obsidian-cli

obsidian-cli is a skill for Claude Code from jackal092927/obsidian-official-cli-skills. It costs 57 tokens per session (1,705 once invoked), scanned A, original, MIT.

A skill for using the official Obsidian command-line interface to manage an Obsidian vault, a folder of linked Markdown notes, including searches, backlinks, tags, tasks, and properties.

In plain words
What is it for?
Useful for searching notes, finding links and backlinks, managing tags or tasks, reading properties, and querying Obsidian bases.
Why use it?
It helps an agent use Obsidian’s indexed features correctly instead of treating every operation as simple file editing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the obsidian-cli plugin — 1 skill shipped together

Good fit Useful for searching notes, finding links and backlinks, managing tags or tasks, reading properties, and querying Obsidian bases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jackal092927/obsidian-official-cli-skills/obsidian-cli
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 jackal092927/obsidian-official-cli-skills --skill obsidian-cli
Clone the repo
git clone --depth 1 https://github.com/jackal092927/obsidian-official-cli-skills

Made for: Claude Code.

Or install obsidian-cli, the plugin that ships this one along with the rest of its 1 skill.

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-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli/github.svg)](https://agentmods.dev/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli)
Your own site
<a href="https://agentmods.dev/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli"><img src="https://agentmods.dev/badge/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli/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-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli"><img src="https://agentmods.dev/badge/skills/jackal092927/obsidian-official-cli-skills/obsidian-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,705 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 $0.00057 $0.01705
Opus 5 $0.00028 $0.00852
Sonnet 5 $0.00011 $0.00341
Haiku 4.5 $0.00006 $0.00170

Measured 9d ago against content hash 5d781d3d6444, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

obsidian-cli 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.

plugins/obsidian-cli/skills/obsidian-cli/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian CLI — Agent Reference

When to Use CLI vs File Tools

Use CLI when you need Obsidian's index or app features: search, backlinks, links, tags, tasks, properties, bases, templates, outline, orphans, unresolved links

Use file tools (Read/Write/Edit/Grep/Glob) for: simple file read/write, bulk text replacement, grep across files — no app dependency

Rule of thumb: if Obsidian's index adds value, use CLI. If it's plain text manipulation, use file tools.

Syntax Basics

obsidian <command> [param=value ...] [flag ...]
  • Vault targeting: vault="My Vault" as first param, or run from inside vault dir
  • File targeting: path=exact/path.md (vault-relative) vs file=name (link-style resolution)
  • Params: key=value — quote values with spaces: name="My Note"
  • Flags: boolean switches, no = — e.g. silent, overwrite, counts, total
  • Multiline: \n for newline, \t for tab in content strings
  • Structured output: format=json (search, base:query), format=tsv (properties, tags)
  • Clipboard: append --copy to copy output

Key Commands

Read & Write

obsidian read path=<path>                                    # read file content
obsidian append path=<path> content="<text>"                 # append to file
obsidian prepend path=<path> content="<text>"                # prepend after frontmatter
obsidian create name=<name> content="<text>" silent          # create file (safe — won't overwrite)
obsidian create name=<name> template=<template> overwrite silent  # create from template
obsidian move path=<from> to=<to>                            # move/rename file
obsidian delete path=<path>                                  # move to system trash (safe)

Gotchas:

  • create without silent opens the file in Obsidian's UI — always add silent during agent operations.
  • create doesn't auto-create directories — use mkdir -p via Bash first if the parent folder doesn't exist.
  • create with template= may place the file in the template's configured folder, ignoring path=. Verify the actual path with search or files after creation.

Read the full file on GitHub · 163 lines

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. 9d ago First seen · 163 lines · 57 tokens per session scan A 5d781d3d6444

Subscribe to this mod's changes

obsidian-cli is a skill published in the GitHub repository jackal092927/obsidian-official-cli-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 1,705 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 2026-08-30.