obsidian-wiki is a framework that helps AI agents build and maintain an interconnected knowledge base from text-based material in an Obsidian vault. It is for people who want their agents to remember discoveries, connect related information, and answer questions with wiki-link citations. Catalogue add-ons provide the agent skills, instructions, agents, and configuration used to create and maintain these wikis.
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 Ar9av/obsidian-wiki --skill obsidian-layout-adjustmentgit clone --depth 1 https://github.com/Ar9av/obsidian-wikiWrote 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/ar9av/obsidian-wiki/obsidian-layout-adjustment)<a href="https://agentmods.dev/skills/ar9av/obsidian-wiki/obsidian-layout-adjustment"><img src="https://agentmods.dev/badge/skills/ar9av/obsidian-wiki/obsidian-layout-adjustment/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/ar9av/obsidian-wiki/obsidian-layout-adjustment"><img src="https://agentmods.dev/badge/skills/ar9av/obsidian-wiki/obsidian-layout-adjustment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.02168 |
| Opus 5.5 | $0.00021 | $0.00867 |
| Sonnet 5.5 | $0.00010 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
obsidian-layout-adjustment 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 19d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Layout Adjustment
This skill is for changing how Obsidian looks with CSS files while working with the user's visual language.
Obsidian is always the same kind of environment: app frame, tab headers, side docks, view headers, pane shells, note surface, properties, file explorer, backlinks, graph, rendered markdown, and status bar. The vault, theme, snippets, plugins, and desired taste direction change, but the canvas stays Obsidian.
The core behavior is translation:
the user names a visible Obsidian object. Translate that phrase into the stable Obsidian layer/backend object, edit the active snippets safely, screenshot the result, and keep iterating without losing good states.
This is not a general CSS workflow and not a fixed-theme generator.
Normal Output Mode
This skill should make live styling work faster, not turn every small request into a report.
In normal use:
- Say the mapping only when it prevents ambiguity.
- Keep the mapping short: one sentence is usually enough.
- Then act: inspect active snippets, checkpoint, patch, format, reload, screenshot.
- Report the result concisely with changed files, checkpoint, and screenshot status.
Good normal update:
"I’m treating 'tabs above the note' as workspace tab headers, not the arrows/book/dots view header. I’ll checkpoint active snippets, patch that selector family only, and screenshot the tab strip."
Do not write a long workflow report unless:
- the user asks for a plan, audit, review, or explanation.
- You are running evals or building this skill.
- You are refactoring without visual changes.
- The request is ambiguous enough that acting first would be risky.
The value is in preventing bad CSS loops while still moving quickly.
Use The Reference
Read references/workflow-reference.md when:
- the user names a visible Obsidian object in natural language.
- The requested target could be more than one Obsidian layer.
- A screenshot shows "nothing changed," "still wrapped," "not lifted," uneven edges, washed-out surfaces, or unreadable icons.
- You are refactoring active snippets without changing the accepted look.
- You need the Obsidian surface map, change-type map, or failure-pattern list.
What ships with it
2 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.
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.
- 19d ago Changed · -6 lines · -63 tokens per session 07da9bfa8d2a
- 1mo ago First seen · 227 lines · 115 tokens per session scan A 2c9232dd39b0
obsidian-layout-adjustment is a skill published in the GitHub repository Ar9av/obsidian-wiki (3,619 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 2,168 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.