vault-health

vault-health is a command for Claude Code from reluctantfuturist/loyal-wingman. It costs 15 tokens per session (805 once invoked), scanned A, original, MIT.

A command that checks the health of an entire knowledge vault, including its folders, links, inbox, and stale content. A knowledge vault is a collection of linked notes and reference files.

In plain words
What is it for?
Use it to run a full or focused check of vault structure, link integrity, inbox age, stale content, and file placement.
Why use it?
It helps find broken links, misplaced files, old unprocessed notes, and content that is no longer connected to the rest of the vault.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the loyal-wingman plugin — 12 skills, 7 commands shipped together

Good fit Use it to run a full or focused check of vault structure, link integrity, inbox age, stale content, and file placement.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/reluctantfuturist/loyal-wingman/vault-health
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/reluctantfuturist/loyal-wingman

Made for: Claude Code.

Or install loyal-wingman, the plugin that ships this one along with the rest of its 12 skills, 7 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vault-health

README.md
[![agentmods](https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/vault-health/github.svg)](https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/vault-health)
Your own site
<a href="https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/vault-health"><img src="https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/vault-health/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vault-health

Your own site · 80×15
<a href="https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/vault-health"><img src="https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/vault-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00805
Opus 5 $0.00008 $0.00402
Sonnet 5 $0.00003 $0.00161
Haiku 4.5 $0.00002 $0.00081

Measured 12d ago against content hash dc8913b0f9e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vault-health scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/vault-health.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vault-health

Comprehensive health check across the entire vault.

Usage

/vault-health                      # Full vault check
/vault-health --quick              # Critical issues only
/vault-health --links              # Link integrity focus

Process

Step 1: Scan Vault Structure

Check all folders exist and are populated:

  • 00_Inbox/
  • 01_Meta/
  • 02_World/
  • 03_Research/
  • 04_Media/
  • 05_Marketing/
  • 10_Projects/

Step 2: Validate All Links

REQUIRED SUB-SKILL: Invoke validate-links with full vault scope

Validate-links will check:

  • All [[wikilinks]] resolve
  • Bidirectional linking in world bible
  • Orphaned files (no incoming links)

Step 3: Check Inbox Health

Scan 00_Inbox/:

  • Count files
  • Flag files >7 days old
  • Check parking lot status

If issues found: Recommend /inbox-processor command

Step 4: Query Stale Content

REQUIRED SUB-SKILL: Invoke query-context to find:

  • Files not modified in >6 months
  • World bible entries never referenced in scenes
  • Research files never linked from world bible
  • Scene seeds >3 months old

Step 5: Check Structural Issues

  • Files in wrong folders (e.g., scene in 01_Meta)
  • Missing required frontmatter
  • Empty folders

Step 6: Report by Severity

## Vault Health Report

**Scan date:** [date]
**Files scanned:** [count]

---

### 🔴 Critical (Fix Now)

**Broken Links:** (from validate-links)
[list]

**Structural Errors:**
[list]

---

### 🟡 Warning (Review Soon)

**Inbox Issues:**
- 00_Inbox has [X] files >7 days old
  → Run /inbox-processor

**Missing Backlinks:** (from validate-links)
[list]

**Stale Content:** (from query-context)
[list]

---

### 🟢 Info (When Convenient)

**Orphaned Entries:** (from validate-links)
[list]

**Old Scene Seeds:**
[list]

---

### ✅ Healthy Areas

- Link integrity: [X]% (from validate-links)
- Frontmatter compliance: [X]%
- Folder structure: OK

---

### Summary

| Category | Status | Action |
|----------|--------|--------|
| Links | [status] | validate-links |
| Inbox | [status] | /inbox-processor |
| Stale content | [status] | /audit [folder] |

**Overall:** [Healthy|Needs Attention|Requires Cleanup]

Read the full file on GitHub · 163 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 163 lines · 15 tokens per session scan A dc8913b0f9e3

Subscribe to this mod's changes

vault-health is a command published in the GitHub repository reluctantfuturist/loyal-wingman (7 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 805 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.