vault-lint
Skill0 starsChanged 2 months agoMITView on GitHub
Use when user says 'lint the vault', 'health check', 'find stale notes', 'vault audit'. Scans for contradictions, orphan pages, stale claims, missing cross-refs. Produces lint report in 02_KNOWLEDGE/learnings/.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jamejialicona-cmyk/vault-startertheir own version, first seen Sep 22, 2026
- slogsdon/skills-vault-knowledgetheir own version, first seen Aug 12, 2026
- tograf/sidebraintheir own version, first seen Jun 21, 2026
- hootbu/llm-wiki-mindtheir own version, first seen May 1, 2026
- Howie126313/obsidian-vault-kittheir own version, first seen Apr 13, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- Howie126313/obsidian-vault-kit★ 3same name
- jamejialicona-cmyk/vault-starter★ 2same name
- hootbu/llm-wiki-mind★ 1same name
- tograf/sidebrain★ 1same name
- slogsdon/skills-vault-knowledge★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- agent-harness-constructionSkill
- claudex-loopSkill
- click-path-auditSkill
- context-budgetSkill
- councilSkill
- deploy-projectSkill
- dreamSkill
- loop-design-checkSkill
- rebootSkill
- regex-vs-llm-structured-textSkill
- rules-distillSkill
- scrapling-officialSkill
- session-auditSkill
- shinen-designSkill
- skillspectorSkill
- skill-stocktakeSkill
- token-budgetSkill
- vault-indexSkill
- vault-ingestSkill
- vault-querySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
Write report to 02_KNOWLEDGE/learnings/YYYY-MM-DD-vault-lint.md:
- Distinctive: line 91
Read-only by default — report findings, don't auto-fix
- Distinctive: line 92
Only write the lint report itself
- Distinctive: line 93
If user says "fix automatically" → do fixes one at a time with explicit confirmation each
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
vault-lint — Karpathy LLM Wiki Health Check
When to use
User says:
- "lint the vault"
- "health check"
- "find stale notes"
- "vault audit"
- "any contradictions?"
Checks to run
1. Contradictions
Grep for opposing claims on the same fact across pages. E.g., two notes saying different things about "X library version" or "Y config flag".
2. Stale claims
Pages with date: frontmatter older than 6 months that reference fast-moving topics (versions, APIs, services). Cross-reference log.md — if newer entries on same topic contradict, flag.
3. Orphan pages
Pages with zero inbound [[wikilinks]] from other notes. Grep all pages for links to each page. Report pages with 0 hits.
4. Concept gaps
Mentions of entities/concepts without their own page. Heuristic: capitalized multi-word terms mentioned in 3+ pages but not having a dedicated note.
5. Missing cross-refs
Pages on related topics that don't link to each other. E.g., two pattern notes on "caching" that don't reference each other.
6. Fillable gaps
Concept pages with TBD or empty sections that could be filled via WebSearch — flag for ingest.
7. Index drift
Pages in 02_KNOWLEDGE/ not listed in index.md, or index entries pointing to deleted files.
Output
Write report to 02_KNOWLEDGE/learnings/YYYY-MM-DD-vault-lint.md:
---
type: learning
date: YYYY-MM-DD
tags: [vault, lint, audit]
---
# Vault Lint — YYYY-MM-DD
## Summary
- N pages scanned
- X contradictions
- Y orphans
- Z stale
## Contradictions
- [[page-a]] vs [[page-b]]: <claim>
## Orphans
- [[page-c]] — suggest: link from [[page-d]]
## Stale
- [[page-e]] — last updated YYYY-MM-DD, references <topic>, newer info in [[log.md]] line N
## Gaps
- Concept "<X>" mentioned in 3 pages, no dedicated note
- Suggested ingest: <WebSearch query>
## Index drift
- [[page-f]] in 02_KNOWLEDGE/ but missing from index.md
- index.md → [[dead-link]] no longer exists
## Actions
- [ ] Resolve contradiction X
- [ ] Link orphan Y from Z
- [ ] Update stale page EAppend to log.md:
## [YYYY-MM-DD] lint | N findings
Report: [[02_KNOWLEDGE/learnings/YYYY-MM-DD-vault-lint]]Rules
- Read-only by default — report findings, don't auto-fix
- Only write the lint report itself
- If user says "fix automatically" → do fixes one at a time with explicit confirmation each
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.