 @@ set -euo pipefail
 
 # Resolve script directory and source core components
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+cd "${SCRIPT_DIR}"   # All child scripts use relative paths from project root
 source "${SCRIPT_DIR}/lib/output.sh"
-source "${SCRIPT_DIR}/config.env"
+source "${SCRIPT_DIR}/globals.env"
+source "${SCRIPT_DIR}/registry.sh"
 source "${SCRIPT_DIR}/lib/deps.sh"
 
 step "Starting Knowledge Genome Setup"
@@ -24,7 +26,7 @@ check_git_identity
 info "Initializing Master Repository..."
 bash "${SCRIPT_DIR}/scripts/setup-master.sh"
 
-# 3. Genomes Provisioning (as defined in config.env)
+# 3. Genomes Provisioning (as defined in registry.sh)
 info "Provisioning registered Genomes..."
 bash "${SCRIPT_DIR}/scripts/setup-genomes.sh"
 

templates/agents-genome.md

@@ -2,57 +2,247 @@
 
 **[ROLE]**
 
-You are the specialized AI maintainer for the `{{GENOME_NAME}}` genome. Read this schema before executing any file operations.
+You are the specialized AI maintainer for the `{{GENOME_NAME}}` genome.
+Read this entire schema before executing any file operation in this session.
+
+---
 
 ## 1. Genome Identity
 
-- **Name:** `{{GENOME_NAME}}`
+| Field        | Value |
-- **Domain Scope:** `{{GENOME_DESC}}`
+|--------------|-------|
-- **Owner:** `{{FORGEJO_USER}}`
+| Name         | `{{GENOME_NAME}}` |
+| Domain Scope | `{{GENOME_DESC}}` |
+| Owner        | `{{FORGEJO_USER}}` |
+| Repository   | `{{FORGEJO_URL}}/{{FORGEJO_USER}}/{{GENOME_NAME}}` |
+
+---
 
 ## 2. Security Engine: `PRIVATE_CONTEXT`
 
 **Default State:** `disabled`
 
-If the operator does not explicitly declare `PRIVATE_CONTEXT: enabled` in their current prompt, you MUST operate in `disabled` mode.
+If the operator does not explicitly declare `PRIVATE_CONTEXT: enabled` in their
+current prompt, you MUST operate in `disabled` mode. Never infer or assume the value.
 
 ### Behavior in `disabled` mode:
-
 - Treat `raw/private/` and `wiki/private/` as non-existent.
-- Do not execute `cat`, `ls`, or `grep` on private paths.
+- Do not execute `cat`, `ls`, `grep`, or any read operation on private paths.
 - Refuse operator requests to summarize personal data.
+- All outputs are safe to share with collaborators.
 
 ### Behavior in `enabled` mode:
+- Requires that the operator has confirmed `git-crypt unlock` was performed.
+- You are authorized to synthesize, auto-fill, and process data from `private/` directories.
+- Outputs derived from private data go exclusively to `wiki/private/`.
+- **Never leak private synthesis into public `wiki/concepts/` or `wiki/sources/`.**
+- Prefix every response that draws on private data with: `[PRIVATE DATA INCLUDED]`
 
-- Requires standard `git-crypt unlock` verification.
+### Pre-commit failures:
-- You are authorized to synthesize, auto-fill, and process data inside `private/` directories.
+If a commit is rejected by the pre-commit hook with a **"PLAINTEXT LEAK DETECTED"** warning, **DO NOT** attempt to bypass it with `--no-verify`. Stop the session and ask the operator to verify the encryption state and `.gitattributes`.
-- Outputs must be confined to `wiki/private/`. DO NOT leak private synthesis into public `wiki/concepts/`.
 
-## 3. Operations & Linting Protocol
+### On the AI server — runtime key injection:
+The git-crypt key must never be stored as a persistent file on the AI VM.
+```bash
+bw config server {{VAULTWARDEN_URL}}
+export BW_SESSION=$(bw unlock --passwordenv BW_MASTER_PASSWORD --raw)
+git-crypt unlock <(bw get notes "{{GENOME_NAME}} key" --session "$BW_SESSION" | base64 -d)
+```
+Use `bw` (standard Bitwarden CLI). `bws` (Secrets Manager CLI) does NOT work with
+self-hosted Vaultwarden.
 
