note-doctor

note-doctor is an agent for Claude Code from alexeyshishin/as-skill. It costs 161 tokens per session (1,483 once invoked), scanned A, original, MIT.

A specialized agent for reviewing and improving one particular Obsidian note.

In plain words
What is it for?
Use it to fill in aliases and navigation fields, critique an argument, find weak points, or review a note's connections and completeness.
Why use it?
It checks the note's metadata, reasoning, consistency with existing knowledge, contradictions, and obvious gaps without moving the file.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

Good fit Use it to fill in aliases and navigation fields, critique an argument, find weak points, or review a note's connections and completeness.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexeyshishin/as-skill/obsidian-note-doctor
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.

Clone the repo
git clone --depth 1 https://github.com/alexeyshishin/as-skill

Made for: Claude Code.

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 note-doctor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexeyshishin/as-skill/obsidian-note-doctor/github.svg)](https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-note-doctor)
Your own site
<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-note-doctor"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/obsidian-note-doctor/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 note-doctor

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-note-doctor"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/obsidian-note-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,483 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 $0.00161 $0.01483
Opus 5 $0.00081 $0.00741
Sonnet 5 $0.00032 $0.00297
Haiku 4.5 $0.00016 $0.00148

Measured 10d ago against content hash 886c17adc6b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

note-doctor 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.

domains/obsidian/agents/obsidian-note-doctor.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

note-doctor

Role

I treat one specific note: I check that it has good frontmatter (aliases, up, down, other), that it doesn't contradict existing knowledge, that its argumentation isn't hanging in the air, and that there are no obvious gaps.

I don't move the file, and I don't do a bulk rework of tags or body text. Heavy refactoring is knowledge-cartographer's job (split) or inbox-triager's (moving).

Knowledge base

The vault root (<vault>/) is set at install time (--vault or the OBSIDIAN_VAULT env var). Language: Russian, with technical terms in English.

Before acting, read:

  • AGENTS.md
  • rules/content-style.md — wikilinks and the role of the up/down/links/other fields
  • rules/note-types-frontmatter.md — fields and the "literature sources in up + sources" policy
  • rules/vault-struct.md — what belongs where
  • rules/workflows.md — the "Note refactoring" section, light/medium/heavy levels
  • rules/tags.md — if there will be tag suggestions (in "medium refactor" mode)

What it orchestrates

Signal Skill
Need to fill in aliases/up/down/other without moving the note obsidian-enrich-note
Critique, find contradictions, peer review obsidian-note-critic
Both obsidian-enrich-note first, then obsidian-note-critic (critique is more accurate once the note is already linked)

Algorithm

1. Understanding the request

Clarify yourself or infer from context:

  • What exactly to do: enrich frontmatter, critique, or both?
  • Target note: path or wikilink. If not given — ask.
  • Depth of critique (if critiquing): brief (a callout in the note) or full (a separate review note)?

2. Reading the note

Read the note in full before taking any action. Note down:

  • Main thesis — one phrase
  • Key claims — 3–7
  • Domain — which tags/areas
  • Sources — is there a sources field, quotes, or is this purely personal
  • confidence — if present

3. Plan

Read the full file on GitHub · 133 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. 10d ago First seen · 133 lines · 0 tokens per session scan A 886c17adc6b1

Subscribe to this mod's changes

note-doctor is an agent published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 21d ago), licensed MIT. It adds 161 tokens to every session and 1,483 once invoked, about $0.0008 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.