wiki-status

Wiki Status — Audit & Delta

You are computing the current state of the wiki: what's been ingested, what's new since last ingest, and what the delta looks like. This helps the user decide whether to append (ingest the delta) or rebuild (archive and reprocess everything).

Before You Start

1. Resolve config — follow the Config Resolution Protocol in llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → ~/.obsidian-wiki/config → prompt setup). This gives OBSIDIAN_VAULT_PATH, OBSIDIAN_SOURCES_DIR, CLAUDE_HISTORY_PATH, and CODEX_HISTORY_PATH.
2. Read .manifest.json at the vault root — this is the ingest tracking ledger

The Manifest

The manifest lives at $OBSIDIAN_VAULT_PATH/.manifest.json. It tracks every source file that has been ingested. If it doesn't exist, this is a fresh vault with nothing ingested.

Source keys are canonical absolute paths (~ and env vars expanded). Never mix ~-relative and absolute keys — the same file would be tracked twice and re-ingested. See llm-wiki/SKILL.md → .manifest.json. Repair a mixed manifest with scripts/manifest.py normalize <vault>.

{
  "version": 1,
  "last_updated": "2026-04-06T10:30:00Z",
  "sources": {
    "/absolute/path/to/file.md": {

Step 1: Scan Current Sources

Build an inventory of everything available to ingest right now:

Documents (from OBSIDIAN_SOURCES_DIR)

Claude History (from CLAUDE_HISTORY_PATH)

Codex History (from CODEX_HISTORY_PATH)

Any other sources the user has pointed at previously

Check the manifest for source paths outside the standard directories.

Step 2: Compute the Delta

Compare current sources against the manifest. Classify each source file:

When a manifest entry has no content_hash (older entry), fall back to mtime comparison only.

For Claude history specifically, also compute:

• New projects (directories in ~/.claude/projects/ not in manifest)
• New conversations within existing projects
• Updated memory files

For Codex history specifically, also compute:

• New rollout files under sessions/**
• Updated session_index.jsonl entries (session title/freshness changes)
• Archived rollout delta only when archive coverage is requested

Step 3: Report the Status

Visibility tally (before rendering the report): Grep frontmatter across all vault .md pages for visibility/internal and visibility/pii tag values. Count:

• public = pages with visibility/public tag or no visibility/ tag at all
• internal = pages with visibility/internal tag
• pii = pages with visibility/pii tag

Include this in the Overview section as Page visibility: N public · M internal · K pii. Skip the line if all pages are untagged (fully public vault).

Present a clear summary:

Step 3b: Compute Token Footprint

After building the status summary, compute the token footprint estimate:

1. Per-tier page sizes — Glob all .md pages. Read the tier: frontmatter field of each (cheap grep). Group pages by tier value (core, supporting, peripheral; unset → supporting).

2. Estimate tokens — For each page, estimate token count as file_size_bytes / 4 (4 chars/token heuristic — no actual tokenizer needed). Sum per tier and total.

3. Index-only estimate — Estimate the cost of an index-only pass: sum len(title) + len(summary) + len(tags) for each page frontmatter (~100 chars each on average), divided by 4.

4. Typical query estimate — Index-only estimate + average full-read cost of 5 pages (total_chars / total_pages * 5 / 4).

5. Threshold check — Read WIKI_TOKEN_WARN_THRESHOLD from config (default: 100000). If 0, skip the warning. If full-wiki token estimate exceeds the threshold, emit a ⚠️ warning with the three remediation suggestions shown in the template above.

6. Include in every standard status run — both normal and insights mode. The methodology note (4 chars/token heuristic) appears as a footnote below the table.

Step 4: What to Do Next

Replace the old single-line Recommendation with a ranked What to Do Next section. Gather these signals before rendering:

4a: Gather signals

0. Staged writes pending (only when WIKI_STAGED_WRITES=true) — Glob $OBSIDIAN_VAULT_PATH/_staging/**/*.md and **/*.patch.md. Count new pages and patches separately. Report the oldest file's age (mtime). This is always listed first if any staged files exist — it has the highest intent signal (the LLM already did the work; the human just needs to review).

