mindlore 0.6.8 → 0.6.9

package/skills/mindlore-explore/SKILL.md

@@ -1,109 +1,109 @@
----
-name: mindlore-explore
-description: Discover unexpected connections between sources — undirected knowledge exploration
-effort: medium
-context: fork
-allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent]
----
-
-# /mindlore-explore
-
-Discover unexpected connections between knowledge sources. Undirected exploration — unlike query (directed search).
-
-## Scope
-
-Default: `--scope all` (project + global birlikte taranır — en değerli mod).
-Options: `--scope project` | `--scope global` | `--scope all`
-
-1. Determine scope from argument (default: all)
-2. If `all`: explore both project `.mindlore/` and global `~/.mindlore/` + cross-reference
-3. If `project`: explore only project-scoped content (current CWD's `.mindlore/`)
-4. If `global`: explore only global `~/.mindlore/` content
-- Never hardcode `.mindlore/` path — always resolve dynamically via `getActiveMindloreDir()`
-
-## Trigger
-
-User says `/mindlore-explore`, "knowledge explore", "baglanti kesfet", "cross-reference bul".
-
-## Flow
-
-**Agent Delegation:** Cross-reference analizini subagent'a delege et (context koruma).
-
-1. Spawn an Agent for analysis:
-   ```
-   Agent({
-     description: "mindlore explore: connections",
-     subagent_type: "Explore",
-     prompt: "[mindlore:explore] Analyze .mindlore/ for unexpected connections. <aşağıdaki talimatları buraya koy>"
-   })
-   ```
-
-   Agent talimatları:
-   a. Read all source and domain files from active scope
-   b. Cross-match by tag + content (see criteria below)
-   c. Rank connections by strength
-   d. Return findings as structured table
-
-2. After agent returns — review and show findings to user
-3. On approval, write connection files (main session handles writes)
-
-**Cross-match criteria:**
-   - Files sharing tags but not referencing each other
-   - Sources covering similar topics from different angles
-   - Sources that could bridge between domains
-3. Rank connections by strength:
-   - **high**: 3+ shared tags + content overlap
-   - **medium**: 2 shared tags or significant content similarity
-   - **low**: 1 shared tag + weak content match
-4. Show findings to user
-5. On approval, write to `connections/` directory
-
-## Connection File Format
-
-Written to `connections/` with frontmatter:
-
-```markdown
----
-type: connection
-slug: connection-source-a-source-b
-date_created: 2026-04-12
-sources: [source-a.md, source-b.md]
-domains: [domain-x.md]
-strength: high
-tags: [shared-tag-1, shared-tag-2]
----
-
-## Connection
-
-[Why these sources are related — LLM explanation]
-
-## Action Suggestion
-
-[What could be done — domain update, new analysis, etc.]
-```
-
-## Rules
-
-- Check for duplicate connections before writing (same source pair)
-- Show findings before writing — user approval required
-- Update INDEX.md with new connections entry
-- Append EXPLORE entry to log.md
-- Strength is LLM-assessed based on tag overlap + content similarity
-- The `[mindlore:explore]` marker in the Agent prompt is required — it triggers the model-router hook to use the cost-optimized model (sonnet by default)
-
-## Output Format
-
-```
-Mindlore Explore — Discovered Connections
-
-Scope: project (.mindlore/)
-Sources scanned: 12
-Connections found: 3 (2 new, 1 existing)
-
-| # | Sources | Strength | Why |
-|---|---------|----------|-----|
-| 1 | react-hooks.md + agent-orchestration.md | medium | Both discuss state management patterns |
-| 2 | karpathy-kb.md + search-retrieval.md | high | FTS5 + knowledge architecture overlap |
-
-Write connections? (y/n)
-```
+---
+name: mindlore-explore
+description: Discover unexpected connections between sources — undirected knowledge exploration
+effort: medium
+context: fork
+allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent]
+---
+
+# /mindlore-explore
+
+Discover unexpected connections between knowledge sources. Undirected exploration — unlike query (directed search).
+
+## Scope
+
+Default: `--scope all` (project + global birlikte taranır — en değerli mod).
