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-archify-visual-check-and-previewgit 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-archify-visual-check-and-preview)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-archify-visual-check-and-preview"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-visual-check-and-preview/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-archify-visual-check-and-preview"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-visual-check-and-preview.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 | $0.00077 | $0.01573 |
| Opus 5.5 | $0.00031 | $0.00629 |
| Sonnet 5.5 | $0.00015 | $0.00315 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
dym-archify-visual-check-and-preview 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-archify-visual-check-and-preview — Bằng chứng trình duyệt thật và vòng preview trực tiếp
Vì sao dùng: deliver chứng minh artifact qua được các kiểm tra tất định trên SVG/HTML. Nó không chứng minh trang đó hành xử đúng trong một trình duyệt thật. Đó là việc của visual-check. Còn preview là vòng lặp bàn phím khi bạn đang chỉnh JSON liên tục.
Kết quả nhận được: một biên lai JSON, một contact sheet HTML, và bốn ảnh PNG thật ở hai kích thước × hai chế độ màu — hoặc một server loopback tự nạp lại chỉ khi bản mới đã qua mọi cổng.
export A=~/.claude/skills/archify
Bằng chứng trình duyệt: visual-check
Chạy trên đúng file HTML đã giao, không sửa và không render lại:
node $A/bin/archify.mjs visual-check out/workflow.html --json
Dạng người đọc (kết quả thật đã chạy trên macOS với Chrome cài sẵn):
automated browser evidence pass: /…/wf.html
visual-check containment pass; captures pass; perceptual visual review pending
receipt /…/wf.visual-check.json
contact sheet /…/wf.visual-check.html
Sidecar sinh ra (quan sát trực tiếp trên đĩa)
Cạnh wf.html, sau một lần chạy:
wf.visual-check.json 16.6K biên lai máy đọc được
wf.visual-check.html 1.8K contact sheet mở bằng trình duyệt
wf.visual-check.1440x900.light.png 392.2K
wf.visual-check.1440x900.dark.png 413.7K
wf.visual-check.2048x1320.light.png 547.2K
wf.visual-check.2048x1320.dark.png 580.7K
Mã thoát — đọc kỹ chỗ này
Từ hằng EXIT tại bin/visual-check.mjs:24:
| rc | Nghĩa |
|---|---|
0 |
pass |
1 |
fail — có vấn đề thật trong trình duyệt |
2 |
skipped — không tìm thấy Chrome/Chromium |
2 không phải pass. Từ CONTRIBUTING.md: "A browser test that was skipped because Chrome was unavailable is skipped, not passed." Một cổng CI coi != 1 là xanh sẽ âm thầm bỏ qua toàn bộ bằng chứng trình duyệt trên runner không có Chrome.
Tìm Chrome
Thứ tự dò trong bin/visual-check.mjs:
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 · 121 lines · 77 tokens per session scan A 9fe464eb94da
dym-archify-visual-check-and-preview is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 77 tokens to every session and 1,573 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-archify-visual-check-and-preview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-archify-visual-check-and-previewRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 77 | Claude Code |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 906 | 2d ago | MIT | A | 40 | Claude Code |