1. _raw/ files — list every file at the top level of $OBSIDIAN_VAULT_PATH/_raw/ that isn't a .gitkeep, excluding the _archived/ subdirectory (already-promoted drafts kept for provenance, not pending work). Count and name them.

2. Stale core pages — scan all vault .md files. A page is "stale" when its updated frontmatter field is ≥90 days before today's date AND it has ≥5 incoming wikilinks (i.e., it's "core" — other pages depend on it). List them by name + last-updated date.

3. Orphan pages — pages with zero incoming wikilinks. To compute: glob all .md pages, extract every [[wikilink]], count references to each page, collect pages with incoming == 0. Show up to 5 names; report total count.

4. Synthesis opportunities — check hot.md for any recent /wiki-synthesize run summary. If the last synthesis run reported N opportunities, surface that count. If no synthesis has been run recently (not in hot.md or log.md within last 14 days), flag it as "synthesis scan overdue".

5. Source delta — from Step 2: count of new + modified sources ready to ingest.

6. Lint issues — check log.md for a recent /wiki-lint run (within last 30 days). If a recent run recorded broken links or missing frontmatter, surface the count. If no lint run appears in the log, flag "lint not run recently".

4b: Rank and render

Score each category and emit a ranked list, capped at 6 items. Always rank in this priority order (skip a category if its count is 0 or it has nothing to report):

Render as:

Empty state: If all categories have nothing to report (no staged files, no _raw/ files, no orphans, no stale pages, no synthesis opportunities, no new sources, no lint issues), output instead:

Overflow: If more than 6 items would be shown, add a footer line: _(N more items available — run /wiki-status --full to see all)_. The --full flag is not yet implemented; this is forward-looking copy that sets expectations.

Insights Mode

Triggered when the user asks something like "wiki insights", "what's central in my wiki", "show me the hubs", "cross-domain bridges", "what pages are most important", or "wiki structure". This mode is additive — it doesn't replace the delta report, it analyzes the shape of the wiki itself.

Where the delta report tells the user what's pending, insights mode tells them what they've already built and where the interesting structure lives. Complements wiki-lint (which finds problems) by surfacing interesting structure.

What to compute

First, run the graph analyser. This replaces manual wikilink parsing — one command produces all the raw data you need:

Output fields used below:

• god_nodes — pages ranked by total degree (in + out). Use for anchor pages and hub classification.
• communities — page clusters by link density (label propagation / Leiden). Use for bridge detection and cluster labelling.
• surprising_connections — cross-community edges ranked by unexpectedness. Use directly in the Surprising Connections section.
• dead_ends — pages with zero outgoing links. Use for orphan-adjacent and cross-linker suggestions.
• isolated — pages with zero links in either direction. Use for stubs/orphan reporting.
• stats — total pages, edges, communities.

Fallback (if obsidian-wiki is not installed): glob all .md pages, extract every [[wikilink]], and build incoming, outgoing, and tags maps manually.

You'll reuse this data across all sections below.

1. Anchor pages (top hubs). Pages with the most incoming links — the load-bearing concepts.

   • Rank all pages by incoming count, take top 10
   • For each, note both incoming and outgoing counts: pages with high incoming and high outgoing are connector hubs (most valuable)
   • Pages with high incoming but zero outgoing are sink hubs — flag as cross-linker candidates

2. Bridge pages. Pages that connect otherwise-disconnected tag clusters — removing them would partition the graph. These are often more structurally important than raw hub count suggests.