+Options: `--scope project` | `--scope global` | `--scope all`
+
+1. Determine scope from argument (default: all)
+2. If `all`: explore both project `.mindlore/` and global `~/.mindlore/` + cross-reference
+3. If `project`: explore only project-scoped content (current CWD's `.mindlore/`)
+4. If `global`: explore only global `~/.mindlore/` content
+- Never hardcode `.mindlore/` path — always resolve dynamically via `getActiveMindloreDir()`
+
+## Trigger
+
+User says `/mindlore-explore`, "knowledge explore", "baglanti kesfet", "cross-reference bul".
+
+## Flow
+
+**Agent Delegation:** Cross-reference analizini subagent'a delege et (context koruma).
+
+1. Spawn an Agent for analysis:
+   ```
+   Agent({
+     description: "mindlore explore: connections",
+     subagent_type: "Explore",
+     prompt: "[mindlore:explore] Analyze .mindlore/ for unexpected connections. <aşağıdaki talimatları buraya koy>"
+   })
+   ```
+
+   Agent talimatları:
+   a. Read all source and domain files from active scope
+   b. Cross-match by tag + content (see criteria below)
+   c. Rank connections by strength
+   d. Return findings as structured table
+
+2. After agent returns — review and show findings to user
+3. On approval, write connection files (main session handles writes)
+
+**Cross-match criteria:**
+   - Files sharing tags but not referencing each other
+   - Sources covering similar topics from different angles
+   - Sources that could bridge between domains
+3. Rank connections by strength:
+   - **high**: 3+ shared tags + content overlap
+   - **medium**: 2 shared tags or significant content similarity
+   - **low**: 1 shared tag + weak content match
+4. Show findings to user
+5. On approval, write to `connections/` directory
+
+## Connection File Format
+
+Written to `connections/` with frontmatter:
+
+```markdown
+---
+type: connection
+slug: connection-source-a-source-b
+date_created: 2026-04-12
+sources: [source-a.md, source-b.md]
+domains: [domain-x.md]
+strength: high
+tags: [shared-tag-1, shared-tag-2]
+---
+
+## Connection
+
+[Why these sources are related — LLM explanation]
+
+## Action Suggestion
+
+[What could be done — domain update, new analysis, etc.]
+```
+
+## Rules
+
+- Check for duplicate connections before writing (same source pair)
+- Show findings before writing — user approval required
+- Update INDEX.md with new connections entry
+- Append EXPLORE entry to log.md
+- Strength is LLM-assessed based on tag overlap + content similarity
+- The `[mindlore:explore]` marker in the Agent prompt is required — it triggers the model-router hook to use the cost-optimized model (sonnet by default)
+
+## Output Format
+
+```
+Mindlore Explore — Discovered Connections
+
+Scope: project (.mindlore/)
+Sources scanned: 12
+Connections found: 3 (2 new, 1 existing)
+
+| # | Sources | Strength | Why |
+|---|---------|----------|-----|
+| 1 | react-hooks.md + agent-orchestration.md | medium | Both discuss state management patterns |
+| 2 | karpathy-kb.md + search-retrieval.md | high | FTS5 + knowledge architecture overlap |
+
+Write connections? (y/n)
+```

package/skills/mindlore-ingest/SKILL.md

@@ -1,195 +1,195 @@
----
-name: mindlore-ingest
-description: Add new knowledge sources to .mindlore/ (URL, text, file, PDF, GitHub repo)
-effort: medium
-allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch]
-context: fork
-agent: coder
----
-
-## Script Resolution
-
-Resolve `MINDLORE_PKG` (package root) using one of these methods, in order:
-1. If CC injected "Base directory for this skill: /path/to/skills/mindlore-ingest" → `MINDLORE_PKG = {base_directory}/../..`
-2. Fallback: run `node -e "console.log(require('path').join(require('child_process').execSync('npm root -g',{encoding:'utf8'}).trim(),'mindlore')))"`
-
-Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
-
-# /mindlore-ingest
-
-Add a new knowledge source to the `.mindlore/` knowledge base.
-
-## Scope
-
-Tüm ingest işlemleri global `~/.mindlore/` dizinine yazılır.
-Proje ayrımı frontmatter'daki `project` alanı ile yapılır.
