agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/vault-index/SKILL.md

vault-index

Skill0 starsChanged 3 months agoMITView on GitHub

Rebuild the vault-index note from current vault state. Use when /vault-index is invoked, when the morning skill flags "vault-index not found" or a stale delta, when the user asks "what's in my vault" / "give me a vault overview" / "how's my vault organized", or after a large batch of new Concepts has landed. Do NOT use for searching specific notes — use the obsidian skill instead.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the current vault-index if it exists, to capture the prior state for the "Recent changes" section:

    line 16
  2. Distinctive:

    If it doesn't exist, note that this is a fresh build.

    line 20
  3. Distinctive:

    All Concept page names (as wikilinks)

    line 31
  4. Distinctive:

    All Clipping note names (newest first based on filename date prefix, if any)

    line 32
  5. Distinctive:

    All Context file names

    line 33
  6. Distinctive:

    All Project note names

    line 34
  7. Distinctive:

    Write the rebuilt vault-index by overwriting the file directly:

    line 38
  8. Distinctive:

    Use the exact format specified below.

    line 45
  9. Distinctive:

    Write the note with this exact structure.

    line 57
  10. Distinctive:

    Do not include Daily Notes in the index — those are temporal logs, not knowledge graph nodes, and adding them would make the morning delta …

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: /vault-index

Rebuild vault-index.md from current vault state so the morning skill's overnight delta is accurate — stale or absent index degrades morning briefings.

Don't: include Daily Notes in the index — they're temporal logs, not knowledge graph nodes. Don't run this for targeted note lookup — use the obsidian skill instead.

Steps

  1. Determine today's date and time (YYYY-MM-DD HH:MM)
  2. Read the current vault-index if it exists, to capture the prior state for the "Recent changes" section:
    obsidian read file='vault-index'
    If it doesn't exist, note that this is a fresh build.
  3. Scan the vault for current state:
    obsidian search query='Concepts/' limit=200
    obsidian search query='Clippings/' limit=200
    obsidian search query='Context/' limit=50
    obsidian search query='Projects/' limit=50
  4. From the scan results, compile:
    • All Concept page names (as wikilinks)
    • All Clipping note names (newest first based on filename date prefix, if any)
    • All Context file names
    • All Project note names
  5. Diff against the prior vault-index (from step 2) to identify what's new or missing. If no prior index exists, mark all entries as "Initial build."
  6. Write the rebuilt vault-index by overwriting the file directly:
    VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal"
    cat > "$VAULT/vault-index.md" << 'VAULTEOF'
    [insert rendered content here]
    VAULTEOF
    Use the exact format specified below.
  7. Commit the change:
    VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal"
    git -C "$VAULT" add '<the note paths you wrote>' && git -C "$VAULT" commit -m "docs: rebuild vault-index [YYYY-MM-DD]"
  8. Report what changed: counts per section, and anything flagged in the diff.

vault-index.md format

Write the note with this exact structure. The morning skill parses the section headers to detect drift — keep them verbatim.

# Vault Index

*Last updated: YYYY-MM-DD HH:MM*

## Concepts (N)

[[Concept page 1]]
[[Concept page 2]]
...

## Clippings (N)

[[Clipping note 1]]
[[Clipping note 2]]
...

## Context (N)

[[Context/accountability]]
[[Context/patterns]]
...

## Projects (N)

[[Projects/Project Name]]
...

## Recent changes

*Since prior index:*
- Added: [[Note A]], [[Note B]] (or "none")
- Removed: [names] (or "none" — note: removals are best-effort based on what was in the prior index)

When the morning skill flags drift

The morning skill reports drift when it finds Concept pages, Clippings, or Context files not listed in the current index. After morning surfaces this, invoke /vault-index to reconcile. The rebuilt index becomes the new baseline.

Notes on scan completeness

obsidian search returns results sorted by recency, limit 200. If any section likely has more than 200 entries, note it in the output and suggest running the rebuild in sections. In practice, Concepts and Clippings are the two sections most likely to grow beyond this.

Do not include Daily Notes in the index — those are temporal logs, not knowledge graph nodes, and adding them would make the morning delta meaningless.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.