   • For each page P, find pairs of pages (A, B) where:
     • A links to P, B is linked from P (or vice versa)
     • A and B share no tags with each other
     • P is the only path between A's tag cluster and B's tag cluster within 2 hops
   • Rank by how many cross-cluster pairs P bridges; show top 5
   • Label each: "P bridges [tag-cluster-A] ↔ [tag-cluster-B]"

3. Tag cluster cohesion. For each tag with ≥ 5 pages, score how tightly the pages within it are interconnected:

   • n = number of pages sharing this tag
   • actual_links = number of wikilinks between any two pages in this tag group
   • cohesion = actual_links / (n × (n−1) / 2) — ratio of actual links to maximum possible
   • Fragmented clusters (cohesion < 0.15, n ≥ 5): these pages share a topic but aren't woven together. Surface them as cross-linker targets.
   • Show top 5 tags by cohesion (strongest clusters) and bottom 5 (most fragmented)

4. Surprising connections. Cross-category wikilinks that are non-obvious — scored by how unexpected they are:

   • Score each wikilink that crosses category boundaries (e.g., concepts/ → entities/, skills/ → synthesis/):
     • +3 if the linking page or claim is marked ^[ambiguous] (uncertain connection, worth reviewing)
     • +2 if the linking page is marked ^[inferred] (synthesized, not directly stated)
     • +2 if the categories are in different knowledge layers (e.g., concepts ↔ entities more surprising than concepts ↔ concepts)
     • +2 if source page has ≤ 2 total links (peripheral) but target has ≥ 8 (hub) — unexpected reach from edge to center
   • Show top 5 scored connections with a plain-language reason for each

5. Orphan-adjacent suggestions. Pages linked from a top-10 hub but with zero outgoing links of their own. Dead-ends in high-traffic areas — prime cross-linker candidates.

6. Rough clusters. Group anchor pages by dominant tag. (Simple tag intersection — just for orientation.)

7. Graph delta since last run. Compare the current link graph to the snapshot stored in the previous _insights.md:

   • Read the <!-- GRAPH_SNAPSHOT: ... --> line at the bottom of the previous _insights.md (if it exists) — it contains a compact JSON edge list
   • Compute: new pages added, pages removed, new wikilinks created, wikilinks removed
   • Flag: pages that were isolated last run but now have incoming links ("newly connected: X, Y")
   • Flag: pages that lost incoming links since last run ("link target may have been renamed: A, B")
   • If no previous snapshot exists, skip this section

8. Tier assignment suggestions. After computing hubs and bridges, recommend tier: changes. Never write tier: to pages — only surface suggestions so the human can decide.

   • Promote to core: pages with ≥5 incoming links OR top-5 bridge position that currently have tier: supporting or no tier: field
   • Demote to peripheral: pages with ≤1 incoming link AND not updated in 90+ days that currently have tier: supporting or tier: core
   • Show up to 10 suggestions (promotions first, then demotions), formatted as:

     Tier Suggestions:
     ↑ core    [[concepts/attention-mechanism]] — 14 incoming links, currently tier=supporting
     ↑ core    [[entities/andrej-karpathy]]     — bridge (3 cluster pairs), currently unset
     ↓ peripheral [[concepts/old-concept]]       — 0 incoming, 120 days stale
   • If all high-link pages already have tier: core and all low-link pages have tier: peripheral, emit: "Tier assignments look healthy — no changes suggested."

9. Suggested questions. Questions this wiki structure is uniquely positioned to answer — or that reveal gaps:

   • From ^[ambiguous] claims: "Resolve: What is the exact relationship between X and Y?"
   • From bridge pages: "Explore: Why does P connect [cluster-A] to [cluster-B]?"
   • From pages with zero incoming links: "Link: X has no incoming links — what should reference it?"
   • From fragmented clusters (cohesion < 0.15): "Audit: Should tag [T] be split into more focused sub-tags?"
   • Show up to 7, prioritizing AMBIGUOUS first, then bridge nodes, then isolates

Output

Write the result to _insights.md at the vault root. Overwrite freely — it's regenerable. At the very end, embed a compact graph snapshot as an HTML comment so the next run can diff against it.

