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 Rheinmir/setup --skill dym-scientific-agent-skills-dong-gop-them-sua-skillgit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-scientific-agent-skills-dong-gop-them-sua-skill)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-them-sua-skill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-them-sua-skill/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/rheinmir/setup/dym-scientific-agent-skills-dong-gop-them-sua-skill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-them-sua-skill.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 | $0.00078 | $0.02854 |
| Opus 5.5 | $0.00031 | $0.01142 |
| Sonnet 5.5 | $0.00016 | $0.00571 |
| Haiku 4.5 | $0.00008 | $0.00285 |
Grade A, and why
dym-scientific-agent-skills-dong-gop-them-sua-skill 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-scientific-agent-skills-dong-gop-them-sua-skill — Đóng góp: thêm hoặc sửa một skill
Track ĐÓNG GÓP. File này dành cho người clone chính repo skill để sửa nó. Nếu bạn chỉ muốn dùng skill, quay lại 01.
Vì sao dùng: repo có một số luật ngầm mà CI chặn cứng và validator báo lỗi rất khó hiểu (đặc biệt là luật strictyaml). File này là bản kê đúng thứ tự, để PR không bị đá vì lý do hình thức.
Sinh ra cái gì: một skills/<name>/ hợp lệ, một tests/<name>/ nếu skill có scripts/, một entry trong tests/skill-requirements.toml, và một PR vượt cổng.
0. Có nên nằm trong repo này không
AGENTS.md liệt kê các loại bị từ chối như thường lệ:
- Skill kỹ thuật phần mềm/phán đoán code chung — chúng cạnh tranh chỗ chọn ở mọi task.
- Hạ tầng chung có dán thêm một ví dụ khoa học (vector database, cloud SDK) — nhận một cái là phải gánh mọi đối thủ.
- Skill "orchestrator" rộng, chuyên route sang skill khác — theo thiết kế là đè lên mọi chuyên gia.
- Provider thứ hai cho một dịch vụ đã có skill.
Trong phạm vi: một skill hẹp cho một package/database/platform/workflow nghiên cứu — scanpy, depmap, benchling-integration, experimental-design.
Các skill dùng chung đang tồn tại (docx, pdf, pptx, generate-image, markdown-mermaid-writing) là helper định dạng output hẹp, và AGENTS.md nói thẳng chúng không phải tiền lệ để mở rộng phạm vi.
1. Layout
plugin.json # manifest Agent Plugins (repo root)
skills/<skill-name>/
├── SKILL.md # BẮT BUỘC — file duy nhất bắt buộc
├── references/ # tuỳ chọn: tài liệu dài, chỉ nạp khi cần
├── scripts/ # tuỳ chọn: helper chạy được
└── assets/ # tuỳ chọn: template, tài nguyên tĩnh
Ba luật tuyệt đối:
- Tên thư mục =
nametrong frontmatter. Không khớp là hỏng. - Test KHÔNG BAO GIỜ nằm dưới
skills/. Thư mục skill chỉ chứa thứ agent nạp. Test đi vàotests/<skill-name>/, fixture vàotests/<skill-name>/fixtures/. - Diagram cũng không nằm dưới
skills/. Nếu có, nó ởdocs/images/<skill-name>.png.
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.
- yesterday First seen · 186 lines · 78 tokens per session scan A 055549d7fb75
dym-scientific-agent-skills-dong-gop-them-sua-skill is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 78 tokens to every session and 2,854 once invoked, about $0.0003 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 2026-11-07.
dym-scientific-agent-skills-dong-gop-them-sua-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-scientific-agent-skills-dong-gop-them-sua-skillRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 78 | Claude Code |
| dataladK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 147 | Claude Code |
| manuscript-as-codeforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | today | Apache-2.0 | A | 43 | Claude Code |
| latex-diffflonat/flonat-research | Skill | 149 | 5d ago | MIT | A | 56 | Claude Code |
| refactor-research-codeShaishavMaisuria/research-paper-lifecycle-skills | Skill | 60 | 15d ago | Apache-2.0 | A | 60 | Claude Code, Codex |
| template-publishdocxology/template | Skill | 23 | today | Apache-2.0 | A | 52 | Claude Code, Codex |
| implement-experimentTalonT-Org/AutoSkillit | Skill | 5 | yesterday | MIT | A | 24 | Claude Code |