-`raw/` altına proje bazlı klasörleme yapılmaz (session sync hariç).
-Frontmatter'a `project: {CWD project adı}` otomatik eklenir.
-
-## Trigger
-
-User shares a URL, text, file, or says "kaynak ekle", "source ingest", "bu linki kaydet", "knowledge ingest".
-
-## Multi-URL Support
-
-Birden fazla URL verildiğinde (boşluk veya virgülle ayrılmış):
-
-1. URL'leri parse et — boşluk veya virgülle split
-2. Her URL için sırayla mevcut URL Mode pipeline'ını çalıştır:
-   - Fetch → raw/ yazımı → sources/ dönüşümü → INDEX.md güncelle → log → FTS5 sync
-3. Her URL için ayrı `skill-memory` dedup kontrolü yap
-4. Her URL sonrası 7-point quality gate uygula
-5. Hata olan URL'yi raporla ama sonrakine devam et (fail-forward)
-6. Tüm URL'ler bittikten sonra toplu rapor döndür:
-
-```json
-{ "processed": 3, "failed": 0, "skipped": 1, "sources": ["slug1", "slug2", "slug3"] }
-```
-
-Örnek kullanım:
-```
-/mindlore-ingest https://docs.aws.amazon.com/lambda/latest/dg/best-practices.html https://docs.aws.amazon.com/dynamodb/latest/developerguide/best-practices.html
-```
-
-## Modes
-
-### URL Mode (v0.5.2 — Zero-Token Pipeline)
-
-**Trigger:** Input starts with `http://` or `https://`
-
-**Pre-check (before fetch):**
-```bash
-node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" get mindlore-ingest last_ingest_urls
-```
-If URL already in the list, warn user: "This URL was ingested recently. Re-ingest?"
-
-**Flow:**
-
-1. **Fetch raw content (zero token):**
-   ```bash
-   node "$MINDLORE_PKG/dist/scripts/fetch-raw.js" "$URL" --out-dir "$MINDLORE_DIR/raw"
-   ```
-   Script output: `{ "saved": "/path/to/raw/2026-04-18-abc123.md", "chars": 14823, "method": "curl" }`
-
-2. **Read first 3000 chars (heading-aware truncation):**
-   - Read the saved raw file
-   - Find the last `##` heading before char 3000
-   - Truncate at that heading boundary (not mid-paragraph)
-   - If no heading found before 3000, truncate at last paragraph break
-
-3. **Write sources/ summary from truncated content:**
-   - Extract: title, description (first paragraph), key topics
-   - Generate frontmatter: slug, type: source, source_url, date_captured, tags, quality
-   - `project: {path.basename(process.cwd()) ile CWD'den alınan proje adı}`
-   - `source_type` is auto-detected from URL pattern (see Source Summary Format)
-   - Write to `$MINDLORE_DIR/sources/{slug}.md`
-
-4. **Update INDEX.md** with new source entry
-
-5. **Update skill_memory:**
-   ```bash
-   node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" set mindlore-ingest last_ingest_urls "$URL"
-   ```
-
-6. **Return to caller (this is all the ana session sees):**
-   ```json
-   { "source_id": "abc123", "title": "Extracted Title" }
-   ```
-
-**Token budget:** ~2-3k tokens in fork context (vs ~40-50k before). Ana session: ~50 tokens.
-
-**Fallback:** If fetch-raw.js fails (network error, unsupported format), fall back to existing WebFetch-based flow with warning: "Zero-token fetch failed, using legacy flow (higher token cost)."
