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 LigphiDonk/Oh-my--paper --skill research-newsgit clone --depth 1 https://github.com/LigphiDonk/Oh-my--paperWrote 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/ligphidonk/oh-my--paper/research-news)<a href="https://agentmods.dev/skills/ligphidonk/oh-my--paper/research-news"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/research-news/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/ligphidonk/oh-my--paper/research-news"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/research-news.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 64 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00020 | $0.01101 |
| Opus 5 | $0.00010 | $0.00550 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
research-news 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research-news
Canonical Summary
Daily paper recommendation workflow — search arXiv and Semantic Scholar, score and recommend papers
Trigger Rules
Use this skill when the user request matches its research workflow scope. Prefer the bundled resources instead of recreating templates or reference material. Keep outputs traceable to project files, citations, scripts, or upstream evidence.
Resource Use Rules
- This skill has no bundled resource directories beyond its main instructions.
Execution Contract
- Resolve every relative path from this skill directory first.
- Prefer inspection before mutation when invoking bundled scripts.
- If a required runtime, CLI, credential, or API is unavailable, explain the blocker and continue with the best manual fallback instead of silently skipping the step.
- Do not write generated artifacts back into the skill directory; save them inside the active project workspace.
Upstream Instructions
You are the Research News Assistant for Dr. Claw.
Goal
Help users discover the latest research papers by searching arXiv and Semantic Scholar, scoring them by relevance, recency, popularity, and quality, and generating a recommended papers list.
Workflow
Step 1: Collect Context
- Get the current date (YYYY-MM-DD)
- Read research configuration from the News Dashboard config (passed via arguments or environment)
- Scan existing notes to build a keyword index
Step 2: Search Papers
Execute the search script (scripts are located in server/scripts/research-news/):
cd server/scripts/research-news
python search_arxiv.py \
--config "$CONFIG_PATH" \
--output arxiv_filtered.json \
--max-results 200 \
--top-n 10 \
--categories "cs.AI,cs.LG,cs.CL,cs.CV,cs.MM,cs.MA,cs.RO"
Step 3: Read Filtered Results
Read arxiv_filtered.json containing scored and ranked papers.
Step 4: Generate Recommendations
Create a structured recommendation list with:
- Paper title, authors, links
- Score breakdown (relevance 40%, recency 20%, popularity 30%, quality 10%)
- Matched research domains and keywords
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.
- 12d ago First seen · 122 lines · 20 tokens per session scan A 517b1910adee
research-news is a skill published in the GitHub repository LigphiDonk/Oh-my--paper (724 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,101 once invoked, about $0.0001 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
report-compose
A Paper Scout research-report workflow creates and archives reports in Lark, a collaboration and document platform. It covers document structure, diagrams, local media, delivery through Lark, and user notification.
workspace-manage
A workspace-management guide for Paper Scout, covering file layout, naming, tracked outputs, cleanup, validation, branches, pull requests, and INDEX.md logs.
memory-manage
A memory tool for Paper Scout research runs, helping retrieve, organize, and update lessons and hypotheses from earlier research cruises.
paper-deep-dive
A research workflow for investigating a selected paper or a research question it raises by reading papers, finding outside evidence, saving sources, and extracting report-ready insights.
paper-source
A research workflow for finding and downloading a broad collection of recent academic papers from configured sources, with Hugging Face Papers as the default source.
remote-compute
A routing guide for research tasks that exceed a computer’s local computing capacity. It directs those tasks to the Qizhi platform instead of reducing the work to reading only.