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 Orkas-AI/Orkas-Awesome-AgentSkills --skill paper-researchgit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/paper-research)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/paper-research"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/paper-research/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/orkas-ai/orkas-awesome-agentskills/paper-research"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/paper-research.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 | $0.00003 | $0.01475 |
| Opus 5.5 | $0.00001 | $0.00590 |
| Sonnet 5.5 | $0.00001 | $0.00295 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
paper-research 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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-research
When to use
- The user asks for recent or latest ArXiv papers by topic, author, category, keyword, or query phrase.
- The user provides an ArXiv ID, abs URL, or PDF URL and wants a structured summary, classification, deep reading, or follow-up reading suggestions.
- The user wants a short research scan: paper list, contribution summary, methods, evidence, limitations, and which papers deserve deeper reading.
Do not use for general web literature reviews outside ArXiv, thesis coaching, homework tutoring, or long-term research memory management. Do not save a research log unless the user explicitly asks to save one.
How to call
Use the bundled script for ArXiv API metadata. Then synthesize the result with the reading workflow in references/paper-reading-workflow.md.
Search by keyword, author, category, or ArXiv query:
$ORKAS_NODE $ORKAS_PC_DIR/bin/run-skill.cjs paper-research arxiv_api -- search --query "multi-agent systems" --count 5
Read one paper by ArXiv ID or URL:
$ORKAS_NODE $ORKAS_PC_DIR/bin/run-skill.cjs paper-research arxiv_api -- read --id "2401.12345"
Parameters:
search --query: ArXiv API search query. Plain text is treated asall:<query>. Native ArXiv prefixes such asau:,cat:,ti:,abs:, andid:are passed through.search --count: number of papers to return. Default5; maximum50.search --sort-by:submittedDate,lastUpdatedDate, orrelevance. DefaultsubmittedDate.search --sort-order:descendingorascending. Defaultdescending.read --id: ArXiv ID, abs URL, or PDF URL.
Workflow:
- Run the script for metadata and abstracts.
- For search results, rank papers by topic fit, novelty signal, method relevance, and whether the abstract supports the user's stated goal.
- For a single paper, classify the paper with
references/category-reading-guides.mdwhen the topic matches one of the known AI research categories; otherwise use the general reading guide. - If the user asks for deep reading and the current environment can fetch the paper/PDF/source, inspect the paper body before making claims about methods, experiments, formulas, or limitations.
- If only the abstract is available, label the output as abstract-based and avoid overclaiming.
- If the user asks to save notes, first confirm the target file/path. Use
references/research-log-template.mdfor the entry shape.
What ships with it
4 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.
- 1mo ago First seen · 147 lines · 3 tokens per session scan A 86265ae69344
paper-research is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 3mo ago), licensed MIT. It adds 3 tokens to every session and 1,475 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
handoff
Write one self-contained goal that a fresh session can continue from. Use when context is running out, before clearing a session, when usage passes 95% on a long run, or when asked for a handoff.
init
Set up Dory in this repo by exploring it, creating wiki/ from the template, and connecting the usage statusline. Use when a project has no wiki/ yet, or when asked to set up Dory.
SalesEnablementOS
Complete sales enablement intelligence — content library, onboarding, skills training, competitive battlecards, coaching frameworks, win/loss analysis, and building a sales machine that scales without the founder.
developer-advocate
Activates DeveloperAdvocate for developer relations strategy, technical content, and community growth. Use when you need a developer onboarding documentation plan, technical blog post or tutorial writing, developer community growth strategy, conference talk abstract and structure, or a DevRel metrics framework to…
learning-coach
Activates LearningCoach for adaptive education and curriculum design. Use when you need curriculum structure with learning objectives and assessments, Socratic teaching method with discovery-based explanations, concept maps and knowledge graph building, quiz and formative assessment generation with explanations, or…