zettelkasten

zettelkasten is a skill for Claude Code, Codex from isorensen/lox-brain. It costs 30 tokens per session (4,032 once invoked), scanned A, original, MIT.

A code-knowledge note system that turns information from a codebase into small, linked Zettelkasten notes. Zettelkasten is a method of keeping atomic notes, with each note focused on one idea.

In plain words
What is it for?
Use it to extract concepts from a repository, create linked notes, and store them in an Obsidian vault through Lox.
Why use it?
It preserves knowledge that might otherwise stay in developers' heads or be lost during handoffs and context switches.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it to extract concepts from a repository, create linked notes, and store them in an Obsidian vault through Lox.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isorensen/lox-brain/zettelkasten
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 isorensen/lox-brain --skill zettelkasten
Clone the repo
git clone --depth 1 https://github.com/isorensen/lox-brain

Made for: Claude Code, Codex.

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 zettelkasten

README.md
[![agentmods](https://agentmods.dev/badge/skills/isorensen/lox-brain/zettelkasten/github.svg)](https://agentmods.dev/skills/isorensen/lox-brain/zettelkasten)
Your own site
<a href="https://agentmods.dev/skills/isorensen/lox-brain/zettelkasten"><img src="https://agentmods.dev/badge/skills/isorensen/lox-brain/zettelkasten/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 zettelkasten

Your own site · 80×15
<a href="https://agentmods.dev/skills/isorensen/lox-brain/zettelkasten"><img src="https://agentmods.dev/badge/skills/isorensen/lox-brain/zettelkasten.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,032 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 $0.00030 $0.04032
Opus 5 $0.00015 $0.02016
Sonnet 5 $0.00006 $0.00806
Haiku 4.5 $0.00003 $0.00403

Measured 10d ago against content hash e580d78dfc7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zettelkasten 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 10d 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.

skills/zettelkasten/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zettelkasten — Smart Notes from Code

Configuration

This skill reads your Lox configuration from ~/.lox/config.json:

  • vault.preset: determines folder structure (zettelkasten or para)
  • vault.local_path: path to your Obsidian vault (default: ~/Obsidian/Lox)

Folder mapping by preset:

Preset Atomic notes folder Tags folder
zettelkasten 6 - Atomic Notes/ 3 - Tags/
para 4 - Resources/Zettelkasten/ 4 - Resources/Tags/

When the skill refers to "the atomic notes folder" or "the tags folder" below, it means the folder corresponding to the user's configured preset.

Content language defaults to pt-BR. Technical terms and code identifiers stay in English. If the project's primary language is different (detected from README, CLAUDE.md, or user preference), adapt accordingly.

Purpose

Code lives in repos. Knowledge lives in people's heads — until they leave, forget, or context-switch. This skill extracts implicit knowledge from a codebase and crystallizes it into atomic, cross-linked notes following the Zettelkasten method.

Why Zettelkasten for code knowledge:

  • Atomic notes force clarity — one concept per note means no buried insights
  • Cross-linking reveals hidden relationships between components, decisions, and patterns
  • Graph View in Obsidian turns your project into a navigable knowledge map
  • Status progression (#baby -> #child -> #adult) tracks note maturity over time

Modes of Operation

Mode 1: Full Project Scan (no arguments)

Trigger: /zettelkasten with no arguments.

Workflow:

  1. Explore the codebase — Read project structure, package.json/pyproject.toml, README, key source files, config files, tests. Use the Explore sub-agent for large codebases.
  2. Identify knowledge atoms — Extract distinct concepts:
    • Overall architecture and system boundaries
    • Key design decisions and their rationale (ADRs if present)
    • Data flow / pipeline descriptions
    • Technology stack choices and why
    • Database schema and relationships
    • API contracts and integration points
    • Security model and access control
    • Deployment and infrastructure patterns
    • Testing strategy
    • Non-obvious patterns or conventions
  3. Generate notes — One .md file per concept, output to docs/zettelkasten/.
  4. Create tag files — .md files with content in docs/zettelkasten/tags/ for every new tag introduced.
  5. Generate MOC — Create docs/zettelkasten/_MOC.md linking all generated notes.
  6. Report — List all created files and suggest next steps.

Read the full file on GitHub · 381 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. 10d ago First seen · 381 lines · 30 tokens per session scan A e580d78dfc7c

Subscribe to this mod's changes

zettelkasten is a skill published in the GitHub repository isorensen/lox-brain (2 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 4,032 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 2026-08-31.

Related

Other skills, from other repositories

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

wiki-digest

Generate a periodic knowledge digest — a human-readable newsletter-style summary of what was learned, updated, and connected in your wiki over a specified period (day/week/month). Use when the user says "what did I learn this week", "give me a digest", "weekly summary", "knowledge report", "what's new in my wiki"…

Ar9av/obsidian-wiki · 121 tokens

wiki-import

Import a wiki knowledge graph into the current vault — either from a graph.json export file (stubs) or from an OKF (Open Knowledge Format) markdown bundle (full page bodies). Use this skill when the user says "import wiki", "import from export", "load graph.json", "import vault", "import OKF bundle", "import OKF"…

Ar9av/obsidian-wiki · 108 tokens

wiki-research

Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X", "find everything about Y", "do a deep dive on Z", "autonomous research on X", or wants comprehensive, web-sourced…

Ar9av/obsidian-wiki · 87 tokens

hermes-history-ingest

Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their /.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest…

Ar9av/obsidian-wiki · 108 tokens