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-arex-skill-contributor-dong-gop-skillWrote 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-arex-skill-contributor-dong-gop-skill)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-arex-skill-contributor-dong-gop-skill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-contributor-dong-gop-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-arex-skill-contributor-dong-gop-skill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-contributor-dong-gop-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 | $0.00051 | $0.02080 |
| Opus 5.5 | $0.00020 | $0.00832 |
| Sonnet 5.5 | $0.00010 | $0.00416 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade A, and why
dym-arex-skill-contributor-dong-gop-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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-arex-skill-contributor-dong-gop-skill — Contributor: đóng góp / refresh một repo skill vào thư viện
Vì sao dùng: Bạn muốn thêm repo vào bộ 1.000, hoặc cập nhật một skill đã cũ so với upstream.
Sinh ra cái gì: Một cây skill runtime dưới skills/repositories/repo-skills/<skill-id>/, router đã sinh lại, catalog đã cập nhật, và một PR khai đủ nguồn gốc.
1. File bắt buộc của một skill mới
skills/repositories/repo-skills/<skill-id>/
├── SKILL.md ← bắt buộc
├── references/repo-provenance.md ← bắt buộc
├── references/repo-routing-metadata.json ← bắt buộc (v2)
├── sub-skills/ ← khi upstream có nhiều vùng workflow lớn
└── scripts/ ← script validate/preflight nhỏ, nếu giúp skill an toàn hơn
repo-routing-metadata.json v2 chỉ giữ mức tối thiểu: định danh chuẩn owner/repository, skill ID, taxonomy hash, routing status, và assignment chính xác. Lý do phân loại và bằng chứng đầy đủ nằm NGOÀI cây runtime — trong artifact routing-decision hoặc thư mục handoff skills/disco/routing_decision/ của repo.
Tách bạch: test case, review note, generation report không nằm trong thư mục skill runtime, trừ khi chúng thực sự là guidance runtime.
2. Cách sinh: dùng Creator, đừng viết tay
disco --creator -p "/skill:create-repo-skill Create and verify a repository skill for /absolute/path/to/repo."
Rồi để verify-repo-skill gác. Phân loại (classification) là bước riêng sau verify, đối chiếu với taxonomy cố định.
Khi không có family nào khớp chính xác → ghi unclassified và hỏi người dùng có import không. Muốn đưa vào thì đề xuất mở rộng taxonomy và chờ duyệt trước khi đổi taxonomy canonical. Phân loại bị gián đoạn hoặc không truy cập được là blocked/failed — không đoán bừa một route.
3. Rebuild router (đừng sửa tay Markdown sinh ra)
node cli/packages/coding-agent/src/disco/skills/verify-repo-skill/scripts/update_repo_skills_router.mjs \
--library-root skills/repositories
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 · 158 lines · 51 tokens per session scan A 1403283767a8
dym-arex-skill-contributor-dong-gop-skill is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 51 tokens to every session and 2,080 once invoked, about $0.0002 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-arex-skill-contributor-dong-gop-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-arex-skill-contributor-dong-gop-skillRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 51 | 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 |