-
-### Text Mode
-1. User pastes text directly
-2. Save to `.mindlore/raw/` with `source_type: text-paste`
-3. Follow steps 3-7 from URL mode
-
-### PDF Mode
-1. Read PDF with CC Read tool: `Read(file_path, pages: "1-5")` (max 20 pages/request)
-2. **Do NOT use markitdown for PDF** — quality is poor
-3. Save extracted text to `.mindlore/raw/`
-4. Follow steps 3-7 from URL mode
-5. For v0.3+: Marker CLI or Chandra as optional alternatives
-
-### File Mode
-1. Read the file with `Read` tool
-2. Save to `.mindlore/raw/`
-3. Follow steps 3-7 from URL mode
-
-## Source Summary Format
-
-The sources/ file should contain:
-- **1-paragraph summary** of what the source is about
-- **Key takeaways** (3-7 bullet points)
-- **Relevance to project** (why this matters)
-- **Related** links to other sources/domains in .mindlore/
-
-Required frontmatter fields include `source_type` — auto-detected:
-- `github-repo` if URL contains `github.com/{owner}/{repo}` (not a file/blob URL)
-- `docs` if URL contains `/docs/`, `/documentation/`, or `/api/`
-- `blog` if URL contains `/blog/`, `/post/`, or `/article/`
-- `video` if URL contains `youtube.com`, `youtu.be`, or `vimeo.com`
-- `url-fetch` as default fallback for all other URLs
-- `text-paste` for Text Mode
-- `pdf` for PDF Mode
-- `file` for File Mode
-
-### Extraction Template
-
-After detecting `source_type`, check if a matching extraction template exists:
-
-1. Read `~/.mindlore/templates/extraction/{source_type}.md`
-2. If found, follow the "Extraction Instructions" section for source analysis
-3. If not found, Read `~/.mindlore/templates/extraction/default.md` and follow that
-4. User can override with `--type <type>` argument (e.g., `/mindlore-ingest https://example.com --type changelog`)
-
-The template guides WHAT to extract from the source. Apply its instructions when writing the source summary in `sources/{slug}.md`.
-
-## Quality Assessment
-
-Assign quality automatically during ingest using this heuristic:
-- `high`: Official docs (anthropic, github docs, MDN), primary research, authoritative references
-- `medium`: Blog posts, tutorials, conference talks, X threads with substance
-- `low`: Raw notes, text pastes, quick captures, low signal-to-noise
-
-LLM may override the heuristic based on content analysis. Always set quality — never leave it null.
-
-## Domain Update Rules
-
-- Read the relevant domain page first
-- Add new information under the appropriate section
-- Add backlink to the source in the domain's references
-- Update max 2 domain pages per ingest (prevent scope creep)
-- If no relevant domain exists, note it — don't create one during ingest
-
-## INDEX.md Update
-
-Only update the stats line: increment source count and total count.
-```
-N source, N analysis, N total
-```
-
-## Post-Ingest Quality Gate
-
-After every ingest, verify all 7 checkpoints before reporting success:
-
-0. **Duplicate check** — Ingest öncesi mevcut DB'de benzer içerik ara:
-   ```bash
-   node "$MINDLORE_PKG/dist/scripts/lib/similarity.js" "<title or first 100 chars>"
-   ```
-   Eğer score > 0.7 olan sonuç varsa KULLANICIYA SOR: "Bu içerik '${slug}' ile benzer görünüyor. Yine de eklensin mi?"
-   Kullanıcı onaylarsa devam et, yoksa atla.
-1. **raw/ file exists** — immutable capture written with frontmatter (slug, type, source_url, project)
-2. **sources/ summary exists** — processed summary with full frontmatter (slug, type, title, tags, quality, description)
-3. **INDEX.md updated** — stats line incremented, Recent section has new entry
-4. **Domain updated** — if relevant domain exists, new finding added (max 1 domain per ingest)
-5. **log.md entry** — append `| {date} | ingest | {slug}.md |`
-6. **FTS5 indexed** — FileChanged hook auto-triggers, but verify: `node "$MINDLORE_PKG/dist/scripts/mindlore-fts5-search.js" "{keyword}"` returns the new file
-
-If any checkpoint fails, fix it before reporting "ingest complete". Do NOT skip steps.
-
-Optional: run full health check for structural integrity:
-```bash
-node "$MINDLORE_PKG/dist/scripts/mindlore-health-check.js"
-```
+---
+name: mindlore-ingest
+description: Add new knowledge sources to .mindlore/ (URL, text, file, PDF, GitHub repo)
+effort: medium
+allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch]
+context: fork
+agent: coder
+---
+
+## Script Resolution
+
+Resolve `MINDLORE_PKG` (package root) using one of these methods, in order:
+1. If CC injected "Base directory for this skill: /path/to/skills/mindlore-ingest" → `MINDLORE_PKG = {base_directory}/../..`
+2. Fallback: run `node -e "console.log(require('path').join(require('child_process').execSync('npm root -g',{encoding:'utf8'}).trim(),'mindlore')))"`
+
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
+# /mindlore-ingest
+
+Add a new knowledge source to the `.mindlore/` knowledge base.
