agentmods.dev

paper-search

paper-search is a skill for Claude Code from JeanDiable/obsidian-claude. It costs 28 tokens per session (912 once invoked), scanned A, original, MIT.

A search workflow for finding paper notes in an Obsidian vault by title, author, keyword, research area, or tag.

In plain words
What is it for?
Use it to find papers by a particular author, topic, domain, or tag, with results scored and grouped by research area.
Why use it?
It helps locate related papers in a large collection without manually opening and scanning every note.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the obsidian-claude plugin — 19 skills shipped together

not rated 2repo 8mo ago A scan 28 tokens original MIT

Good fit Use it to find papers by a particular author, topic, domain, or tag, with results scored and grouped by research area.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeandiable/obsidian-claude/paper-search
View source ↗ JeanDiable/obsidian-claude
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.

Any agent
npx skills add JeanDiable/obsidian-claude --skill paper-search
Clone the repo
git clone --depth 1 https://github.com/JeanDiable/obsidian-claude

Made for: Claude Code.

Or install obsidian-claude, the plugin that ships this one along with the rest of its 19 skills.

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 paper-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeandiable/obsidian-claude/paper-search/github.svg)](https://agentmods.dev/skills/jeandiable/obsidian-claude/paper-search)
Your own site
<a href="https://agentmods.dev/skills/jeandiable/obsidian-claude/paper-search"><img src="https://agentmods.dev/badge/skills/jeandiable/obsidian-claude/paper-search/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 paper-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeandiable/obsidian-claude/paper-search"><img src="https://agentmods.dev/badge/skills/jeandiable/obsidian-claude/paper-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 912 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 $0.00028 $0.00912
Opus 5.5 $0.00011 $0.00365
Sonnet 5.5 $0.00006 $0.00182
Haiku 4.5 $0.00003 $0.00091

Measured 2mo ago against content hash 976e514ee3d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-search 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 2mo 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/paper-search/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Paper Searcher.

Goal

Help users search for related papers in existing paper notes through keywords, authors, research domains, or specific topics.

Workflow

Step 1: Parse Search Query

Analyze user's search query to determine:

  1. Search type

    • Title search: query contains specific title
    • Author search: query contains author name
    • Keyword search: query contains specific keywords
    • Domain search: query for specific domain
    • Tag search: query contains specific tags

  2. Extract search parameters

    • Primary search terms (must match)
    • Secondary keywords (optional)
    • Exclusion keywords (optional)

  3. Determine search scope

    • All domains (default)
    • Specific domain (if specified)

2.1 Search Strategy

Use Grep in 50_Clippings/Papers/ directory to search:

  • Title search: search titles across all files
  • Author search: search frontmatter authors field
  • Keyword search: search document content
  • Domain search: search specific domain folders

2.2 Search Parameters

# Search by title
grep -r -i "query keyword" "$OBSIDIAN_VAULT_PATH/50_Clippings/Papers/" --include="*.md"

# Search by author
grep -r "author name" "$OBSIDIAN_VAULT_PATH/50_Clippings/Papers/" --include="*.md" | grep -i "author"

# Search by domain
grep -r "keyword" "$OBSIDIAN_VAULT_PATH/50_Clippings/Papers/[domain]/"

Step 3: Process Search Results

3.1 Organize Results

  1. Extract basic info

    • Paper title
    • Authors
    • Publication date
    • Domain
    • File path

  2. Match context

    • Extract matching lines (where keywords appear)
    • Used for calculating relevance

3.2 Calculate Relevance Score

  • Title match (high weight): +10 points
  • Content match (medium weight): +5 points
  • Author match (high weight): +8 points
  • Domain match (medium weight): +5 points
  • Tag match (medium weight): +3 points

3.3 Apply Filtering

  • Exclude papers containing exclusion keywords
  • Remove papers with quality score below threshold (optional)

Read the full file on GitHub · 140 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. 2mo ago First seen · 140 lines · 28 tokens per session scan A 976e514ee3d2

Subscribe to this mod's changes

paper-search is a skill published in the GitHub repository JeanDiable/obsidian-claude (2 stars, last pushed 8mo ago), licensed MIT. It adds 28 tokens to every session and 912 once invoked, about $0.0001 per session on Opus 5.5. 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.

Research
Related

paper-search compared with skills from other repositories

paper-search next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
paper-searchJeanDiable/obsidian-claudeSkill28mo agoMITA28Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code