process

process is a skill for Claude Code from tuan3w/obsidian-vault-agent. It costs 134 tokens per session (2,914 once invoked), scanned A, original, MIT.

A guided workflow for turning a source note—such as a research paper, book, lecture, or saved article—into useful knowledge in a personal note collection.

In plain words
What is it for?
Use it to process one source note, identify its main ideas, create concept or note entries, and connect them to related notes.
Why use it?
It helps you understand and remember what you read instead of leaving important ideas buried in long notes. It also makes you answer questions about the material before extracting concepts and links.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the obsidian-vault-agent plugin — 13 skills, 20 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add skills/tuan3w/obsidian-vault-agent/process
Any agent
npx skills add tuan3w/obsidian-vault-agent --skill process
Clone the repo
git clone --depth 1 https://github.com/tuan3w/obsidian-vault-agent

Made for: Claude Code.

Or install obsidian-vault-agent, the plugin that ships this one along with the rest of its 13 skills, 20 agents, 3 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 process

README.md
[![agentmods](https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/process.svg)](https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/process)
Your own site
<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/process"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/process.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00134 $0.02914
Opus 5 $0.00067 $0.01457
Sonnet 5 $0.00027 $0.00583
Haiku 4.5 $0.00013 $0.00291

Measured 6d ago against content hash 588bdb293c27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

process 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 6d 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.

skills/process/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill is INTERACTIVE by design. The desirable-difficulty questions in Stage 3 are not optional ceremony — the friction IS the learning. The user's answers shape what gets extracted and how.

<Use_When>

  • User has a source note (paper, post, book, lecture, course, clipping) to process
  • User wants to extract concepts into Term or Note entries
  • User asks what's important in something they've read
  • User wants to build wikilink connections from a note into the rest of the vault
  • User says "process this", "atomize this", "extract concepts", "what did I learn" </Use_When>

<Do_Not_Use_When>

  • User wants to find new papers on a topic (use /paper-discover)
  • User wants web research on something new (use /research)
  • User wants to synthesize ACROSS multiple existing vault notes (use /synthesize)
  • The note is already a Term, Note, or Thought (not a source note) </Do_Not_Use_When>

Stage 1: READ THE SOURCE NOTE

Ask the user which note to process if it's not clear from context. Then read it.

Verify the note type is a source type: paper, post, book, lecture, course, or a Clipping. If the note is a Term, Note, or Thought, stop and explain why this workflow doesn't apply.

Read the frontmatter and body:

mcp__obsidian-vault__read_note(path="path/to/note.md")

Or if MCP is unavailable:

Read("/absolute/path/to/note.md")

Stage 2: MARK AS PROCESSING

Update frontmatter to signal active work:

mcp__obsidian-vault__update_frontmatter(
  path="path/to/note.md",
  updates={"processing_status": "processing", "updated_date": "YYYY-MM-DD"}
)

Stage 3: ASK DESIRABLE-DIFFICULTY QUESTIONS

Read the full file on GitHub · 321 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. 6d ago First seen · 321 lines · 134 tokens per session scan A 588bdb293c27

Subscribe to this mod's changes

process is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (37 stars, last pushed 5mo ago), licensed MIT. It adds 134 tokens to every session and 2,914 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.