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-archify-ci-diagram-gateWrote 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-ci-diagram-gate)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-archify-ci-diagram-gate"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-ci-diagram-gate/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-ci-diagram-gate"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-ci-diagram-gate.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 | $0.00067 | $0.01951 |
| Opus 5.5 | $0.00027 | $0.00780 |
| Sonnet 5.5 | $0.00013 | $0.00390 |
| Haiku 4.5 | $0.00007 | $0.00195 |
Grade A, and why
dym-archify-ci-diagram-gate 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-archify-ci-diagram-gate — Chốt cổng CI cho sơ đồ trong dự án của bạn
Vì sao dùng: sơ đồ kiến trúc bị thối là vì không ai bắt buộc chúng phải đúng. Nếu nguồn JSON của sơ đồ nằm trong repo, CI có thể từ chối merge khi nguồn không còn validate được.
Kết quả nhận được: một job CI chặn PR, và (tuỳ chọn) các file HTML đã render làm artifact tải về.
Đây là ví dụ viết mới, tối thiểu. Nó không phải bản sao của
.github/workflows/ci.ymltrong repo Archify — file đó build và test chính Archify (ma trận Node 18/20/22/24, test trình duyệt thật, decode WebM, kiểm định danh release) và không liên quan gì tới việc bạn dùng Archify.
Bố cục repo giả định
docs/diagrams/
runtime.architecture.json
release.workflow.json
checkout.sequence.json
Quy ước đặt tên <tên>.<type>.json là thứ giữ script bên dưới ngắn — loại sơ đồ suy ra từ chính tên file. Nếu bạn không theo quy ước này, hãy khai một bảng ánh xạ tường minh.
Script cổng
scripts/check-diagrams.sh:
#!/usr/bin/env bash
set -uo pipefail
A="${ARCHIFY_HOME:?đặt ARCHIFY_HOME trỏ vào thư mục skill archify}"
CLI="node $A/bin/archify.mjs"
failed=0
shopt -s nullglob
for f in docs/diagrams/*.json; do
base="$(basename "$f" .json)"
type="${base##*.}"
case "$type" in
architecture|workflow|sequence|dataflow|lifecycle) ;;
*) echo "BỎ QUA $f (không suy ra được loại từ tên file)"; continue ;;
esac
$CLI validate "$type" "$f" --quality showcase --json > "/tmp/${base}.validate.json"
rc=$?
case $rc in
0) echo "OK $f" ;;
2) echo "LỖI GỌI $f — dòng lệnh sai, không phải lỗi nội dung sơ đồ"; failed=1 ;;
*) echo "HỎNG $f"; failed=1
python3 -c "import json,sys;[print(' ',d['code'],'—',d['message']) for d in json.load(open(sys.argv[1])).get('diagnostics',[])]" \
"/tmp/${base}.validate.json" ;;
esac
done
exit $failed
Ba điểm cố ý:
- Phân biệt rc
2với rc1.2nghĩa là script của bạn gọi sai (loại sơ đồ lạ, cờ lạ,--repo-rootsai chỗ). Gộp chung với1sẽ khiến bạn đi sửa sơ đồ trong khi lỗi nằm ở CI. - Ép
--quality showcase. Nếu không, một biên lai 4-check có thể trôi qua và bạn tưởng đã nghiệm thu showcase. - In
diagnostics[].code, không in stack. Mã ổn định, thông điệp thì không.
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 · 188 lines · 67 tokens per session scan A 82581ce05d9c
dym-archify-ci-diagram-gate is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 1,951 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-ci-diagram-gate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-archify-ci-diagram-gateRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 67 | Claude Code |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 69 | Claude Code |
| atmos-profilescloudposse/atmos | Skill | 1.4k | today | Apache-2.0 | A | 35 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.2k | yesterday | MIT | A | 56 | Claude Code, Codex |
| monorepo-managementwshobson/agents | Skill | 42k | 2d ago | MIT | C | 54 | Claude Code |
| managing-github-actions-secretsPostHog/posthog-foss | Skill | 728 | today | MIT | A | 67 | Claude Code, Codex |
| postman-newman-automationLambdaTest/agent-skills | Skill | 391 | 2d ago | MIT | A | 156 | Claude Code, Codex |