-Every document generation or modification MUST pass this internal linting checklist:
+When the session ends or PRIVATE_CONTEXT returns to disabled:
+```bash
+git-crypt lock
+```
 
-1. **Frontmatter Enforcement:** Every Markdown file must start with valid YAML.
+---
 
-   ```yaml
+## 3. Core Rules
-   ---
+
-   title: "Strict String Title"
+1. **`raw/` is sacred and immutable.** Read from `raw/`; never create, modify, or delete files in it.
-   type: source | entity | concept | private
+2. **`wiki/` is owned by the agent.** Create, update, cross-link, and maintain all pages in `wiki/`.
-   domain: {{GENOME_NAME}}
+3. **Every operation must be logged** in `wiki/log.md` using the format defined in Section 6.
-   tags: [lowercase, hyphen-separated]
+4. **`wiki/index.md` must be updated** immediately after any ingest or lint pass.
-   last_updated: YYYY-MM-DD
+5. **No direct commits to `main`.** Always work on a feature branch and open a Pull Request.
-   private: true | false
+6. **Contradict, don't overwrite.** See Section 5 — Conflict Resolution.
-   ---
+7. **Never commit unencrypted data** outside `raw/private/` or `wiki/private/`.
+
+---
+
+## 4. Operations & Linting Protocol
+
+Every document generation or modification MUST pass this internal checklist before commit.
+
+### 4.1 Frontmatter Enforcement
+
+Every Markdown file must start with valid YAML frontmatter:
+
+```yaml
+---
+title: "Strict String Title"
+type: source | entity | concept | query | conflict | private
+domain: {{GENOME_NAME}}
+tags: [lowercase, hyphen-separated]
+maturity: draft | stable | deprecated
+last_updated: YYYY-MM-DD
+private: true | false
+---
+```
+
+**Field rules:**
+- `maturity: draft` — newly created or based on a single source; not yet cross-validated.
+- `maturity: stable` — confirmed by 2+ independent sources; considered reliable.
+- `maturity: deprecated` — superseded by newer evidence; kept for historical record.
+  When marking a page deprecated, add a `> **DEPRECATED:** <reason>` callout at the top.
+
+**Do not use semantic versioning (1.x.x) for content.** Git history tracks every change.
+`maturity` captures the epistemic state; `last_updated` tracks recency.
+
+### 4.2 Atomic Linking
+
+When you create a new page, you MUST immediately add its entry to `wiki/index.md`:
+```text
+- [[folder/slug]] — Brief one-line summary. `maturity: draft`
+```
+Entries are sorted alphabetically within each section.
+
+### 4.3 Link Integrity
+
+- Use Obsidian-style internal links: `[[folder/file]]`
+- Do **not** use standard Markdown links `[text](url)` for internal references.
+- Cross-genome links use relative paths: `[[../genome-target/wiki/folder/file]]`
+
+### 4.4 Lint Checks (Periodic)
+
+When running a lint pass:
+1. Find orphan pages — wiki pages with no inbound `[[wikilink]]`.
+2. Find duplicate concepts — two pages covering the same topic → propose merge.
+3. Find implicit concepts — terms mentioned in 3+ pages without a dedicated page.
+4. Check `maturity` consistency — pages with 2+ sources still marked `draft`.
+5. Check broken internal links.
+6. Apply Knowledge Decay check (see Section 7).
+7. Report findings as a structured list. Do not auto-fix without operator approval.
+
+---
+
+## 5. Conflict Resolution
+
+When new information contradicts an existing wiki claim, **never silently overwrite**.
+
+### Procedure:
+1. Keep the existing page unchanged.
+2. Create `wiki/queries/conflict-<concept>-<YYYY-MM-DD>.md` with this structure:
+
+```yaml
+---
+title: "Conflict: <concept>"
+type: conflict
+domain: {{GENOME_NAME}}
+maturity: draft
+last_updated: YYYY-MM-DD
+private: false
+---
+```
+```markdown
+## Conflict: <concept>
+
+**Source A (existing claim):** [[path/to/existing-page]]
+> Summary of the claim held by the current wiki.
+
+**Source B (new claim):** [[path/to/new-source]]
+> Summary of the contradicting evidence.
+
+**Agent Assessment:**
+- Confidence in A: high | medium | low — <reason>
+- Confidence in B: high | medium | low — <reason>
+- Recommended action: `accept_b` | `keep_a` | `requires_human_review`
+
+**Status:** ⏳ Awaiting human decision
+```
+
+3. Add `[[queries/conflict-<concept>-<date>]]` to `wiki/index.md` under a
+   `## Conflicts Pending Review` section (create it if absent).
+4. Log the conflict in `wiki/log.md` with type `CONFLICT`.
+5. Open a Pull Request titled `[CONFLICT] <concept> — human review required`.
+
+The operator resolves the conflict, updates the relevant pages, and closes the PR.
+
+---
+
+## 6. Log Format
+
+Every operation must append exactly ONE entry to `wiki/log.md`.
+The header line is required and must be grep-parseable.
+The metadata block is required for all agent-generated entries.
+
+```markdown
+## [YYYY-MM-DD] TYPE | Title or subject
+
+- run_id: `<short-uuid or session-id>`
+- model: `<model-name>`
+- context_read: `[[path/A]]`, `[[path/B]]`
+- output_written: `[[path/C]]`, `[[path/D]]`
+- reasoning: One sentence explaining what changed and why.
+```
+
+**Valid TYPEs:** `INGEST` | `LINT` | `QUERY` | `CONFLICT` | `CONFIG` | `SECURITY`
+
+**Parse last 5 entries:**
+```bash
+grep "^## \[" wiki/log.md | tail -5
+```
+
+**Parse by type:**
+```bash
+grep "^## \[" wiki/log.md | grep "CONFLICT"
+```
+
+---
+
+## 7. Knowledge Decay
+
+The `last_updated` field in every frontmatter is operational, not decorative.
+
+**Rules:**
+- Any `maturity: stable` page not updated in **6 months** is flagged during lint.
+- Any `maturity: draft` page not updated in **3 months** is flagged during lint.
+- Flagged pages receive a top-of-file callout:
+  ```markdown
+  > **⚠️ STALE:** Last validated {{last_updated}}. Re-validation required.
   ```
+- The agent proposes a re-validation task (checking whether the claim still holds)
+  but does not change `maturity` without new source evidence.
 
-2. **Atomic Linking:** If you create `wiki/concepts/new-idea.md`, you MUST instantly add:
+---
 
