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-impeccable-ci-integrationWrote 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-impeccable-ci-integration)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-impeccable-ci-integration"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-ci-integration/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-impeccable-ci-integration"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-ci-integration.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 | $0.00042 | $0.01901 |
| Opus 5.5 | $0.00017 | $0.00760 |
| Sonnet 5.5 | $0.00008 | $0.00380 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
dym-impeccable-ci-integration 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-impeccable-ci-integration — Cắm detector vào CI của dự án bạn
Vì sao dùng: biến 61 luật tất định thành một cổng chặn, để design slop không lọt qua review.
Sinh ra cái gì: một bước CI có mã thoát rõ ràng, cộng file impeccable.json làm artifact để soi lại.
Đây là ví dụ viết mới, tối giản, cho người tiêu thụ. Đừng copy
.github/workflows/ci.ymlcủa repo Impeccable: nó build và test chính Impeccable (matrix Node 22.18.0/24, Playwright, provider API key, cổng generated-output) — không liên quan gì tới việc bạn quét dự án mình.
Ba điều phải xử lý đúng trong CI
- rc 2 nghĩa là "có phát hiện", không phải crash. Coi mọi
rc != 0là lỗi hạ tầng là hiểu sai. Rẽ nhánh tường minh:0xanh,2đỏ vì design,1đỏ vì quét không xong. - Đường dẫn sai không làm CI đỏ. Target không tồn tại chỉ in
Warning: cannot access ...rồi thoát 0 (cli/engine/cli/main.mjs:326). Đổi tên thư mục là cổng lặng lẽ quét 0 file mà vẫn xanh. Phải tự kiểm tra target tồn tại. - Đừng gọi qua
npxnếu cần tách stdout/stderr.npxgộp stderr vào stdout (đo trên npm 10.9.2). Cài dependency và gọi./node_modules/.bin/impeccable.
Thêm: package.json khai engines.node >= 22.18.0. Node thấp hơn vẫn chạy nhưng npm cảnh báo EBADENGINE — pin runner ở 22.18 trở lên cho gọn log.
Script cổng (dùng chung cho mọi CI)
scripts/design-gate.sh:
#!/usr/bin/env bash
# Cổng design tất định. rc: 0 sạch · 1 quét không xong · 2 có finding.
set -uo pipefail
TARGET="${1:-src}"
REPORT="${2:-impeccable.json}"
BIN=./node_modules/.bin/impeccable
[ -x "$BIN" ] || { echo "::error::impeccable chưa được cài. Chạy: npm ci"; exit 1; }
[ -e "$TARGET" ] || { echo "::error::target quét không tồn tại: $TARGET"; exit 1; }
"$BIN" detect --json "$TARGET" > "$REPORT"
rc=$?
case "$rc" in
0) echo "Design gate: sạch (0 finding chính)."; ;;
2) echo "::error::Design gate: có finding. Xem $REPORT."
node -e '
const f = require("./'"$REPORT"'").filter(x => !x.advisory);
for (const x of f) console.log(`${x.file}${x.line ? ":" + x.line : ""} [${x.antipattern}] ${x.snippet}`);
console.log(`\n${f.length} finding chính.`);
'
;;
1) echo "::error::Design gate: ít nhất một target không quét được (lỗi vận hành)."; ;;
*) echo "::error::Design gate: mã thoát lạ ($rc)."; ;;
esac
exit "$rc"
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 · 185 lines · 42 tokens per session scan A fd2e4930587e
dym-impeccable-ci-integration is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 42 tokens to every session and 1,901 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-impeccable-ci-integration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-impeccable-ci-integrationRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 42 | Claude Code |
| temps-design-systemgotempsh/temps | Skill | 904 | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| designjuliusz-cwiakalski/agentic-delivery-os | Skill | 43 | today | MIT | A | 14 | Claude Code |
| frontend-designerData-Wise/craft | Skill | 4 | 3d ago | MIT | A | 52 | Claude Code |
| blueprintbig-emotion/agent-atelier | Skill | 3 | 24d ago | MIT | A | 0 | Claude Code |
| validate-fidelitybig-emotion/agent-atelier | Skill | 3 | 24d ago | MIT | A | 41 | Claude Code |
| architecture-diagrammingjoao-aires/agent-skills-public | Skill | 2 | 2d ago | MIT | A | 44 | Claude Code, Codex |