obsidian-archive

obsidian-archive is a skill for Claude Code from bgorkem/bgorkem-skills. It costs 106 tokens per session (2,610 once invoked), scanned A, original, MIT.

A note-taking tool that turns the current chat into a short reference note and saves it in an Obsidian vault. Obsidian is an app for organising linked plain-text notes.

In plain words
What is it for?
Archiving decisions, findings, instructions, or other useful parts of a coding session in a chosen Obsidian folder. It requires an Obsidian connection through MCP.
Why use it?
It preserves the useful conclusions from a conversation without keeping a full transcript. The saved note can be found and linked to later.

Skill for Claude Code

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

Part of the obsidian-archive plugin — 1 skill shipped together

Good fit Archiving decisions, findings, instructions, or other useful parts of a coding session in a chosen Obsidian folder. It requires an Obsidian connection through MCP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bgorkem/bgorkem-skills/obsidian-archive
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 bgorkem/bgorkem-skills --skill obsidian-archive
Clone the repo
git clone --depth 1 https://github.com/bgorkem/bgorkem-skills

Made for: Claude Code.

Or install obsidian-archive, the plugin that ships this one along with the rest of its 1 skill.

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-archive

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/bgorkem/bgorkem-skills/obsidian-archive"><img src="https://agentmods.dev/badge/skills/bgorkem/bgorkem-skills/obsidian-archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,610 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 $0.00106 $0.02610
Opus 5 $0.00053 $0.01305
Sonnet 5 $0.00021 $0.00522
Haiku 4.5 $0.00011 $0.00261

Measured 11d ago against content hash ad477351a8d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

obsidian-archive 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 11d 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.

plugins/obsidian-archive/skills/obsidian-archive/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian Archive

Distil the current conversation into a concise reference note and save it to the user's Obsidian vault under the configured archive folder, one file per conversation.

The goal is a future-user-friendly note: something they can grep or backlink to months later and immediately recall what was figured out. Not a transcript. Not a stenographer's record. A distillation.

Configuration

Before using this skill, set the archive folder below to a path that exists (or should exist) in your vault. It's a vault-relative path — no leading slash, trailing slash optional. The skill will save every note under this folder.

archive_folder: AI/Conversations/

If the value above is left at a placeholder, looks empty, or obviously doesn't match the user's vault, ask once which folder to use and proceed with that for this call — don't guess, and don't silently fall back to the example value. If the user specifies a different folder inline (e.g. "save it under Notes/Chats/ instead"), respect that override for the call but don't treat it as a permanent change to the configured default — that's an edit to this file.

Throughout the rest of this skill, <archive_folder> refers to the configured value above.

When to use

Trigger on any of:

  • "Archive this conversation", "save this chat", "add this to Obsidian", "log this"
  • "Save what we learned", "capture this", "write this up", "file this away"
  • "Remember this for later", "turn this into a note"

If the user's intent is ambiguous (e.g. "save this" could mean saving a file they uploaded), ask one quick clarifying question before proceeding.

Requirements

  • The mcp-obsidian MCP server, connected to the user's Obsidian vault.
  • The Local REST API Obsidian community plugin, installed and enabled in that vault.
  • Obsidian running while the skill is used (the REST API needs the app to be open).

Dependencies

This skill orchestrates tools from the mcp-obsidian MCP server. If these aren't loaded into context, call tool_search(query="obsidian") first to load them.

Read the full file on GitHub · 197 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. 11d ago First seen · 197 lines · 106 tokens per session scan A ad477351a8d9

Subscribe to this mod's changes

obsidian-archive is a skill published in the GitHub repository bgorkem/bgorkem-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 2,610 once invoked, about $0.0005 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