obsidian-llm-wiki: Command for Claude Code

.claude/commands/lint-related-work.md

lint-related-work is a command for Claude Code from mickeytony0215-png/obsidian-llm-wiki. It costs 40 tokens per session (1,474 once invoked), scanned A, original, MIT.

A checker for the Related Work section of a research paper, which explains earlier studies and compares them with the new work.

In plain words
What is it for?
Checking a Markdown note or PDF while reading a paper, writing a paper, or preparing a research talk. TDD is not mentioned; the input describes a fairness and framing check instead.
Why use it?
It flags overly absolute wording, claims without citations, and mismatches between a paper’s claims and its comparison studies. It can also compare the framing with baseline papers.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/lint-related-work.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 lint-related-work

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/mickeytony0215-png/obsidian-llm-wiki/lint-related-work"><img src="https://agentmods.dev/badge/commands/mickeytony0215-png/obsidian-llm-wiki/lint-related-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,474 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 $0.00040 $0.01474
Opus 5 $0.00020 $0.00737
Sonnet 5 $0.00008 $0.00295
Haiku 4.5 $0.00004 $0.00147

Measured 12d ago against content hash 4f1844501e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lint-related-work 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/lint-related-work.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated fairness check for Related Work framing. Two phases: a fast mechanical pass and an optional cross-validation pass against baseline PDFs.

This repo ships the command spec only. The implementation is intentionally not bundled; fork users either reimplement the checks described below or wrap their preferred linter under this command name.

Use cases

  1. Reading a new paper: $ARGUMENTS is a note or PDF path. Flag framing red flags immediately after /read-paper.
  2. Writing your own paper: $ARGUMENTS is your draft path. Self-check for unfair framing before submission.
  3. Preparing a lab-seminar talk: lint the paper's main baselines before the talk.

Input format

/lint-related-work <path-to-note-or-pdf>
  • .md note: read the Related Work or Problem-statement section and check every baseline description.
  • .pdf: extract with pdftotext -layout, then locate the "Related Work" / "State of the Art" / "II." section.
  • No argument: scan the current note.

Checks

Phase 1: mechanical red flags (fast)

  1. Absolutist-wording grep: search the Related Work and baseline-description text for:

    • Completeness claims: completely overlooked, entirely fails, cannot support, never, always fails
    • Exaggeration claims: significant burden, excessive, severely limits, critically flawed

    Output: line number, quoted text, risk grade.

  2. Baseline extraction: grep for Author et al. [N] patterns and list every cited baseline.

  3. Scope keyword check (when input is a .md note):

    • Pull the paper's own keywords from frontmatter tags or Index Terms.
    • For each baseline, if its topic clearly does not match (e.g. an authentication paper citing a task-scheduling paper as a baseline), flag it.

Phase 2: cross-validation against the baseline PDF (slow, requires baseline in raw/papers/)

  1. Self-description check (needs baseline PDF):
    • For any baseline criticised with absolutist wording in Phase 1, look for its PDF in raw/papers/.
    • Extract the baseline's Abstract + Contributions sections.
    • Grep the baseline for the criticised claim.
    • Example: the paper criticises a baseline as "centralized", but the baseline's Abstract describes itself as "distributed" — severe inconsistency.

Read the full file on GitHub · 150 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 · 150 lines · 40 tokens per session scan A 4f1844501e99

Subscribe to this mod's changes

lint-related-work is a command published in the GitHub repository mickeytony0215-png/obsidian-llm-wiki (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,474 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.