agentmods.dev

dym-diagram-design-selfcheck-and-your-ci

dym-diagram-design-selfcheck-and-your-ci is a skill for Claude Code from Rheinmir/setup. It costs 81 tokens per session (2,144 once invoked), scanned A, original, MIT.

A self-check script and GitHub Actions workflow for validating generated diagram HTML. GitHub Actions is a service that runs checks automatically when code changes.

In plain words
What is it for?
Use it to check one or more HTML diagram files locally and run the same gate in a repository's continuous-integration workflow.
Why use it?
Generated HTML has no compiler to catch mistakes, so the included check gives a repeatable pass-or-fail result before work is accepted.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /tmp/dd/skills/diagram-design/scripts/self_check.py "${files[@]}".

not rated 11repo 20d ago A scan 81 tokens original MIT

Good fit Use it to check one or more HTML diagram files locally and run the same gate in a repository's continuous-integration workflow.

Compare 6 skills from other repositories ↓
View source ↗ Rheinmir/setup
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup
agentmods
npx agentmods add skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci

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-diagram-design-selfcheck-and-your-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci/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-diagram-design-selfcheck-and-your-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-diagram-design-selfcheck-and-your-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00081 $0.02144
Opus 5.5 $0.00032 $0.00858
Sonnet 5.5 $0.00016 $0.00429
Haiku 4.5 $0.00008 $0.00214

Measured yesterday against content hash 5c3a3cb9bac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-diagram-design-selfcheck-and-your-ci 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.

.overstack/doyourmagic/diagram-design/skills/dym-diagram-design-selfcheck-and-your-ci/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-diagram-design-selfcheck-and-your-ci — Tự kiểm output và khoá nó bằng CI của BẠN

Vì sao dùng: sơ đồ do agent sinh ra là HTML tự do — không có compiler nào bắt lỗi. self_check.py là cổng tất định, 0-token, không phụ thuộc ngoài được ship bên trong skill để chính agent tự kiểm sản phẩm của mình. Đây là thứ biến "trông có vẻ ổn" thành "đã kiểm".

File này sinh ra gì: một lệnh gate chạy được ở local, cộng một GitHub Actions workflow tối thiểu cho repo của bạn.

Toàn bộ file này là lệnh shell.

1. self_check.py — chữ ký và mã thoát

python3 <skill-dir>/scripts/self_check.py <file.html> [<file.html> ...]

Nhận nhiều file (nargs="+"). Không có cờ nào khác.

Tình huống rc stdout
Mọi file sạch 0 OK <path> mỗi file
Có ít nhất một file lỗi 1 FAIL <path> + danh sách gạch đầu dòng

Đã đo bằng chạy thật: OK → rc=0, FAIL → rc=1. Đây là quy ước 0/1 quen thuộc — khác hai extractor ở 04 (0/2).

Script không có thư viện ngoài — chỉ stdlib (argparse, re, html.parser, pathlib). Chạy được ngay cả trên Python 3.9.6 (đã đo), dù references/doctor.md khai 3.10+.

2. Nó kiểm gì

Docstring khai ba nhóm; danh sách dưới đây lấy từ chính các thông điệp lỗi trong mã.

2.1 Hợp đồng SVG accessible

  • File sơ đồ phải có ít nhất một SVG accessible (không aria-hidden).
  • Mỗi SVG cần role="img".
  • <title> phải là con đầu tiên của SVG.
  • <title> và <desc> phải không rỗng.
  • ID của title/desc phải có tiền tố theo sơ đồ, không bao giờ trần — đây là thứ cho phép nhiều SVG inline chung một trang mà figure này không "mượn" tên của figure kia.
  • aria-labelledby phải trỏ title trước, desc sau, đúng thứ tự.

2.2 An toàn một-file

  • Không tham chiếu từ xa, trừ đúng một stylesheet Google Fonts /css2 đã duyệt.
  • Không URL thực thi được (javascript: …).
  • Không data-URL phi ảnh.
  • Nhiều nhất một <script>, và script đó phải mang đúng thuộc tính data-diagram-co… chính tắc và khớp verbatim controller trong template-motion.html.

Read the full file on GitHub · 202 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 · 202 lines · 0 tokens per session scan A 5c3a3cb9bac3

Subscribe to this mod's changes

dym-diagram-design-selfcheck-and-your-ci is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 81 tokens to every session and 2,144 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.

Design and UXTesting
Related

dym-diagram-design-selfcheck-and-your-ci compared with skills from other repositories

dym-diagram-design-selfcheck-and-your-ci next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-diagram-design-selfcheck-and-your-ciRheinmir/setupSkill1120d agoMITA81Claude Code
webgl-holographic-foilnexu-io/open-designSkill107ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill107ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill107ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10k2d agoApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code