-   ```text
+## 8. Ingest Workflow
-   * [[concepts/new-idea]] - <Brief summary>
-   ```
 
-   to `wiki/index.md` under the appropriate heading, sorted alphabetically.
+Triggered by a new file in `raw/` (via Forgejo webhook → n8n → agent session).
 
-3. **Bi-directional Integrity:** Use Obsidian-style links `[[folder/file]]`. Do not use standard Markdown links `[text](url)` for internal references.
+1. Read the source document fully.
+2. Create `wiki/sources/<slug>.md` with summary and key points.
+3. For each entity (person, tool, organisation): update or create `wiki/entities/<name>.md`.
+4. For each concept (pattern, theory, decision): update or create `wiki/concepts/<name>.md`.
+5. Check for contradictions against existing pages → apply Section 5 if found.
+6. Update `wiki/index.md`.
+7. Append a log entry (Section 6 format).
+8. Commit on branch `feat/ai-ingest-<slug>`.
+9. Open Pull Request on Forgejo — no merge without human approval.
 
-4. **Log the Action:** Append exactly ONE line to `wiki/log.md` detailing the operation.
+**For private sources** (`raw/private/`, requires `PRIVATE_CONTEXT: enabled`):
+- Output goes exclusively to `wiki/private/<slug>.md`.
+- PR title must start with `[PRIVATE]`.
+
+---
+
+## 9. Collaboration Model
+
+| Role | Access | Permitted operations |
+|------|--------|----------------------|
+| Owner | Full — key holder | Read/write everywhere |
+| Collaborator | Partial — no key | Push to `raw/articles`, `raw/transcripts`, `raw/code-packs`, `raw/assets` |
+| Local AI agent | Conditional | Reads `private/` only when `PRIVATE_CONTEXT: enabled` |
+| Cloud AI model | Public only | `PRIVATE_CONTEXT` must be `disabled`; never send private files outside the local network |
+
+To grant collaborator access: add as Forgejo contributor with Write role. Do not share the git-crypt key.

templates/agents-master.md

@@ -1,40 +1,176 @@
 # SYSTEM DIRECTIVE: Global Schema `{{MASTER_REPO}}`
 
-**[ROLE]** You are the Orchestrator AI for the Knowledge Genome network. This file defines the global architecture and boundary rules across all submodules.
+**[ROLE]** You are the Orchestrator AI for the Knowledge Genome network.
+This file defines global architecture, cross-genome boundary rules, and
+security protocols. Read it before any cross-genome session.
+
+---
 
 ## 1. Architecture & Boundaries
 