# Wiki Insights — <TIMESTAMP>
 
## Anchor Pages (top 10 hubs)
| Page | Incoming | Outgoing | Note |
|---|---|---|---|
| [[concepts/transformer-architecture]] | 23 | 8 | connector hub |
| [[entities/andrej-karpathy]] | 17 | 0 | sink hub — cross-linker candidate |
 
## Bridge Pages (top 5)
| Page | Bridges | Cross-cluster pairs |
|---|---|---|
| [[concepts/exponential-growth]] | #ml ↔ #economics | 4 pairs |
 
## Tag Cluster Cohesion
### Most cohesive (well-linked)
- **#ml** — 12 pages, cohesion 0.41
### Most fragmented (cross-linker targets)
- **#systems** — 7 pages, cohesion 0.06 ⚠️ run cross-linker on this tag
 
## Surprising Connections (top 5)
- [[concepts/scaling-laws]] → [[entities/gordon-moore]] — score 5
  - Reason: cross-layer (concepts ↔ entities), marked ^[inferred]
- ...
 
## Orphan-Adjacent (dead-ends near hubs)
- [[concepts/foo]] — linked from 3 hubs, 0 outbound links
 
## Rough Clusters
- **#ml** — transformer-architecture, attention-mechanism, scaling-laws
- **#systems** — distributed-consensus, raft, paxos
 
## Graph Delta Since Last Run
- +3 new pages, +11 new wikilinks
- Newly connected: [[concepts/bar]], [[entities/baz]]
- Lost incoming links: [[references/old-paper]] (target may have been renamed)
 
## Tier Suggestions
↑ core    [[concepts/attention-mechanism]] — 14 incoming links, currently tier=supporting
↑ core    [[entities/andrej-karpathy]]     — top bridge (4 cluster pairs), currently unset
↓ peripheral [[concepts/old-concept]]       — 0 incoming, 132 days stale
 
## Questions Worth Asking
1. Resolve: What is the exact relationship between `scaling-laws` and `moore's-law`? (^[ambiguous] claim)
2. Explore: Why does `exponential-growth` bridge #ml and #economics?
3. Link: `references/foo.md` has no incoming links — what should reference it?
4. Audit: Should tag `#systems` be split? (cohesion 0.06, 7 pages)
 
<!-- GRAPH_SNAPSHOT: {"nodes":["concepts/foo","entities/bar"],"edges":[["concepts/foo","entities/bar"]]} -->

After writing the file, append to log.md:

- [TIMESTAMP] STATUS_INSIGHTS anchors=10 bridges=N cohesion_checked=T surprising=5 questions=7 delta="+N pages +M links" tier_suggestions=N

When to skip

• Vaults with fewer than 20 pages — not enough graph structure. Tell the user and skip.
• After a fresh wiki-rebuild — wait until at least one ingest has happened.

Notes

• If the manifest doesn't exist, report everything as "new" and recommend a full ingest
• This skill only reads and reports — it doesn't modify anything (except writing _insights.md in insights mode, which is regenerable)
• The actual ingest work is done by the ingest skills (wiki-ingest, claude-history-ingest, codex-history-ingest)
• Those skills are responsible for updating the manifest after they finish

QMD Refresh After Vault Writes

QMD is a search index, not the source of truth. If $QMD_WIKI_COLLECTION is empty or unset, skip this step. Run it only after this skill has written or rewritten vault markdown. If QMD refresh fails, do not roll back the vault changes; report the QMD status separately.

Use $QMD_CLI if set; otherwise use qmd.

${QMD_CLI:-qmd} update

If the output says vectors are needed or embeddings may be stale, run:

${QMD_CLI:-qmd} embed

Verify the collection with either:

${QMD_CLI:-qmd} ls "$QMD_WIKI_COLLECTION"

or, when a specific page path is known:

${QMD_CLI:-qmd} get "qmd://$QMD_WIKI_COLLECTION/<page>.md" -l 5

Record one of:

• QMD refreshed: update + embed + verified
• QMD refreshed: update only + verified
• QMD skipped: QMD_WIKI_COLLECTION unset
• QMD skipped: qmd CLI unavailable
• QMD failed: <short error summary>