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 oldwinter/skills --skill vault-mocgit clone --depth 1 https://github.com/oldwinter/skillsWrote 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/oldwinter/skills/vault-moc)<a href="https://agentmods.dev/skills/oldwinter/skills/vault-moc"><img src="https://agentmods.dev/badge/skills/oldwinter/skills/vault-moc/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/oldwinter/skills/vault-moc"><img src="https://agentmods.dev/badge/skills/oldwinter/skills/vault-moc.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 | $0.00176 | $0.01829 |
| Opus 5.5 | $0.00070 | $0.00732 |
| Sonnet 5.5 | $0.00035 | $0.00366 |
| Haiku 4.5 | $0.00018 | $0.00183 |
Grade A, and why
vault-moc 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault MOC
A MOC is a Markdown note whose job is navigation: a reader lands on it, understands the shape of a topic, and reaches the real notes in one click. Build MOCs over a vault that already contains the notes. Link evidence comes from the vault, not from imagination.
Scope
Reach for this when the request names a MOC, map, index, dashboard, or summary over notes that already exist in an Obsidian vault.
In scope: topic MOCs, dashboard MOCs, dated summary MOCs (year, quarter, project span), folder or project index notes, and refreshing an existing MOC.
Out of scope: saving one new note (to-note), Canvas or graph deliverables (canvas-atlas), Obsidian syntax questions (obsidian-markdown).
Defaults: the user's language and vault language win. One MOC per request. A MOC is an index; do not turn it into a second copy of the notes.
Completion contract
Done when all of these hold:
- Every target MOC file exists at a vault-relative path inside the found vault.
- Every wikilink in those files resolves to an existing note path, alias, or heading; unresolved candidates are listed in the report, never guessed into the MOC.
- Each MOC carries a dated scope line naming the topic, the covered date range, and the cutoff date of the inventory.
- The report records the scope decision, the notes inventoried, the links verified, the files written or updated, and the gaps left.
- No note outside the target MOC set was created, modified, deleted, or moved.
Steps
-
Find the vault. A path the user names wins. Otherwise use
OBSIDIAN_VAULT_ROOTwhen it contains a.obsidian/folder. Otherwise read Obsidian's own vault registry (obsidian.jsonin the platform app-data folder) and prefer the vault currently open, then the most recently opened. Otherwise do one shallow search of the home folder and take.obsidian/folders found near the current project. With several candidates left, ask once, listing their paths.Done when: exactly one vault root, and it contains
.obsidian/.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 97 lines · 176 tokens per session scan A 7d6a0c10f822
vault-moc is a skill published in the GitHub repository oldwinter/skills (9 stars, last pushed 3d ago), licensed MIT. It adds 176 tokens to every session and 1,829 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.