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 SebastianElvis/reaper --skill search-papergit clone --depth 1 https://github.com/SebastianElvis/reaperWrote 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/sebastianelvis/reaper/search-paper)<a href="https://agentmods.dev/skills/sebastianelvis/reaper/search-paper"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/search-paper/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/sebastianelvis/reaper/search-paper"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/search-paper.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 | $0.00057 | $0.01865 |
| Opus 5 | $0.00028 | $0.00932 |
| Sonnet 5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
search-paper 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Paper
A single skill that wraps five platform drivers — two preprint archives (arXiv, IACR ePrint) and three metadata services (Semantic Scholar, DBLP, OpenAlex). The SKILL.md itself acts as the orchestrator: each script does one thing per platform, and the agent chains them.
Usage
Invoke this skill by name. On slash-command hosts: /search-paper "<query>".
search-paper "post-quantum threshold signatures" --source iacr --max-results 15
Scripts
Run via Bash. All scripts emit JSON on stdout.
arxiv.py — arXiv preprint server
python3 arxiv.py search "BFT consensus communication complexity" --max-results 10 --categories cs.CR,cs.DC
python3 arxiv.py recent "threshold signatures" --max-results 10 --categories cs.CR
python3 arxiv.py download 2305.12345 --output-dir reaper-workspace/papers/
python3 arxiv.py journal-ref 2305.12345
search— array of{arxiv_id, title, authors, year, abstract, categories, pdf_url, published, journal_ref}sorted by relevance.recent— same fields, sorted by submission date (newest first). Requires a query and/or--categories.download— saves PDF, returns{path, title}.journal-ref— author-supplied venue (sparse but authoritative when present).
iacr.py — IACR ePrint archive
python3 iacr.py search "threshold signatures" --max-results 10
python3 iacr.py recent --max-results 10
python3 iacr.py download 2024/1234 --output-dir reaper-workspace/papers/
python3 iacr.py url 2024/1234
python3 iacr.py pubinfo 2024/1234
search— array of{eprint_id, title, authors, year, abstract, publication_info, venue, pdf_url, url}. Top 5 results are enriched with metadata from the paper page (includingpublication_info).recent— most-recently-posted ePrint papers.download/url— PDF download and URL resolution.pubinfo— scrapes the "Publication info" line from the paper page (e.g. "A major revision of CRYPTO 2023") and best-effort parses out the venue acronym + year.
What ships with it
5 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 · 176 lines · 57 tokens per session scan A 5796c160a797
search-paper is a skill published in the GitHub repository SebastianElvis/reaper (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,865 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 2026-08-31.
Other skills, from other repositories
paper-orchestra
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…
paper-compile
A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.
paper-analyzer
Transform academic papers into in-depth technical articles with multiple writing style options. Use the MinerU Cloud API for high-precision PDF parsing, automatically extracting images, tables, and formulas. Optional formula explanations and GitHub code analysis, generating Markdown and HTML formats.
publish-paper
Take a frozen AIRAS paper from experiment results to the paper of record — realize every stated number from declared values, compile and verify locally until green, then push and let CI re-run the verification, handing the user the CI-built PDF artifact and report. Use after experiments to fill, check, and publish the…
figure-drawing
MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Must be activated BEFORE writing any drawing code. Produces standalone .tex → compiled PDF/PNG → \includegraphics in paper. Never inline TikZ code directly into paper sections.
arxiv-search
Single-machine academic paper search and PDF handling for any research field. Searches arXiv and Semantic Scholar without an API key, with DuckDuckGo as a web fallback, and extracts/downloads PDFs locally. MCP servers (arxiv-mcp-server, Ai2 Asta) are used when available. Use for quick, focused lookups in any…