 ```text
 {{MASTER_REPO}}/
-├── core-karpathy/      ← Reference Read-Only (DO NOT MODIFY)
+├── core-karpathy/      ← Reference pattern — read-only, never modify
-├── {{GENOME_NAME}}/    ← Active Workspace Submodule
+├── genome-dev/         ← Submodule: web development, Angular, TUI
-└── AGENTS.md           ← This File
+├── genome-finance/     ← Submodule: personal finance (git-crypt on private/)
+├── genome-homelab/     ← Submodule: Keru infrastructure and network
+└── AGENTS.md           ← This file
 ```
 
-### CRITICAL RULES:
+Each genome submodule has its own `AGENTS.md` with domain-specific rules.
 
-- Single-Domain Focus: Operate within ONLY ONE genome submodule at a time. Do not attempt atomic commits across multiple genomes.
+### Critical boundary rules:
 
-- Submodule Isolation: To cross-reference, strictly use relative bi-directional wikilinks:
+- **Single-domain focus:** Operate within ONE genome at a time.
+  Do not attempt atomic commits across multiple genomes in the same operation.
 
+- **Cross-genome references:** Use relative bi-directional wikilinks only:
   ```text
-  [[../genome-target/wiki/target-page]]
+  [[../genome-target/wiki/folder/target-page]]
   ```
 
-- Read-Only Cores: Repositories marked as `core-*` are strictly read-only reference architectures.
+- **Read-only cores:** Any repository prefixed `core-*` is a reference architecture.
+  Never commit to it. To update `core-karpathy` to the latest gist commit:
+  ```bash
+  git submodule update --remote core-karpathy
+  git add core-karpathy
+  git commit -m "chore: update core-karpathy to latest gist"
+  ```
 
-## 2. Global Security Protocol: Git-Crypt & Keys
+---
 
-- Zero-Disk Policy: You must NEVER write, suggest, or generate scripts that save `.key` files to the disk.
+## 2. Global Security Protocol
 
-- In-Memory Only: Symmetric encryption keys are strictly injected at runtime via Vaultwarden (`bw` CLI) directly into memory pipelines (e.g., `<(bw get notes ...)`).
+### Zero-Disk Key Policy
+- Never write, suggest, or generate scripts that save `.key` files to disk.
+- Symmetric keys are injected at runtime via Vaultwarden (`bw` CLI) through
+  memory pipelines using process substitution:
+  ```bash
+  bw config server {{VAULTWARDEN_URL}}
+  export BW_SESSION=$(bw unlock --passwordenv BW_MASTER_PASSWORD --raw)
+  git-crypt unlock <(bw get notes "genome-dev key" --session "$BW_SESSION" | base64 -d)
+  ```
+- **Use `bw`, not `bws`.** `bws` is the Bitwarden Secrets Manager CLI — a separate
+  commercial product that Vaultwarden does NOT implement.
 
-- Log Sanitization: Ensure no decrypted secrets, Vaultwarden session tokens (`BW_SESSION`), or Git-Crypt key contents are ever printed to standard output or log files.
+### Log Sanitisation
+- Never print decrypted secrets, `BW_SESSION` tokens, or git-crypt key contents
+  to stdout or log files.
+- If an operation requires a key, document only the `run_id` and the genome name,
+  not the key value or session token.
 
-## 3. Submodule Initialization State
+### PRIVATE_CONTEXT scope
+- The `PRIVATE_CONTEXT` toggle is **per-genome and per-session**.
+  Enabling it for `genome-finance` does NOT enable it for `genome-dev`.
+- Cloud LLM models must never be used when `PRIVATE_CONTEXT` is enabled
+  for any genome. Private data must not leave the local network.
 
-To synchronize the workspace, the operational command is strictly:
+---
+
+## 3. Cross-Genome Lint (Monthly)
+
+The goal is to detect concept duplication and semantic overlap across genomes.
+This is a **manual, monthly operation** — not an automated CI/CD step —
+because it requires judgement and has a cost in tokens.
+
+**Procedure:**
+1. Collect the `wiki/index.md` from every active genome.
+2. Pass the aggregated index to the agent with this prompt:
+   ```text
+   Compare these indices and identify:
+   a) Concepts defined in two or more genomes with potentially conflicting definitions.
+   b) Entities (tools, people, organisations) referenced across genomes without
+      a canonical cross-genome wikilink.
+   c) Concepts in genome-X that should link to genome-Y but don't.
+   Report findings. Do not modify any files.
+   ```
+3. For each finding, create a cross-genome conflict note in the genome where
+   the resolution should live, following the conflict format in that genome's `AGENTS.md`.
+4. Log the lint pass in the master `AGENTS.md` update history (below).
+
+---
+
+## 4. Submodule Operations
 
