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.
git clone --depth 1 https://github.com/Jesseovo/PaperCashWrote 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/plugins/jesseovo/papercash/gemini-extension)<a href="https://agentmods.dev/plugins/jesseovo/papercash/gemini-extension"><img src="https://agentmods.dev/badge/plugins/jesseovo/papercash/gemini-extension/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/plugins/jesseovo/papercash/gemini-extension"><img src="https://agentmods.dev/badge/plugins/jesseovo/papercash/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
papercash 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 6d 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.
What it actually says
{
"name": "papercash",
"display_name": "PaperCash - Academic Paper Skill",
"description": "Academic metadata search, abstract-based review drafts, citation formatting and writing assistance",
"version": "2.0.0",
"entry_point": "SKILL.md",
"author": "Jesse (@Jesseovo)",
"repository": "https://github.com/Jesseovo/PaperCash",
"license": "MIT",
"keywords": ["paper", "academic", "citation", "literature-review", "plagiarism", "ai-detection"]
}
What ships with it
37 files beside gemini-extension.json 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.
- agents/openai.yaml 216 B
- scripts/build_discovery.py 11 KB runs code
- scripts/lib/__init__.py 69 B runs code
- scripts/lib/cache.py 1.2 KB runs code
- scripts/lib/dates.py 1.0 KB runs code
- scripts/lib/dedupe.py 2.0 KB runs code
- scripts/lib/env.py 2.7 KB runs code
- scripts/lib/features/__init__.py 29 B runs code
- scripts/lib/features/ai_humanize.py 12 KB runs code
- scripts/lib/features/citation.py 8.1 KB runs code
- scripts/lib/features/docx_export.py 4.8 KB runs code
- scripts/lib/features/format_helper.py 9.7 KB runs code
- scripts/lib/features/lit_review.py 6.2 KB runs code
- scripts/lib/features/plagiarism_v2.py 11 KB runs code
- scripts/lib/features/plagiarism.py 4.2 KB runs code
- scripts/lib/features/writing.py 11 KB runs code
- scripts/lib/http_client.py 4.0 KB runs code
- scripts/lib/query.py 3.9 KB runs code
- scripts/lib/relevance.py 2.2 KB runs code
- scripts/lib/render_agent.py 9.8 KB runs code
- scripts/lib/render.py 5.8 KB runs code
- scripts/lib/safety.py 8.0 KB runs code
- scripts/lib/schema.py 2.9 KB runs code
- scripts/lib/score.py 1.5 KB runs code
- scripts/lib/setup_wizard.py 2.3 KB runs code
- scripts/lib/similarity_engine.py 11 KB runs code
- scripts/lib/sources/__init__.py 32 B runs code
- scripts/lib/sources/arxiv.py 3.0 KB runs code
- scripts/lib/sources/baidu_xueshu.py 3.3 KB runs code
- scripts/lib/sources/cnki.py 3.5 KB runs code
- scripts/lib/sources/crossref.py 4.1 KB runs code
- scripts/lib/sources/google_scholar.py 3.0 KB runs code
- scripts/lib/sources/pubmed.py 2.2 KB runs code
- scripts/lib/sources/semantic_scholar.py 3.5 KB runs code
- scripts/lib/sources/wanfang.py 3.0 KB runs code
- scripts/lib/ui.py 2.3 KB runs code
- scripts/papercash.py 17 KB runs code
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.
- 6d ago First seen · 12 lines scan A 3486b333a8f4
papercash is a plugin published in the GitHub repository Jesseovo/PaperCash (159 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-21.
Other plugins, from other repositories
co-researcher
Academic research plugin for Claude Code: literature reviews, systematic reviews, peer review and citation checking, with every citation verified against OpenAlex, arXiv and Europe PMC.
co-researcher
Academic research extension for Gemini CLI: literature reviews, systematic reviews, peer review and citation checking, with every citation verified against OpenAlex, arXiv and Europe PMC.
aej-applied-economics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Applied Economics (AEJ: Applied) — the American Economic Association's quarterly journal for empirical applied microeconomics with credible causal identification, spanning labor, development, health, education, public, urban, environmental…
aej-macroeconomics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Macroeconomics (AEJ: Macro) — the American Economic Association's quarterly journal for broad-interest macroeconomics, covering growth, business cycles, monetary and fiscal policy, labor-macro, international macro, and macro-finance. The pack.
acm-mm-skills
A 12-skill depth pack for ACM Multimedia (ACM MM) submissions: multimedia-vs-computer-vision routing, OpenReview submission checks, thematic-area targeting, anonymous rebuttal, ACM sigconf camera-ready, Open Source and Reproducibility tracks, ACM artifact badging, supplementary media, review process, writing style…
asplos-skills
A 12-skill depth pack for ASPLOS submissions: cross-layer venue fit, the two-deadline HotCRP cycle, rapid review and rebuttal strategy, Major Revision handling, camera-ready, ACM artifact badges, hardware-evaluation reproducibility, supplementary appendices, writing style, related work, experiments, and workflow.…