obsidian-brain

A skill that lets an agent use your personal Obsidian vault—your collection of Markdown notes—as context for conversation. It can find relevant notes when you explicitly ask what your notes say.

In plain words
What is it for?
Use it to answer questions based on something you previously wrote, such as “check my notes about this” or “what do my notes say about this?”
Why use it?
It avoids manually searching through your notes and copying useful passages into the chat. It also keeps note lookup separate from changing or organising the vault.

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/hamsurang/kit/obsidian-brain
Any agent
npx skills add hamsurang/kit --skill obsidian-brain
Clone the repo
git clone --depth 1 https://github.com/hamsurang/kit

Made for: Claude Code, Codex.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 945 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 $0.00103 $0.00945
Opus 5 $0.00051 $0.00473
Sonnet 5 $0.00021 $0.00189
Haiku 4.5 $0.00010 $0.00094

Measured 2d ago against content hash cc1e8255d38b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

obsidian-brain 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 2d 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-brain/skills/obsidian-brain/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian Brain — Vault Knowledge as Context

Use vault notes as conversational context and archive session learnings as Zettelkasten notes.

Skill Boundary

Intent Skill
Create, edit, move, search notes obsidian
Use vault knowledge as context obsidian-brain
Archive session learnings /obsidian-archive command
Explicitly load vault context /brain command

Vault Path Resolution

Resolve once per session, cache for reuse:

  1. User override: ~/.claude/obsidian-brain/config.jsonvaultPath
  2. obsidian-cli: obsidian-cli print-default --path-only
  3. Obsidian app config: ~/Library/Application Support/obsidian/obsidian.json
  4. Ask user: "Obsidian vault 경로를 알려주세요"

If vault path is invalid, clear config and re-resolve. See references/vault-setup.md for details.

Context Loading Workflow

When the user asks to reference their notes:

  1. Parse query — extract topic keywords from the user's request
  2. MOC scan — Grep 2-maps/*.md for keywords, read top 3 matching MOCs
  3. Note retrieval — extract [[wikilinks]] from MOCs, read up to 5 linked notes
  4. Fallback search — if MOC scan finds nothing, Grep 1-zettelkasten/ and 0-inbox/ directly for keywords (catches orphan notes not linked to any MOC)
  5. Context budget — stay within 15,000 characters total:
    • 3 MOCs × ~1,000 chars = ~3,000
    • 5 notes × ~2,000 chars = ~10,000
    • Remaining ~2,000 for relationship context
  6. Present — summarize what was found, answer the user's question using note content

If No Notes Found

이 주제에 대한 노트를 찾지 못했습니다.
관련 키워드: [searched terms]

Cold Start (Empty Vault)

If 2-maps/ is empty or missing, inform the user:

vault에 아직 노트가 없습니다. /obsidian-archive 로 학습 내용을 저장해보세요.

Archive Workflow

The /obsidian-archive command handles learning extraction. It follows:

  1. Session analysis — Progressive Summarization으로 학습 추출
  2. MOC scan — 기존 노트와 관련성 검색
  3. Duplicate detection — 중복 노트 확인
  4. Draft generation — 사용자 승인/수정 루프
  5. Save0-inbox/에 저장, MOC 업데이트

Read the full file on GitHub · 95 lines

Files

What ships with it

3 files 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. 2d ago First seen · 95 lines · 103 tokens per session scan A cc1e8255d38b

Subscribe to this mod's changes

obsidian-brain is a skill published in the GitHub repository hamsurang/kit (19 stars, last pushed 4mo ago), licensed MIT. It adds 103 tokens to every session and 945 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 2026-08-30.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens