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 bettyguo/obsidian_mcp --skill build-mocgit clone --depth 1 https://github.com/bettyguo/obsidian_mcpWrote 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/bettyguo/obsidian_mcp/build-moc)<a href="https://agentmods.dev/skills/bettyguo/obsidian_mcp/build-moc"><img src="https://agentmods.dev/badge/skills/bettyguo/obsidian_mcp/build-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/bettyguo/obsidian_mcp/build-moc"><img src="https://agentmods.dev/badge/skills/bettyguo/obsidian_mcp/build-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 | $0.00034 | $0.00653 |
| Opus 5 | $0.00017 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
build-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 11d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
The user wants a navigation hub for a topic. MOCs are the LYT central primitive; they replace folders for many vaults. Default output is static wikilinks (round-trip safe under git); the user can opt into Dataview style.
Procedure
- Capture the topic phrase from the user (e.g. "RAG research"). If absent, ask.
- Call
find_related(seed=topic_phrase, top_k=30). These are the candidate notes. - Optionally call
find_orphans(near_topic=topic_phrase)and merge results — orphans near the topic almost always belong in the MOC. - Call
read_notes_batch(paths=[top 10 candidates])to get headings and lead paragraphs for clustering. - Cluster the candidates into 2–5 sub-themes. Use the notes' headings, primary tags, and lead paragraphs as features. Name each sub-theme with a short imperative phrase.
- Surface the proposed MOC structure to the user IN CHAT (sub-themes + notes that would fall under each). Wait for approval; the user may want to drop notes, add notes, or rename a sub-theme.
- Call
build_moc(title=topic_phrase, notes=approved_paths, structure="grouped", style="wikilinks", confirm=true). Default out path isMOCs/<title>.md; user may override. - Reply with the path and a 2-sentence top-line. Suggest the user link the MOC from their
Home.mdor top-level index (one suggestion, not a demand).
Output format (the MOC body itself)
# {Topic}
> MOC for: {topic phrase}
> Generated: {YYYY-MM-DD}
## {Sub-theme 1}
- [[Note A]]
- [[Note B]]
## {Sub-theme 2}
- [[Note C]]
- [[Note D]]
## Related MOCs
- [[Related MOC]]
## Open questions
-
Anti-patterns
- Don't auto-include every candidate. Cap at ~20 notes. A MOC with 60 entries is a search result, not a map.
- Don't use Dataview by default. Static wikilinks are round-trip safe and don't require a plugin. Use
style="dataview"only when the user asks. - Don't make the MOC encyclopedic. Headings should be imperative ("Use cross-encoders for reranking") not nominal ("Cross-encoders").
- Don't link orphans into the MOC without the user's explicit OK, even if
find_orphansreturned them. Orphan triage is the user's call. - Don't write the MOC over an existing one without
overwrite=Truefrom the user.
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.
- 11d ago First seen · 56 lines · 34 tokens per session scan A 5e7b546d37b4
build-MOC is a skill published in the GitHub repository bettyguo/obsidian_mcp (8 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 653 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.