+
+## Scope
+
+Tüm ingest işlemleri global `~/.mindlore/` dizinine yazılır.
+Proje ayrımı frontmatter'daki `project` alanı ile yapılır.
+`raw/` altına proje bazlı klasörleme yapılmaz (session sync hariç).
+Frontmatter'a `project: {CWD project adı}` otomatik eklenir.
+
+## Trigger
+
+User shares a URL, text, file, or says "kaynak ekle", "source ingest", "bu linki kaydet", "knowledge ingest".
+
+## Multi-URL Support
+
+Birden fazla URL verildiğinde (boşluk veya virgülle ayrılmış):
+
+1. URL'leri parse et — boşluk veya virgülle split
+2. Her URL için sırayla mevcut URL Mode pipeline'ını çalıştır:
+   - Fetch → raw/ yazımı → sources/ dönüşümü → INDEX.md güncelle → log → FTS5 sync
+3. Her URL için ayrı `skill-memory` dedup kontrolü yap
+4. Her URL sonrası 7-point quality gate uygula
+5. Hata olan URL'yi raporla ama sonrakine devam et (fail-forward)
+6. Tüm URL'ler bittikten sonra toplu rapor döndür:
+
+```json
+{ "processed": 3, "failed": 0, "skipped": 1, "sources": ["slug1", "slug2", "slug3"] }
+```
+
+Örnek kullanım:
+```
+/mindlore-ingest https://docs.aws.amazon.com/lambda/latest/dg/best-practices.html https://docs.aws.amazon.com/dynamodb/latest/developerguide/best-practices.html
+```
+
+## Modes
+
+### URL Mode (v0.5.2 — Zero-Token Pipeline)
+
+**Trigger:** Input starts with `http://` or `https://`
+
+**Pre-check (before fetch):**
+```bash
+node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" get mindlore-ingest last_ingest_urls
+```
+If URL already in the list, warn user: "This URL was ingested recently. Re-ingest?"
+
+**Flow:**
+
+1. **Fetch raw content (zero token):**
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/fetch-raw.js" "$URL" --out-dir "$MINDLORE_DIR/raw"
+   ```
+   Script output: `{ "saved": "/path/to/raw/2026-04-18-abc123.md", "chars": 14823, "method": "curl" }`
+
+2. **Read first 3000 chars (heading-aware truncation):**
+   - Read the saved raw file
+   - Find the last `##` heading before char 3000
+   - Truncate at that heading boundary (not mid-paragraph)
+   - If no heading found before 3000, truncate at last paragraph break
+
+3. **Write sources/ summary from truncated content:**
+   - Extract: title, description (first paragraph), key topics
+   - Generate frontmatter: slug, type: source, source_url, date_captured, tags, quality
+   - `project: {path.basename(process.cwd()) ile CWD'den alınan proje adı}`
+   - `source_type` is auto-detected from URL pattern (see Source Summary Format)
+   - Write to `$MINDLORE_DIR/sources/{slug}.md`
+
+4. **Update INDEX.md** with new source entry
+
+5. **Update skill_memory:**
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" set mindlore-ingest last_ingest_urls "$URL"
+   ```
+
+6. **Return to caller (this is all the ana session sees):**
+   ```json
+   { "source_id": "abc123", "title": "Extracted Title" }
+   ```
+
+**Token budget:** ~2-3k tokens in fork context (vs ~40-50k before). Ana session: ~50 tokens.
+
+**Fallback:** If fetch-raw.js fails (network error, unsupported format), fall back to existing WebFetch-based flow with warning: "Zero-token fetch failed, using legacy flow (higher token cost)."
