obsidian-llm-wiki: Command for Claude Code

.claude/commands/read-paper.md

read-paper is a command for Claude Code from mickeytony0215-png/obsidian-llm-wiki. It costs 38 tokens per session (1,476 once invoked), scanned A, original, MIT.

A workflow that reads a research paper PDF and creates a structured paper note, initially marked as unreviewed. The note must pass a separate review before it can be cited by the wiki.

In plain words
What is it for?
Use it to retrieve and read a specified PDF, extract its main facts and structure, and produce a research note. It supports later review and wiki ingestion, with retrieval-backed reading when that infrastructure is available.
Why use it?
It turns a paper into a consistent note while keeping unverified information clearly separated from reviewed research. The process is designed to reduce errors caused by skimming long PDFs.

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/read-paper.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 read-paper

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/mickeytony0215-png/obsidian-llm-wiki/read-paper"><img src="https://agentmods.dev/badge/commands/mickeytony0215-png/obsidian-llm-wiki/read-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,476 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 $0.00038 $0.01476
Opus 5 $0.00019 $0.00738
Sonnet 5 $0.00008 $0.00295
Haiku 4.5 $0.00004 $0.00148

Measured 12d ago against content hash 692da264892a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

read-paper 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/read-paper.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read the PDF I specify, then do the following:

Step 0: Retrieve the full text (anti-skim / anti-hallucination)

This repo ships the command spec only. Step 0 describes an optional chunked-retrieval backend (the reference implementation was built against RAGFlow); it is intentionally not bundled — see /paper-ask and /search-vault for the same spec-only stance on retrieval infrastructure. Without it, skip straight to the fallback below.

Do not dump the entire PDF into context and read it in one pass — long-context reads are prone to skimming and hallucination. Prefer a retrieval-backed pipeline:

  1. Confirm the retrieval stack is running; start it if not, and wait for it to become reachable.
  2. Ingest the PDF (idempotent — a filename already in the index is skipped automatically).
  3. Dump every chunk in document order, with page numbers and tables as structured HTML, to a scratch file.
  4. Coverage contract: read the chunk file in batches of ~20–30 chunks, in order, noting the key facts from each batch before moving to the next. Do not write the note after only reading the Abstract/Intro/Conclusion. Before drafting, self-check: "Have all N/N chunks been processed?" — go back and finish if not.
  5. Treat chunk content as authoritative for numbers and tables (tables are already parsed into structured HTML, more reliable than eyeballing the PDF). In the note's "Main results" section, anchor every key number to its page, e.g. latency 4.6ms (p.9).
  6. Chunks don't carry figure images — when a figure needs to be seen, read the specific PDF page directly.
  7. Fallback: if the retrieval backend isn't running and the user doesn't want to start it, fall back to pdftotext / reading the PDF directly. In that case leave the note's retrieval-id frontmatter field null and mention in the completion message that the paper can be ingested later.

Step 1: Create the paper note

Create a new paper note at the vault root, with this structure:

Read the full file on GitHub · 107 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 · 107 lines · 38 tokens per session scan A 692da264892a

Subscribe to this mod's changes

read-paper is a command published in the GitHub repository mickeytony0215-png/obsidian-llm-wiki (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,476 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.