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.
npx skills add isorensen/lox-brain --skill zettelkastengit clone --depth 1 https://github.com/isorensen/lox-brainWrote 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.
[](https://agentmods.dev/skills/isorensen/lox-brain/zettelkasten)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.04032 |
| Opus 5.5 | $0.00012 | $0.01613 |
| Sonnet 5.5 | $0.00006 | $0.00806 |
| Haiku 4.5 | $0.00003 | $0.00403 |
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 1mo 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.
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 (zettelkastenorpara)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:
- 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.
- 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
- Generate notes — One .md file per concept, output to
docs/zettelkasten/. - Create tag files — .md files with content in
docs/zettelkasten/tags/for every new tag introduced. - Generate MOC — Create
docs/zettelkasten/_MOC.mdlinking all generated notes. - Report — List all created files and suggest next steps.
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.
- 1mo ago First seen · 381 lines · 30 tokens per session scan A e580d78dfc7c
zettelkasten is a skill published in the GitHub repository isorensen/lox-brain (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 4,032 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, list, or version-gated kanban views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
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…
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.
wiki-status
Report wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questions, hubs and bridges, or whether maintenance skills still have pending changes. wiki-digest summarizes learned knowledge instead.
wiki-import
Import a wiki graph into the current vault from graph.json or an OKF/markdown bundle. Use for transferring previously exported wiki content between vaults; pair with wiki-export for the reverse direction.