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 emguide/headless-obsidian-mcp --skill obsidian-vaultgit clone --depth 1 https://github.com/emguide/headless-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/emguide/headless-obsidian-mcp/obsidian-vault)<a href="https://agentmods.dev/skills/emguide/headless-obsidian-mcp/obsidian-vault"><img src="https://agentmods.dev/badge/skills/emguide/headless-obsidian-mcp/obsidian-vault/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/emguide/headless-obsidian-mcp/obsidian-vault"><img src="https://agentmods.dev/badge/skills/emguide/headless-obsidian-mcp/obsidian-vault.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 | $0.00087 | $0.02703 |
| Opus 5 | $0.00044 | $0.01352 |
| Sonnet 5 | $0.00017 | $0.00541 |
| Haiku 4.5 | $0.00009 | $0.00270 |
Grade A, and why
obsidian-vault 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 9d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working an Obsidian vault
The server states its own shared conventions in the MCP instructions it sends
at initialize — pagination (offset/limit/truncated), the shared
folder/tags/where filter vocabulary, link-integrity reporting on writes,
opt-in include_context, did-you-mean suggestions, git-sync behavior, and tool
exposure. Read those; this skill does not repeat them.
What it adds is the part conventions can't carry: which tool answers which intent, and how the tools compose into flows.
Routing: intent → tool
Reading:
| Intent | Tool |
|---|---|
| "Find something about X" (topical) | search_notes_ranked — BM25, best notes first |
| Literal string or regex, every hit | search_notes |
| User named a note in prose ("the Alpha Project note") | resolve_note — title/alias/basename → path |
| "today's note", a date, "yesterday" | resolve_daily_note |
| "What's in this vault?" | list_folders, then list_tags, then list_notes |
| Read a whole note | read_notes (batches up to 50) |
| Read part of a note | get_outline, then read_section |
| "What links here / what does this reference?" | get_links |
| "I'm looking at X — what else matters?" | get_related_notes |
| Notes with a frontmatter condition | query_notes |
| Notes carrying a tag | find_by_tag |
| "What have I touched lately?" | list_recent_notes |
| Outstanding checkboxes | list_tasks |
| Vault health | get_vault_stats, drill down with list_vault_issues |
| "Why is tool X missing?" | get_config (always exposed) |
Writing (present only when the operator's OBSIDIAN_TOOLS policy exposes them):
| Intent | Tool |
|---|---|
| New note | write_note, or apply_template for a templated one |
| Add to the end / start | append_note / prepend_note |
| Add or rewrite one section | add_section / append_to_section / replace_section |
| Change a specific string | patch_note |
| Tick or un-tick a checkbox | set_task_state |
| Tags | add_tag / remove_tag |
| Frontmatter | set_frontmatter, add_property_values / remove_property_values, rename_property |
| Rename or relocate a note | move_note (rewrites inbound wikilinks) |
| Rename a heading | rename_section (rewrites inbound #anchors) |
| The same change across many notes | bulk_edit |
| Remove a note | delete_note (trash-safe by default) |
| Create a folder | create_folder (invisible to list_folders until it holds a note) |
| Rename or relocate a folder | move_folder (rewrites inbound folder-qualified links) |
| Remove a folder | delete_folder (trash-safe; recursive:true if not empty) |
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.
- 9d ago First seen · 240 lines · 87 tokens per session scan A de68a5b72ba1
obsidian-vault is a skill published in the GitHub repository emguide/headless-obsidian-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,703 once invoked, about $0.0004 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
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…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.