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 alexeyshishin/as-skill --skill obsidian-refactor-lecturegit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/obsidian-refactor-lecture)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-refactor-lecture"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-refactor-lecture/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/alexeyshishin/as-skill/obsidian-refactor-lecture"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-refactor-lecture.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 | $0.00135 | $0.02087 |
| Opus 5 | $0.00068 | $0.01043 |
| Sonnet 5 | $0.00027 | $0.00417 |
| Haiku 4.5 | $0.00014 | $0.00209 |
Grade A, and why
obsidian-refactor-lecture 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The skill turns a large set of lecture notes into a structured knowledge graph:
- the original lecture becomes a "table of contents" — sections are replaced with a short summary +
[[wikilink]]; - extracted concepts are created as separate notes named
<Discipline> – <Concept>.md; - if a discipline MOC exists, it's updated with links to the new notes (no such MOC is guaranteed to exist right now — see "Lecture notes format" below).
Limit: no more than 3 sets of notes per run. If the user names more, ask which three to process now — the rest go in a follow-up run.
Base rules
Vault structure, tag taxonomy, frontmatter, file names — in .claude/rules/:
vault-struct.md, tags.md (the "Structural tags" section), note-types-frontmatter.md, file-naming.md.
Lecture notes format
A lecture file follows the pattern <NN>. <Discipline> лекция <YYYY-MM-DD>.md, filed under 02. Сферы/03. Образование/02. Конспекты/, and contains:
---
tags:
- university # real lecture notes use this, not #lecture — check what's already on sibling notes before picking
up: "[[02. Сферы]]" # observed real notes point straight at 02. Сферы, not at a per-discipline MOC
aliases: []
down: []
links: []
other: []
---
There's no confirmed per-discipline MOC or discipline: field in the current vault — only one real lecture note was available to check, and it links up straight to 02. Сферы. If a ## Discipline MOC turns out to exist (check 02. Сферы/07. Карты/ and 02. Сферы/03. Образование/), link to it instead and update this file; otherwise ask the user before inventing one.
Processing algorithm
Step 1. Read and identify candidates
Criteria for "extract / keep" — knowledge-structures.md (the "When to split a section into its own note" section). One thing specific to lectures: leave Q&A blocks in the lecture as-is; extract only if the answer is a full-blown concept ≥10 lines long.
Step 2. Draft a plan and show it to the user
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.
- 10d ago First seen · 196 lines · 135 tokens per session scan A 01bf93f3df96
obsidian-refactor-lecture is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 22d ago), licensed MIT. It adds 135 tokens to every session and 2,087 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 2026-08-31.
Other skills, from other repositories
cognitive-compile
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.
guide
Interactive 8-module learning path for the shipped skills, role-adaptive.
pdf-courseware-to-obsidian
A workflow that turns local PDF or PowerPoint course materials into structured Chinese study notes in an Obsidian vault. Obsidian is a note-taking app that stores linked Markdown files and related images.
lc-logger
Log a LeetCode problem into the user's Obsidian interview-prep tracker (daily notes + Dataview dashboard). Trigger whenever the user pastes a leetcode.com problem URL — even with no other words — or says anything like "log this", "log this lc problem", "just did/solved a problem", "add two sum to my log", "did 239…
yt-digest
Turn a YouTube URL into a vault-ready research digest — transcript, key learning moments with timestamp deep-links, and screenshots of visual moments (slides, demos, dashboards). Use when the user pastes a YouTube link they're researching, says "summarize this video", "/yt-digest ", "youtube digest", or asks to…
context7-mcp
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.