+
+### Text Mode
+1. User pastes text directly
+2. Save to `.mindlore/raw/` with `source_type: text-paste`
+3. Follow steps 3-7 from URL mode
+
+### PDF Mode
+1. Read PDF with CC Read tool: `Read(file_path, pages: "1-5")` (max 20 pages/request)
+2. **Do NOT use markitdown for PDF** — quality is poor
+3. Save extracted text to `.mindlore/raw/`
+4. Follow steps 3-7 from URL mode
+5. For v0.3+: Marker CLI or Chandra as optional alternatives
+
+### File Mode
+1. Read the file with `Read` tool
+2. Save to `.mindlore/raw/`
+3. Follow steps 3-7 from URL mode
+
+## Source Summary Format
+
+The sources/ file should contain:
+- **1-paragraph summary** of what the source is about
+- **Key takeaways** (3-7 bullet points)
+- **Relevance to project** (why this matters)
+- **Related** links to other sources/domains in .mindlore/
+
+Required frontmatter fields include `source_type` — auto-detected:
+- `github-repo` if URL contains `github.com/{owner}/{repo}` (not a file/blob URL)
+- `docs` if URL contains `/docs/`, `/documentation/`, or `/api/`
+- `blog` if URL contains `/blog/`, `/post/`, or `/article/`
+- `video` if URL contains `youtube.com`, `youtu.be`, or `vimeo.com`
+- `url-fetch` as default fallback for all other URLs
+- `text-paste` for Text Mode
+- `pdf` for PDF Mode
+- `file` for File Mode
+
+### Extraction Template
+
+After detecting `source_type`, check if a matching extraction template exists:
+
+1. Read `~/.mindlore/templates/extraction/{source_type}.md`
+2. If found, follow the "Extraction Instructions" section for source analysis
+3. If not found, Read `~/.mindlore/templates/extraction/default.md` and follow that
+4. User can override with `--type <type>` argument (e.g., `/mindlore-ingest https://example.com --type changelog`)
+
+The template guides WHAT to extract from the source. Apply its instructions when writing the source summary in `sources/{slug}.md`.
+
+## Quality Assessment
+
+Assign quality automatically during ingest using this heuristic:
+- `high`: Official docs (anthropic, github docs, MDN), primary research, authoritative references
+- `medium`: Blog posts, tutorials, conference talks, X threads with substance
+- `low`: Raw notes, text pastes, quick captures, low signal-to-noise
+
+LLM may override the heuristic based on content analysis. Always set quality — never leave it null.
+
+## Domain Update Rules
+
+- Read the relevant domain page first
+- Add new information under the appropriate section
+- Add backlink to the source in the domain's references
+- Update max 2 domain pages per ingest (prevent scope creep)
+- If no relevant domain exists, note it — don't create one during ingest
+
+## INDEX.md Update
+
+Only update the stats line: increment source count and total count.
+```
+N source, N analysis, N total
+```
+
+## Post-Ingest Quality Gate
+
+After every ingest, verify all 7 checkpoints before reporting success:
+
+0. **Duplicate check** — Ingest öncesi mevcut DB'de benzer içerik ara:
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/lib/similarity.js" "<title or first 100 chars>"
+   ```
+   Eğer score > 0.7 olan sonuç varsa KULLANICIYA SOR: "Bu içerik '${slug}' ile benzer görünüyor. Yine de eklensin mi?"
+   Kullanıcı onaylarsa devam et, yoksa atla.
+1. **raw/ file exists** — immutable capture written with frontmatter (slug, type, source_url, project)
+2. **sources/ summary exists** — processed summary with full frontmatter (slug, type, title, tags, quality, description)
+3. **INDEX.md updated** — stats line incremented, Recent section has new entry
+4. **Domain updated** — if relevant domain exists, new finding added (max 1 domain per ingest)
+5. **log.md entry** — append `| {date} | ingest | {slug}.md |`
+6. **FTS5 indexed** — FileChanged hook auto-triggers, but verify: `node "$MINDLORE_PKG/dist/scripts/mindlore-fts5-search.js" "{keyword}"` returns the new file
+
+If any checkpoint fails, fix it before reporting "ingest complete". Do NOT skip steps.
+
+Optional: run full health check for structural integrity:
+```bash
+node "$MINDLORE_PKG/dist/scripts/mindlore-health-check.js"
+```