obsidian-llm-wiki: Command for Claude Code

.claude/commands/review-note.md

review-note is a command for Claude Code from mickeytony0215-png/obsidian-llm-wiki. It costs 34 tokens per session (2,139 once invoked), scanned A, original, MIT.

A detailed audit of a paper note against the paper's PDF, checking claims, numbers, reasoning, and conclusions. It also updates the note's review status and records the audit history.

In plain words
What is it for?
Use it after reading a paper, when a wiki-ingestion check blocks a note, or when an existing note needs rechecking. It helps verify measurements, percentages, methods, results, conclusions, arithmetic, and logical consistency.
Why use it?
It helps prevent inaccurate notes from being cited in a research wiki. The audit checks more than a quick summary, including numerical details and contradictions between the text and tables.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is mickeytony0215-png/obsidian-llm-wiki's own configuration. It tells Claude Code how to work on obsidian-llm-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obsidian-llm-wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mickeytony0215-png/obsidian-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mickeytony0215-png/obsidian-llm-wiki/main/.claude/commands/review-note.md
Clone the repo
git clone --depth 1 https://github.com/mickeytony0215-png/obsidian-llm-wiki

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 review-note

README.md
[![agentmods](https://agentmods.dev/badge/commands/mickeytony0215-png/obsidian-llm-wiki/review-note/github.svg)](https://agentmods.dev/commands/mickeytony0215-png/obsidian-llm-wiki/review-note)
Your own site
<a href="https://agentmods.dev/commands/mickeytony0215-png/obsidian-llm-wiki/review-note"><img src="https://agentmods.dev/badge/commands/mickeytony0215-png/obsidian-llm-wiki/review-note/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 review-note

Your own site · 80×15
<a href="https://agentmods.dev/commands/mickeytony0215-png/obsidian-llm-wiki/review-note"><img src="https://agentmods.dev/badge/commands/mickeytony0215-png/obsidian-llm-wiki/review-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,139 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 $0.00034 $0.02139
Opus 5 $0.00017 $0.01069
Sonnet 5 $0.00007 $0.00428
Haiku 4.5 $0.00003 $0.00214

Measured 12d ago against content hash d2dbe3cbae1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-note 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 12d 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.

.claude/commands/review-note.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-note — paper-note audit

Audit whether a paper note is consistent with its PDF, so the note can be safely cited by the wiki.

When to use

  • Right after /read-paper, to upgrade the note from review_status: unreviewed
  • When /ingest-to-wiki's gate blocks you
  • For re-auditing an existing note after a concern arises

Review depth: full

Not a skim. Every claim is checked against the PDF, with particular attention to:

  • Every quantitative datum (table cells, percentages, ms / Mbps / iteration counts)
  • Core-claim consistency (motivation, problem, method, results, conclusion)
  • Logical consistency (motivation → methodology → experiment → results → conclusion)
  • Data credibility (perfect arithmetic progressions, in-text/table contradictions, "every metric is optimal" anti-patterns)

Procedure

Fast path: if the note already has a ## Pre-review report section (produced by the optional /pre-review batch command), skip straight to Step 6 and build the Review Checklist from that report — but first spot-check 2–3 of its "verified consistent" items against the evidence (failed spot-check → rerun the pre-review). Also rerun the pre-review if it is more than 30 days old or the note was edited since. After the user confirms, rewrite the ## Pre-review report section as ## Review log per Step 7's format.

Step 1: Load sources

  1. Read the target paper note (usually a root-level .md)
  2. Load the PDF's evidence. Prefer a chunk-level retrieval backend if one is available (see /read-paper Step 0 / /paper-ask — not bundled with this repo, spec-only): its evidence is page-anchored and its tables are pre-structured, which is more reliable than a raw re-read. Without one, read the PDF directly (follow the PDF source link in frontmatter or the top-of-note link) and note in the review record that it was "not corroborated by chunk-level retrieval."
  3. If the PDF path is missing, ask the user to confirm the actual location

Step 2: Decompose claims

Read the full file on GitHub · 194 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. 12d ago First seen · 194 lines · 34 tokens per session scan A d2dbe3cbae1a

Subscribe to this mod's changes

review-note is a command published in the GitHub repository mickeytony0215-png/obsidian-llm-wiki (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 2,139 once invoked, about $0.0002 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.