obsidian-knowledge

obsidian-knowledge is a skill for Claude Code from Michael-OvO/obsidian-knowledge-agent. It costs 146 tokens per session (895 once invoked), scanned A, original, MIT.

A workflow for organizing information in an Obsidian vault, a folder of linked Markdown notes. It can capture a quick note or link, organize an inbox, or turn larger material into structured notes suited to the existing vault.

In plain words
What is it for?
Use it to process links, PDFs, Word files, slides, syllabi, papers, transcripts, and URL lists into notes, indexes, and other organized Obsidian content.
Why use it?
It keeps imported information consistent with the vault's folders, naming, links, formatting, and teaching style, while matching the amount of work to the size of the material.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the obsidian-knowledge plugin — 1 skill, 12 commands, 2 hooks shipped together

Good fit Use it to process links, PDFs, Word files, slides, syllabi, papers, transcripts, and URL lists into notes, indexes, and other organized Obsidian content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge
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 Michael-OvO/obsidian-knowledge-agent --skill obsidian-knowledge
Clone the repo
git clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agent

Made for: Claude Code.

Or install obsidian-knowledge, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 2 hooks.

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 obsidian-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge/github.svg)](https://agentmods.dev/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge)
Your own site
<a href="https://agentmods.dev/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge"><img src="https://agentmods.dev/badge/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge/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 obsidian-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge"><img src="https://agentmods.dev/badge/skills/michael-ovo/obsidian-knowledge-agent/obsidian-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 895 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 $0.00146 $0.00895
Opus 5 $0.00073 $0.00447
Sonnet 5 $0.00029 $0.00179
Haiku 4.5 $0.00015 $0.00089

Measured 9d ago against content hash 682f19c13e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

obsidian-knowledge 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_links.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-knowledge/skills/obsidian-knowledge/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian Knowledge Ingest

This skill helps with any knowledge work in an Obsidian vault — from saving a single link to building a whole course's notes. It does as much or as little structuring as the material needs, fits the vault it's in, recalls what it learned about that vault before each run, and reflects afterward to get better over time — without any model training.

Match the effort to the material. Decide the altitude first (see "Choose the altitude" in the workflow): a Capture is one clean note, a Small collection is a few notes plus a light index, and only a genuinely large, structured input earns the Full build below. Default to the lightest touch; escalate only when the material clearly asks for it.

How to use it

  1. Read the rules first. Read these bundled references in order:

    • references/style-guide.md — the teaching-note voice and quality bar
    • references/self-evolution.md — the recall → reflect learning loop
    • references/obsidian-conventions.md — frontmatter, wikilinks, naming, LaTeX, Mermaid, canvas
    • references/vault-architecture.md — folder roles and branch boundaries
    • references/ingestion-workflow.md — the full workflow you will execute

    If the target vault already has these files at .agents/ in its root, prefer those — they may be customized for that vault.

  2. Recall (Phase 0, Step 0). Before classifying, read .agents/learned/ if it exists: apply conventions.md, use examples.md as few-shot classification guidance, and follow any matching playbook in learned/skills/. Silent on a fresh vault.

  3. Execute the workflow in references/ingestion-workflow.md:

    • Phase 0 — Ingest: classify the input profile and extract a structural map.
    • Phases 1–3 — Compile: scaffold the tree, write content/source/concept notes (deep ML/Quant notes use the artifacts that teach — runnable code, a LaTeX equation, a diagram — where each earns its place, not to fill a quota), build the concept-graph canvas.
    • Phases 4–5 — Distribute: wire prev/next navigation, validate all wikilinks (run the bundled scripts/validate_links.py that sits next to this skill, or the inline check in the workflow's Phase 4), run the teaching-quality pass.
    • Phase 6 — Commit: commit the collection; clear Inbox/ only with explicit user approval.

Read the full file on GitHub · 58 lines

Files

What ships with it

6 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. 9d ago First seen · 58 lines · 146 tokens per session scan A 682f19c13e74

Subscribe to this mod's changes

obsidian-knowledge is a skill published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (207 stars, last pushed 2mo ago), licensed MIT. It adds 146 tokens to every session and 895 once invoked, about $0.0007 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.