obsidian-vault

obsidian-vault is a skill for Claude Code from odere-pro/claude-wiki-pages-plugin. It costs 98 tokens per session (597 once invoked), scanned A, original, MIT.

A safety guide for using the Obsidian command-line tool, which lets scripts work with notes in an Obsidian vault.

In plain words
What is it for?
It is for resolving the requested vault, passing it explicitly to every Obsidian command, and keeping related file operations inside that vault.
Why use it?
It prevents commands and file operations from accidentally targeting the wrong vault or writing outside the selected one.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-wiki-pages plugin — 26 skills, 5 commands, 17 agents, 7 hooks shipped together

Good fit It is for resolving the requested vault, passing it explicitly to every Obsidian command, and keeping related file operations inside that vault.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault
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 odere-pro/claude-wiki-pages-plugin --skill obsidian-vault
Clone the repo
git clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-plugin

Made for: Claude Code.

Or install claude-wiki-pages, the plugin that ships this one along with the rest of its 26 skills, 5 commands, 17 agents, 7 hooks.

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 obsidian-vault

README.md
[![agentmods](https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault/github.svg)](https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault)
Your own site
<a href="https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/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.

agentmods 80×15 button for obsidian-vault

Your own site · 80×15
<a href="https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/obsidian-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 597 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 $0.00098 $0.00597
Opus 5 $0.00049 $0.00298
Sonnet 5 $0.00020 $0.00119
Haiku 4.5 $0.00010 $0.00060

Measured 11d ago against content hash 58ec65e28c3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 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.

skills/obsidian-vault/SKILL.md · 50 lines

What it actually says

Obsidian Vault — safe CLI scoping

The Obsidian CLI (obsidian, used by obsidian-cli, obsidian-graph-colors) can act on any vault registered on the machine. This skill is the convention that keeps an agent inside the one vault it was asked to work on — the behavioural twin of the firewall hook, which enforces the same boundary on the write path.

The rule

  1. Resolve the vault first. VAULT=$(bash scripts/resolve-vault.sh && …) — use the four-tier resolution, never a hard-coded path. The resolved path is the only vault you may touch.
  2. Always pass the vault explicitly. Every Obsidian CLI call carries --vault "$VAULT" (or the CLI's equivalent). Never rely on the CLI's "current"/"default" vault — that is whatever the user last opened.
  3. Never operate on a different vault name. If a task names another vault, stop and surface it; do not switch vaults to satisfy it.
  4. File operations stay inside the vault. Reads/writes you issue alongside the CLI must resolve under $VAULT. Writes outside it are rejected by the firewall hook anyway — treat that block as a contract, not an obstacle to work around.

Why both a skill and a hook

  • The hook (scripts/firewall.sh, firewall engine command) is the enforcement: it blocks an out-of-vault Write/Edit regardless of intent.
  • This skill is the intent: it teaches an agent to scope correctly in the first place, so the hook rarely has to fire. Defence in depth — a confused agent is stopped by the hook; a careful agent never reaches it.

Configuration

Vault isolation is configured under firewall in claude-wiki-pages.json (enabled, mode = enforce/warn/off, allowPaths, denyPaths). To let an agent write to an extra root (e.g. a shared notes directory), add it to firewall.allowPaths — do not disable the firewall.

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. 11d ago First seen · 50 lines · 98 tokens per session scan A 58ec65e28c3c

Subscribe to this mod's changes

obsidian-vault is a skill published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 597 once invoked, about $0.0005 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

schema-evolve

This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…

voxpelli/vp-claude · 139 tokens

knowledge-maintain

This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies structural fixes (missing sections…

voxpelli/vp-claude · 183 tokens

raindrop-triage

This skill should be used when the user asks to 'triage unsorted bookmarks', 'clean up raindrop inbox', 'sort unsorted', 'organize bookmarks', 'raindrop triage', 'process bookmark backlog', 'promote triaged bookmarks', 'classify triaged', 'raindrop cleanup', 'deduplicate bookmarks', 'find duplicate bookmarks', 'tag…

voxpelli/vp-claude · 181 tokens

knowledge-garden

This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a…

voxpelli/vp-claude · 152 tokens

knowledge-prime

This skill should be used when the user asks to 'prime context', 'load project knowledge', 'what do we know about this project', 'knowledge brief', 'project context', 'what packages are documented', 'show coverage for this project', 'dependency coverage report', 'which of our deps have notes', 'knowledge primer'…

voxpelli/vp-claude · 128 tokens

nudge

This skill (explicit /nudge only) manages Claude Code feature-adoption nudges sourced from the Basic Memory note main/reference/claude-code-noteworthy-features. Bare /nudge = Mode A (sync): re-read the note, filter out features already marked adopted or declined, and regenerate the tip cache…

voxpelli/vp-claude · 210 tokens