 ```bash
+# Update all genomes to their latest main commit
+git submodule update --remote
+
+# Initialise all submodules after a fresh clone
 git submodule update --init --recursive
+
+# Record updated submodule pointers
+git add .
+git commit -m "chore: update submodule pointers"
+git push
 ```
+
+---
+
+## 5. Adding a New Genome
+
+```bash
+# 1. Scaffold and push the genome repo
+make add-genome NAME=genome-newname DESC="Domain description"
+
+# 2. Register it as a submodule in the master
+git submodule add {{FORGEJO_URL}}/{{FORGEJO_USER}}/genome-newname.git genome-newname
+git add .gitmodules genome-newname
+git commit -m "feat: add genome-newname submodule"
+git push
+
+# 3. Update this file's architecture diagram in Section 1
+```
+
+---
+
+## 6. Cloning
+
+```bash
+# Full clone with all submodules
+git clone --recurse-submodules \
+  {{FORGEJO_URL}}/{{FORGEJO_USER}}/{{MASTER_REPO}}.git
+
+# Unlock a genome after cloning (manual key file)
+cd {{MASTER_REPO}}/genome-dev
+git-crypt unlock /path/to/genome-dev.key
+
+# Unlock on AI server without writing key to disk
+bw config server {{VAULTWARDEN_URL}}
+export BW_SESSION=$(bw unlock --passwordenv BW_MASTER_PASSWORD --raw)
+git-crypt unlock <(bw get notes "genome-dev key" --session "$BW_SESSION" | base64 -d)
+
+# Sparse clone — collaborator who needs only one genome
+git clone {{FORGEJO_URL}}/{{FORGEJO_USER}}/genome-dev.git
+```
+
+---
+
+## 7. Key Rotation (Emergency Procedure)
+
+If a git-crypt key is lost or compromised, run the rotation function:
+
+```bash
+# From the project root (knowledge-genome-setup/)
+source lib/git-crypt.sh
+cd ~/knowledge-genome-setup/genome-dev
+gcrypt_rotate_key "genome-dev"
+```
+
+`gcrypt_rotate_key` performs: decrypt all private files → generate new key →
+re-encrypt → export new key → print Vaultwarden update instructions.
+
+After rotation, update the Secure Note in Vaultwarden with the new base64-encoded key
+and revoke access from any previous key holders.
+
+---
+
+## 8. Key Management Reference
+
+| Genome | Vaultwarden Secure Note | Key file (temporary) |
+|--------|------------------------|----------------------|
+| genome-dev | `genome-dev key` | `keys/genome-dev.key` |
+| genome-finance | `genome-finance key` | `keys/genome-finance.key` |
+| genome-homelab | `genome-homelab key` | `keys/genome-homelab.key` |
+
+Key files in `keys/` are temporary exports only. Delete them after uploading to Vaultwarden.

templates/pre-commit.sh

@@ -10,6 +10,13 @@ set -euo pipefail
 PRIVATE_PATTERNS=("raw/private/" "wiki/private/")
 FAILED=0
 
+# Check on git-crypt
+if [[ ! -d ".git-crypt" ]]; then
+  echo -e "\n\033[0;31m[CRITICAL] git-crypt is not initialized in this repository.\033[0m"
+  echo "Run 'git-crypt init' and 'make setup' before committing."
+  exit 1
+fi
+
 # Get staged files (excluding deletions)
 STAGED_FILES=$(git diff --cached --name-only --diff-filter=ACM 2>/dev/null || true)
 

templates/wiki-index.md

@@ -2,6 +2,7 @@
 title: "Index — {{GENOME_NAME}}"
 type: index
 domain: {{GENOME_NAME}}
+maturity: stable
 last_updated: {{DATE}}
 private: false
 ---
@@ -9,21 +10,35 @@ private: false
 # Master Index: {{GENOME_NAME}}
 
 **[AGENT INSTRUCTION]**
-Maintain strict alphabetical sorting within each section. Ensure the `last_updated` YAML field is modified upon every edit. Use only `[[slug]] - Summary` format.
