obsidian-world — Claude Code command: what it does, how to install
obsidian-world is a Claude Code command that loads context from an Obsidian vault in stages. It runs on requests to catch up or check current priorities.
MIT ★ 5,412 updated 2026-10-24
/plugin marketplace add eugeniughelbur/obsidian-second-brain
/plugin install obsidian-second-brain@obsidian-second-brainWhat obsidian-world does
obsidian-world gathers identity details and current work from files in an Obsidian vault. It starts with identity and values, then reads the index, logs, and notes about current work. After levels L0–L2, it gives a short status covering priorities, unfinished threads, and overdue tasks.
Level L3 is reserved for a specific question or task. During complex work, the command can save key context to PINNED.md and clear that file when the task is done. If identity files or index.md are missing, it offers to create them or run /obsidian-init.
Before creating or updating a note, the command must read and follow references/ai-first-rules.md. If it cannot find that file, it must say so before writing. The command also uses the obsidian-second-brain skill.
What it helps with
- load priorities and current work from an Obsidian vault
- find unfinished tasks in logs and daily notes
- get a short status before starting work
- save key details from a complex task in
PINNED.md
Example prompts for the agent
- Load context from my Obsidian vault.
- Summarize what is happening now and find unfinished tasks.
- Save the key details of this task to
PINNED.md.
How to install obsidian-world
1Plugin marketplace
/plugin marketplace add eugeniughelbur/obsidian-second-brain/plugin install obsidian-second-brain@obsidian-second-brain2Manually: put the files in place
.claude/commands/obsidian-world.mdCall it with /obsidian-world. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/obsidian-world.mdCall it with /prompts:obsidian-world. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/obsidian-world.prompt.mdManually: put the files in place
.gemini/commands/obsidian-world.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about obsidian-world
How do I install obsidian-world in Claude Code?
Add the marketplace with /plugin marketplace add eugeniughelbur/obsidian-second-brain, then install the plugin with /plugin install obsidian-second-brain@obsidian-second-brain. The Claude Code command file is .claude/commands/obsidian-world.md.
What does obsidian-world do?
It loads vault context in stages, then summarizes current priorities, unfinished work, and overdue tasks. For a specific task, it can load deeper context and save details to PINNED.md.
What happens if the vault has no index.md?
The command offers to run /obsidian-init to generate one. If identity files are missing, it offers to create them after asking about the user's role, values, and communication preferences.
Source text
obsidian-world.md · MIT
--- description: Load your identity, values, priorities, and current state in one shot - with progressive context levels to avoid burning tokens category: vault triggers_en: ["load context", "what is going on", "where am I", "load my world"] triggers_de: ["Kontext laden", "was ist gerade los", "wo stehe ich", "meine Welt laden"] triggers_es: ["carga el contexto", "qué está pasando", "dónde estoy", "ponme al tanto de todo", "dame el resumen de mi vida"] triggers_pt: ["carregue contexto", "o que está acontecendo", "onde estou", "carregue meu mundo"] triggers_zh: ["加载我的完整背景", "告诉我现在的整体状况", "读取我的身份和当前重点", "先了解一下我的情况"] --- Use the obsidian-second-brain skill. Execute `/obsidian-world`: 1. Read `_CLAUDE.md` first if it exists in the vault root 2. Load context progressively - start light, go deeper only as needed: **L0 - Identity (~170 tokens)** Read these files if they exist (search for them if paths differ): - `SOUL.md` or `About Me.md` - who the user is, communication style, thinking preferences - `CRITICAL_FACTS.md` - ~120 tokens of always-needed context: timezone, manager, location, company, role - `CORE_VALUES.md` or `Values.md` - decision-making principles and non-negotiables **L1 - Navigation (~1-2K tokens)** - Read `index.md` - the catalog of all vault pages. This tells Claude what exists without loading everything. - Read recent operation log (last 10 entries): if `Logs/` exists, read today's and yesterday's `Logs/YYYY-MM-DD.md`; otherwise read `log.md` **L2 - Current State (~2-5K tokens)** - Read `Home.md` or `Dashboard.md` - current top-level priorities - Read today's daily note (if it exists) for what's already in progress - Read the last 3 daily notes for recent momentum and open threads - Scan active kanban boards for in-progress and overdue items - Check for session digests from previous conversations (look for "End of Day" or "Session Digest" sections) **L3 - Deep Context (on demand, ~5-20K tokens)** - Only load if needed for a specific question or task - Read active project notes (status: active) for current goals and blockers - Read full source/reference notes (the concept or knowledge folder per `references/folder-map.md` - wiki-style `wiki/concepts/` or `raw/`, Obsidian-style `Knowledge/`) if the user asks about a specific topic - Identify key people interacted with recently (last 7 days of daily notes) 3. Present a brief status after L0-L2 (do NOT load L3 unless needed): - **Who I am to you**: confirm the persona and communication style - **Your current priorities**: top 3-5 active threads (from index.md + boards) - **Open threads from last session**: anything unfinished (from operation log + daily notes) - **Overdue / needs attention**: tasks or projects that are stale - **Today so far**: what's already logged today Keep output concise - this is a boot-up sequence, not a report. The user should glance at it and say "yes, Claude is up to speed" and start working immediately. 4. **Core memory pinning** - during the session, if the user is working on a specific task that requires persistent context (debugging a complex API, reviewing a long document, planning a project), Claude can PIN critical information to a `PINNED.md` file at the vault root: - Write task-specific facts, schemas, or reference data to `PINNED.md` - This file is loaded at L0 alongside SOUL.md and CRITICAL_FACTS.md - When the task is done, clear `PINNED.md` - This prevents critical session context from being lost during long conversations or context compaction - Claude should proactively suggest pinning when it detects the user is deep in a complex task If identity files (SOUL.md, CRITICAL_FACTS.md) don't exist, offer to create them by asking 5-7 quick questions about the user's role, values, and communication preferences. If `index.md` doesn't exist, offer to run `/obsidian-init` to generate it. --- **AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future agent` preamble, rich frontmatter (`type`, `date`, `tags`, `ai-first: true`, plus type-specific fields), recency markers per external claim, mandatory `[[wikilinks]]` for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future agent retrieval - not human reading. **Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`.
© Eugeniu Ghelbur · MIT · eugeniughelbur/obsidian-second-brain