vault-audit

vault-audit is a skill for Claude Code from Aiyo28/memento-os. It costs 56 tokens per session (563 once invoked), scanned A, original, MIT.

A vault health check for a project knowledge store. It checks project structure, finds outdated notes, reviews expired items, and processes the inbox.

In plain words
What is it for?
Use it to check required project files, flag stale or expired reasoning notes, identify items to archive or remove, and review unprocessed inbox entries.
Why use it?
It helps prevent old or unprocessed information from making the vault confusing or unreliable.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the memento-os plugin — 7 skills shipped together

Good fit Use it to check required project files, flag stale or expired reasoning notes, identify items to archive or remove, and review unprocessed inbox entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiyo28/memento-os/vault-audit
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.

Any agent
npx skills add Aiyo28/memento-os --skill vault-audit
Clone the repo
git clone --depth 1 https://github.com/Aiyo28/memento-os

Made for: Claude Code.

Or install memento-os, the plugin that ships this one along with the rest of its 7 skills.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiyo28/memento-os/vault-audit/github.svg)](https://agentmods.dev/skills/aiyo28/memento-os/vault-audit)
Your own site
<a href="https://agentmods.dev/skills/aiyo28/memento-os/vault-audit"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/vault-audit/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-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiyo28/memento-os/vault-audit"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/vault-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 563 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 $0.00056 $0.00563
Opus 5 $0.00028 $0.00282
Sonnet 5 $0.00011 $0.00113
Haiku 4.5 $0.00006 $0.00056

Measured 10d ago against content hash b93b9fc5a3a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vault-audit 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 10d 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.

adapters/codex/skills/vault-audit/SKILL.md · 72 lines

What it actually says

/vault-audit

Check structure. Flag staleness. Process inbox. Suggest cleanup.

Steps

1. Structure Check

Verify each project under Projects/ has:

  • _context.md (required)
  • Active Reasoning Artifacts table in _context.md
  • Subfolders created on-demand (don't flag missing empty folders)

2. Staleness Scan

For each project _context.md, check Active Reasoning Artifacts table:

Expiry check (first — overrides priority-based staleness):

  • Scan for expires: YYYY-MM-DD in artifact text
  • If past expiry date → flag as EXPIRED regardless of priority
  • Show: "EXPIRED: #X — <artifact summary> (expired YYYY-MM-DD). Still valid?"

Priority-based staleness (for artifacts without expiry):

Priority Age Action
critical > 90 days Flag for review — ask if invalidation trigger has fired
volatile > 30 days Flag for resolution — upgrade to critical or delete
settled > 90 days Suggest archiving to Decisions/ folder
noise Any age Flag for immediate removal
superseded Any age Should already be evicted — flag if still in L1

3. Inbox Processing

Check _inbox/ for unprocessed items. For each:

  • Identify type (research, note, decision, reference)
  • Route to correct project and subfolder
  • Add proper frontmatter
  • Update project _context.md document index

4. Fluff Detection

Flag documents that may be stale or redundant:

  • Files with status: draft older than 30 days
  • Duplicate content across projects
  • Documents with no wikilinks (orphaned)
  • MOC files with no backlinks (orphaned hubs)
  • experiment-context files past their teardown date
  • [S] seeds dormant > 90 days (not activated, not decided)

5. Report

## Vault Audit — {date}

**Structure:** {OK or issues found}
**Stale artifacts:** {count by priority level}
**Inbox:** {count processed, count remaining}
**Suggestions:** {cleanup actions}
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. 10d ago First seen · 72 lines · 56 tokens per session scan A b93b9fc5a3a3

Subscribe to this mod's changes

vault-audit is a skill published in the GitHub repository Aiyo28/memento-os (4 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 563 once invoked, about $0.0003 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.

Related

Other skills, from other repositories