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.
npx skills add Aiyo28/memento-os --skill vault-auditgit clone --depth 1 https://github.com/Aiyo28/memento-osWrote 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.
[](https://agentmods.dev/skills/aiyo28/memento-os/vault-audit)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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-DDin 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.mddocument index
4. Fluff Detection
Flag documents that may be stale or redundant:
- Files with
status: draftolder than 30 days - Duplicate content across projects
- Documents with no wikilinks (orphaned)
- MOC files with no backlinks (orphaned hubs)
experiment-contextfiles 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}
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.
- 10d ago First seen · 72 lines · 56 tokens per session scan A b93b9fc5a3a3
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.
Other skills, from other repositories
jumbo-add-guideline
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
hypermnesic-memory
Use when Hermes needs durable project or personal memory through the local hypermnesic CLI: retrieve prior context, think through related notes, resolve entities, inspect writable folders, capture notes, or preview guarded writes.
tree-ring-memory
Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
calendar
Manage calendar events via CalDAV (Google/iCloud/Nextcloud) or local ICS files. View, create, and query events.
email-assistant
Read, search, draft, and send emails via Himalaya CLI or Python IMAP/SMTP. Requires email account configuration.