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 | $0.00002 | $0.00737 |
| Sonnet 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 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 — 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.
- 12d 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 2mo ago), licensed MIT. It adds 3 tokens to every session and 1,475 once invoked, about $0.0000 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
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.