agentmods.dev

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai is a skill for Claude Code from Rheinmir/setup. It costs 93 tokens per session (2,084 once invoked), scanned A, original, MIT.

A pre-installation review process for agent skills, which are instruction files that can tell an agent to run code, install packages, access the network, or change files. It examines the skill and its scripts before allowing installation.

In plain words
What is it for?
Use it to preview a skill, inspect its scripts and network or shell access, and optionally run a local scan before installation.
Why use it?
It helps you identify unsafe or unexpected actions before giving a skill control over your development environment. The result is an install-or-reject decision based on the available code and reports.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions AGENTS.md; built for openclaw.

not rated 11repo 20d ago A scan 93 tokens original MIT

Good fit Use it to preview a skill, inspect its scripts and network or shell access, and optionally run a local scan before installation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai
View source ↗ Rheinmir/setup
Install

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.

Any agent
npx skills add Rheinmir/setup --skill dym-scientific-agent-skills-tham-dinh-truoc-khi-cai
Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup

Made for: Claude Code.

Wrote 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.

agentmods badge for dym-scientific-agent-skills-tham-dinh-truoc-khi-cai

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai/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.

agentmods 80×15 button for dym-scientific-agent-skills-tham-dinh-truoc-khi-cai

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.02084
Opus 5.5 $0.00037 $0.00834
Sonnet 5.5 $0.00019 $0.00417
Haiku 4.5 $0.00009 $0.00208

Measured yesterday against content hash 07261f6d06d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

grep -rnE 'requests\.|urlopen|subprocess|os\.system|curl |wget ' skills/literature-review/
.overstack/doyourmagic/scientific-agent-skills/skills/dym-scientific-agent-skills-tham-dinh-truoc-khi-cai/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-scientific-agent-skills-tham-dinh-truoc-khi-cai — Thẩm định một skill TRƯỚC khi cài

Vì sao dùng: Agent Skill là chỉ dẫn mà agent của bạn sẽ tuân theo — nó có thể bảo agent chạy code tuỳ ý, cài package, gọi mạng, sửa file. Repo này nhận đóng góp cộng đồng và tự nói thẳng là không đảm bảo đã soát hết. Đây là bước bắt buộc trước 01. Sinh ra cái gì: một quyết định cài/không cài cho từng skill, dựa trên nội dung skill + báo cáo quét của repo + (tuỳ chọn) một lần quét cục bộ của chính bạn.

Bước 1 — Đọc SKILL.md mà không cài

# render SKILL.md trong terminal, không ghi file nào
gh skill preview K-Dense-AI/scientific-agent-skills literature-review

# ghim một version cụ thể để đọc
gh skill preview K-Dense-AI/scientific-agent-skills [email protected]

Chạy tương tác, gh skill preview còn cho picker để duyệt thêm scripts/, references/. Đây mới là chỗ cần soi: một skill xấu hiếm khi xấu ở SKILL.md, nó xấu trong scripts/.

Cần đọc bằng shell (grep, diff) thì clone read-only rồi soi:

git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas
cd /tmp/sas

# skill này chạm mạng ở đâu, gọi shell ở đâu
grep -rnE 'requests\.|urlopen|subprocess|os\.system|curl |wget ' skills/literature-review/

# skill này đòi biến môi trường nào
grep -rn 'environ\|getenv\|API_KEY' skills/literature-review/

Bước 2 — Tra báo cáo quét của repo

Repo chạy Cisco AI Defense Skill Scanner hằng tuần (cron Thứ Hai 09:00 UTC, .github/workflows/security-scan.yml), quét gia tăng — skill không đổi thì mang kết quả cũ sang; rescan toàn bộ ít nhất mỗi 30 ngày hoặc khi đổi scanner/model.

  • Người đọc: docs/security-report.md
  • Máy đọc (có last_scanned từng skill): docs/security-report.json

Tổng ở lần quét 2026-08-31 (đọc từ docs/security-report.json → totals):

163 skill · 988 finding · CRITICAL 34 · HIGH 9 · MEDIUM 241 · LOW 703 · INFO 1
skill "an toàn": 147/163

Read the full file on GitHub · 137 lines

Changes

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.

  1. yesterday First seen · 137 lines · 93 tokens per session scan A 07261f6d06d9

Subscribe to this mod's changes

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 93 tokens to every session and 2,084 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Building agentsSecurity
Related

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai compared with skills from other repositories

dym-scientific-agent-skills-tham-dinh-truoc-khi-cai next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-scientific-agent-skills-tham-dinh-truoc-khi-caiRheinmir/setupSkill1120d agoMITA93Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code