obsidian-cli

A command-line skill for working with Obsidian, an app that stores linked notes in a personal knowledge vault. It uses a running Obsidian instance to search, read, create, edit, and analyze notes and their metadata.

In plain words
What is it for?
Use it to search notes, manage daily notes and tasks, inspect backlinks and orphan notes, edit metadata, work with templates, and analyze vault structure.
Why use it?
It provides terminal access to vault content and structure, including links, tags, tasks, and properties, without requiring manual navigation through the app.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/trtmn/agent-plugins/obsidian-cli
Any agent
npx skills add trtmn/agent-plugins --skill obsidian-cli
Clone the repo
git clone --depth 1 https://github.com/trtmn/agent-plugins

Made for: Claude Code, Codex.

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00125 $0.02964
Opus 5 $0.00063 $0.01482
Sonnet 5 $0.00025 $0.00593
Haiku 4.5 $0.00013 $0.00296

Measured yesterday against content hash 09989a18b355, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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 · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian CLI Skill

The user has the obsidian CLI installed, which communicates with a running Obsidian instance over a local REST API. Use it to search, read, create, modify, and analyze notes without touching files directly on disk.

When to Use CLI vs Direct File Access

Use CLI Use Direct Read/Edit Use Both
Search (search, search:context) Large content edits requiring precise line-level changes Find notes with CLI, then Read/Edit their files
Graph analysis (backlinks, orphans, deadends, unresolved) Multi-line insertions at specific positions Get vault path with vault info=path, then Glob/Grep
Properties/tags (read, set, list, count) Complex regex replacements List tasks with CLI, edit file to restructure
Tasks (list, toggle, filter) Reading very large files with offset/limit
Daily notes (read, append, prepend)
Templates (list, read, insert)
Vault-wide counts and statistics
Opening files in Obsidian UI

Key principle: Use CLI for discovery and metadata; use direct file access for surgical edits. Combine them for find-then-edit workflows.

CLI Syntax Conventions

obsidian <command> [key=value ...] [bare-flags]
  • file= resolves by name like wikilinks (no extension needed): file=Meeting Notes
  • path= is an exact vault-relative path: path=Journal/2024-01-15.md
  • Quote values with spaces: file="Project Planning", content="Hello World"
  • Newlines in content: Use \n — e.g., content="Line 1\nLine 2"
  • Bare boolean flags have no value: total, verbose, counts, done, todo
  • vault= targets a specific vault: vault="Work Vault"
  • format=json for structured/parseable output (prefer this for programmatic use)
  • Most commands default to the active file when file=/path= is omitted

Safe vs Destructive Operations

Safe (no confirmation needed)

  • All read commands: read, search, search:context, file, files, folders, outline, wordcount, recents
  • All list commands: tags, properties, tasks, backlinks, links, orphans, deadends, unresolved, aliases, bookmarks, templates, bases, plugins, themes, snippets, hotkeys, commands, tabs, workspace
  • Single-value reads: tag, property:read, daily:read, daily:path, template:read, random:read, vault, vaults, version, history, history:list, history:read, diff, publish:list, publish:site, publish:status, base:query, base:views
  • UI navigation: open, daily, search:open, tab:open, web

Read the full file on GitHub · 398 lines

Files

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.

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. yesterday First seen · 398 lines · 125 tokens per session scan A 09989a18b355

Subscribe to this mod's changes

obsidian-cli is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 4d ago), licensed Unlicense. It adds 125 tokens to every session and 2,964 once invoked, about $0.0006 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens