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.
npx skills add tuan3w/obsidian-vault-agent --skill paper-discovergit clone --depth 1 https://github.com/tuan3w/obsidian-vault-agentWrote 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.
[](https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/paper-discover)<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/paper-discover"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/paper-discover/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.
<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/paper-discover"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/paper-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01648 |
| Opus 5 | $0.00029 | $0.00824 |
| Sonnet 5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
paper-discover 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User asks to find papers on a topic ("find papers about scaling laws")
- User wants papers related to an existing note ("what papers connect to this?")
- User is /processing a paper and wants to find related work
- User asks "what should I read about X?"
- User provides a DOI or paper title and wants similar papers
- User wants to fill gaps in a knowledge domain </Use_When>
<Do_Not_Use_When>
- User has a paper file to analyze (use /paper or /book-analyzer)
- User wants to process an existing vault note (use /process)
- User wants general web research, not academic papers (use /research) </Do_Not_Use_When>
<Execution_Policy>
- Search first, present results, then create notes only if user approves
- Always check vault for existing paper notes before creating duplicates
- Rank by vault relevance, not just citation count
- Cap at 10 results per search — quality over quantity
- Respect Semantic Scholar rate limits (100 req/5min) </Execution_Policy>
Stage 1: PARSE QUERY AND CONTEXT
Determine the search mode from user input:
Mode A — Topic search (default): User provides a topic or question. Extract search terms.
"find papers about scaling laws for LLMs" → query: "scaling laws large language models"
Mode B — Similar papers: User references an existing vault note or provides a paper ID/DOI.
- Read the referenced note to extract title, key concepts
- Use the paper's Semantic Scholar ID or DOI for recommendations
- Fall back to keyword search if no ID available
Mode C — Gap filling: User asks about a domain. Search vault first to identify what's covered, then search for papers on uncovered subtopics.
Stage 2: SEARCH
Run the search script:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 213 lines · 58 tokens per session scan A 6a4fa7be83e6
paper-discover is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,648 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
shapely-compute
Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates.
residues
Problem-solving strategies for residues in complex analysis.
hilbert-spaces
Problem-solving strategies for hilbert spaces in functional analysis.
interpolation
Problem-solving strategies for interpolation in numerical methods.
boundary-value-problems
Problem-solving strategies for boundary value problems in odes pdes.