lint-vault
Skill1 starsChanged 19 days agoMITView on GitHub
Check vault metadata, links, hierarchy and structural contracts in the selected deployed vault; report defects without automatic fixes.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ingest-sourceSkill
- process-inboxSkill
- process-ready-ingestion-inboxSkill
- review-vault-healthSkill
- start-a-focusSkill
- update-project-next-actionsSkill
- update-project-summarySkill
- skill.mdSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 8
Check metadata, links, hierarchy and other structural contracts.
- Distinctive: line 23
Read the vault rules and Procedure completely before acting.
- Distinctive: line 33
Do not process Inbox, rewrite summaries, normalize broad relationships, delete notes, or apply fixes unless authorized.
≈ “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.
Files
Lint Vault
Check metadata, links, hierarchy and other structural contracts. Report errors and warnings without applying fixes.
For judgment about usefulness, stale project state or unnecessary workflows, use review-vault-health. Lint findings can inform that review.
Source of truth
- Vault rules:
AGENTS.md - Checks and severity:
procedures/lint-vault.md - Contracts helper:
.agents/skills/lint-vault/scripts/contracts_audit.py(requires the siblinglinks_audit.py; note headers, Type identities and Skill pairs, not full YAML or semantic validation) - Compactness helper:
.agents/skills/lint-vault/scripts/compactness_audit.py - Tolaria icon helper:
.agents/skills/lint-vault/scripts/tolaria_icon_audit.py - Hierarchy helper:
.agents/skills/lint-vault/scripts/hierarchy_audit.py(belongs_todrift per the vault's hierarchy ADR, exceptions read fromhierarchy_rootandaccepted_double_parentfrontmatter flags;--treeprints the inferred home tree) - Link helper:
.agents/skills/lint-vault/scripts/links_audit.py(unresolved or ambiguous wikilinks, missing relative Markdown link targets and relationship values that are not wikilinks; fenced code and code spans are ignored; exit status 1 on errors) - MIT-licensed Phosphor name list:
.agents/skills/lint-vault/references/phosphor-icon-names.txt
Read the vault rules and Procedure completely before acting.
Guardrails
- Inventory canonical tracked notes and exclude implementation, local, generated, cache, attachment, and support trees.
- Use the five helpers for deterministic contract, compactness, icon, hierarchy and link findings, then inspect actual notes before conclusions. The pinned Phosphor name list checks identifiers, not glyph rendering or a live app registry; the current Tolaria picker remains authoritative. The Procedure documents reproducible refresh and upstream notices.
- Compactness thresholds are review signals, not blanket failures for long evidence.
- Recommend preservation-led routing, never blanket shortening; a threshold does not authorize deletion. A valid result may be no change, safe wording reduction, reorganization or routing, or a structural split.
- In scheduled runs, identify a narrowly matched responsible agent task when possible, report it with the proposed workflow, and wait for user confirmation before contacting it. If none exists, offer to perform the focused follow-up in the current task.
- Project human views are optional. Validate existing views, but do not report absence solely because an active Project has no saved-view surface; honor an explicit
Project view: falsemarker. Respect Inbox boundaries, UI-authored Type state, and deliberate local conventions. - Do not process Inbox, rewrite summaries, normalize broad relationships, delete notes, or apply fixes unless authorized.
- Route strategic questions to
review-vault-health.
Select this package by the requested vault role, not its name alone. Reuse rules and the complete Procedure already read in this session while they remain current; reread after a relevant change.
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
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.