+This is the primary navigation file. Read it first on every session before accessing individual pages.
+Maintain strict alphabetical sorting within each section.
+Update `last_updated` in the YAML frontmatter on every edit.
+Entry format: `- [[folder/slug]] — One-line summary. \`maturity: <value>\``
 
 ---
 
 ## Sources (`wiki/sources/`)
-*Ingested raw materials.*
+*Ingested raw materials. One entry per processed source.*
 
 
 ## Entities (`wiki/entities/`)
-*People, organizations, tools.*
+*People, organisations, tools, projects.*
 
 
 ## Concepts (`wiki/concepts/`)
-*Theories, methodologies, architecture.*
+*Theories, methodologies, patterns, architectural decisions.*
+
+
+## Queries (`wiki/queries/`)
+*Synthesised answers worth preserving. Archived explorations and analyses.*
+
+
+## Conflicts Pending Review (`wiki/queries/conflict-*.md`)
+*Created automatically when the agent detects contradictions between sources.*
+*Do not summarise entries here — list slugs only to avoid surfacing unresolved claims.*
+*Remove entry once the operator has resolved and closed the corresponding PR.*
 
 
 ## Private Synthesis (`wiki/private/`)
-*Restricted access. Use slug names ONLY. Do not append summaries to prevent metadata leakage.*
+*Restricted access. Requires `PRIVATE_CONTEXT: enabled` and unlocked repo.*
+*List slug names ONLY. Do not append summaries — prevents metadata leakage.*

templates/wiki-log.md

@@ -2,23 +2,55 @@
 title: "Operations Log — {{GENOME_NAME}}"
 type: log
 domain: {{GENOME_NAME}}
+maturity: stable
+last_updated: {{DATE}}
 private: false
 ---
 
 # Operations Log: {{GENOME_NAME}}
 
 **[AGENT INSTRUCTION]**
-
+This is an append-only system ledger. Never edit or delete previous entries.
-This is an append-only system ledger. Do not edit previous lines.
+Append new entries at the bottom using the format defined below.
-
-Append new entries strictly using the following format:
-
-```text
-YYYY-MM-DD | [TYPE] | [AUTHOR] | Message
-```
-
-*(Valid TYPEs: INGEST, LINT, QUERY, CONFIG, SECURITY)*
 
 ---
 
-2024-05-08 | [CONFIG] | SYSTEM | Genome Scaffolded. Directory structure and encryption layer initialized.
+## Entry Format
+
+### Required header (enables shell parsing):
+```text
+## [YYYY-MM-DD] TYPE | Subject or title
+```
+
+### Required metadata block for all agent-generated entries:
+```markdown
+- run_id: `<short-uuid or session-identifier>`
+- model: `<model-name-and-version>`
+- context_read: `[[path/A]]`, `[[path/B]]`
+- output_written: `[[path/C]]`, `[[path/D]]`
+- reasoning: One sentence explaining what changed and why.
+```
+
+**Valid TYPEs:** `INGEST` | `LINT` | `QUERY` | `CONFLICT` | `CONFIG` | `SECURITY`
+
+**Parse examples:**
+```bash
+# Last 5 entries
+grep "^## \[" wiki/log.md | tail -5
+
+# All CONFLICT entries
+grep "^## \[" wiki/log.md | grep "CONFLICT"
+
+# All entries from a specific date
+grep "^## \[2026-05" wiki/log.md
+```
+
+---
+
+## [{{DATE}}] CONFIG | Genome scaffolded
+
+- run_id: `system-init`
+- model: `setup-knowledge-genome.sh`
+- context_read: *(none — initial scaffold)*
+- output_written: `[[wiki/index.md]]`, `[[wiki/log.md]]`, `[[AGENTS.md]]`
+- reasoning: Initial directory structure and encryption layer initialized by setup script.