Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Rheinmir/setupnpx agentmods add skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-validate-test-scanWrote 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-validate-test-scan)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-validate-test-scan"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-validate-test-scan/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-validate-test-scan"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-dong-gop-validate-test-scan.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 | $0.00055 | $0.03049 |
| Opus 5.5 | $0.00022 | $0.01220 |
| Sonnet 5.5 | $0.00011 | $0.00610 |
| Haiku 4.5 | $0.00006 | $0.00305 |
Grade A, and why
dym-scientific-agent-skills-dong-gop-validate-test-scan scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- có `eval`/`exec`/`os.system`, có module trùng tên thư viện chuẩn, có đường dẫn cục bộ hardcode; How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-scientific-agent-skills-dong-gop-validate-test-scan — Đóng góp: validate, test, scan
Track ĐÓNG GÓP. Mọi lệnh chạy từ gốc repo skill đã clone.
Vì sao dùng: đây là các cổng CI thật. Chạy trước là biết PR đỏ ở đâu trong vài giây thay vì chờ vòng CI. Sinh ra cái gì: kết quả pass/fail cục bộ khớp với cái CI sẽ nói, cộng comment markdown của scanner nếu bạn chạy wrapper.
Thiết lập môi trường
Đường chính thức:
uv sync
Nếu máy chưa có uv (như máy đã dùng để kiểm chứng bundle này), cổng nhanh nhất vẫn chạy được bằng venv thuần, vì tests/_meta chỉ cần thư viện chuẩn + pytest:
python3.13 -m venv .venv
./.venv/bin/pip install pytest
./.venv/bin/python -m pytest tests/_meta -q
Repo yêu cầu Python 3.13+ (pyproject.toml → requires-python = ">=3.13").
Cổng 1 — spec conformance
# một skill
uv run skills-ref validate skills/<name>
# cả bộ, đúng như CI làm
for d in skills/*/; do uv run skills-ref validate "$d"; done
Đã chạy thật trên cả 163 thư mục (qua venv thuần, không uv): 0 lỗi. Output khi hợp lệ: Valid skill: skills/depmap, exit 0.
.github/workflows/skill-spec-validation.yml chạy đúng thứ đó ở mọi PR chạm skills/, cộng các luật repo mà skills-ref không kiểm: metadata.version có mặt, allowed-tools là chuỗi ngăn cách bằng dấu cách, scalar trong metadata được quote, và cảnh báo khi vượt 500 dòng.
Không có uv? skills-ref cài được thẳng:
./.venv/bin/pip install "skills-ref @ git+https://github.com/agentskills/agentskills.git#subdirectory=skills-ref"
./.venv/bin/skills-ref validate skills/<name>
Nó còn hai subcommand hữu ích khi debug: read-properties (in property của skill dạng JSON) và to-prompt (sinh XML <available_skills> mà agent thực sự thấy).
Cổng 2 — tests/_meta, tín hiệu nhanh nhất trong repo
uv run --with pytest python -m pytest tests/_meta -q
Đã chạy thật: 10 passed, 1213 subtests passed in 1.82s. Thuần thư viện chuẩn, không package khoa học nào, vài giây.
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 · 215 lines · 55 tokens per session scan A 1c5c46b4bb89
dym-scientific-agent-skills-dong-gop-validate-test-scan is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 3,049 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). 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-validate-test-scan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-scientific-agent-skills-dong-gop-validate-test-scanRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 55 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |