brain

A command that loads relevant personal notes from an Obsidian vault, a folder of linked Markdown notes, into the current conversation.

In plain words
What is it for?
Finding topic-related notes through maps of content and direct searches, then summarizing the most relevant results.
Why use it?
It lets the coding agent use your existing notes about a topic instead of starting without that personal context.

Command

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 commands/hamsurang/kit/brain
Clone the repo
git clone --depth 1 https://github.com/hamsurang/kit
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 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 $0.00031 $0.00375
Opus 5 $0.00015 $0.00187
Sonnet 5 $0.00006 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 7042ce846791, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/commands/brain.md · 53 lines

What it actually says

/brain — Load Vault Knowledge

Load notes from Obsidian vault as conversational context.

Usage

/brain rust ownership
/brain react hooks
/brain 이전에 정리한 캐싱 전략

Prerequisites

  1. Load references/vault-setup.md and resolve vault path
  2. Verify vault structure exists

Execution

  1. Parse topic — extract keywords from the argument (or ask if empty)
  2. MOC scan — Grep 2-maps/*.md for topic keywords
  3. Read top 3 MOCs — extract [[wikilinks]] from matching MOCs
  4. Read up to 5 linked notes — prioritize most relevant by keyword match
  5. Fallback search — if no MOCs matched, Grep 1-zettelkasten/ and 0-inbox/ directly for keywords to find orphan notes not yet linked to any MOC
  6. Context budget — stay within 15,000 characters total
  7. Present findings — summarize loaded notes and answer in context

Output Format

vault에서 [N]개 노트를 찾았습니다:
  - [[note-1-title]] (from MOC: topic-name)
  - [[note-2-title]] (from MOC: topic-name)

[Answer the user's question using the loaded note content]

No Results

"[topic]"에 대한 노트를 찾지 못했습니다.
검색한 키워드: [terms]
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 · 53 lines · 31 tokens per session scan A 7042ce846791

Subscribe to this mod's changes

brain is a command published in the GitHub repository hamsurang/kit (19 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 375 once invoked, about $0.0002 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.