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-chat-commandsWrote 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-chat-commands)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-impeccable-chat-commands"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-chat-commands/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-chat-commands"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-chat-commands.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 | $0.00059 | $0.02391 |
| Opus 5.5 | $0.00024 | $0.00956 |
| Sonnet 5.5 | $0.00012 | $0.00478 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade A, and why
dym-impeccable-chat-commands 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-impeccable-chat-commands — 23 lệnh /impeccable (chỉ gõ trong CHAT)
Vì sao dùng: một bộ từ vựng design chung với agent — audit, critique, polish, harden... — thay vì mỗi lần lại mô tả lại từ đầu.
Sinh ra cái gì: thay đổi code trong dự án, cộng các artifact dưới .impeccable/ (PRODUCT.md, DESIGN.md, surfaces/*.md, critique/*.md).
⚠️ Mọi thứ trong file này gõ trong khung chat của AI agent, KHÔNG phải terminal. CLI chặn cố ý:
$ npx impeccable init "init" is not a CLI command. Type /impeccable init in your AI coding agent's chat ... (rc 1)Lệnh shell nằm ở
01–04. Đừng trộn hai loại.
Bắt đầu: /impeccable init (một lần cho mỗi dự án)
/impeccable init
init soi dự án, hỏi chỉ những khoảng trống thật sự về bối cảnh sản phẩm bền vững, rồi ghi PRODUCT.md (người dùng, mục đích, bối cảnh vận hành, ràng buộc, giọng điệu, bằng chứng). Nếu đã có code, nó đề nghị luôn DESIGN.md (màu, typography, component). Nó cũng cấu hình trước live mode và ghi buildPath vào .impeccable/config.json.
Mọi lệnh khác đọc hai file này trước khi làm việc. Bỏ init là mọi lệnh sau đó đoán mò bối cảnh.
buildPath có hai giá trị:
| Giá trị | Nghĩa |
|---|---|
"comp" |
Sinh bản comp full-fidelity trước rồi build bám theo. Đậm hơn, lâu hơn. |
"code" |
Build thẳng bằng code, tham vọng ghi vào direction contract của surface brief. Gọn hơn, nhanh hơn. |
{ "buildPath": "comp" }
Ghi đè trên một máy bằng .impeccable/config.local.json (ví dụ harness của bạn không có image generation). Không cần chạy lại init để đổi: mỗi trang quyết định có toggle ở footer, lật là bind cho phiên đó.
23 lệnh
Đếm và mô tả lấy từ plugin/skills/impeccable/scripts/command-metadata.json, không phải từ bảng trong README.
Thiết lập & bối cảnh
| Lệnh | Tham số | Làm gì |
|---|---|---|
/impeccable init |
— | Setup một lần: PRODUCT.md, cấu hình live, gợi ý bước kế |
/impeccable document |
— | Sinh DESIGN.md từ code đang có (màu, type, spacing, radii, component). Theo format Google Stitch |
/impeccable extract |
[target] |
Gom pattern/component/token lặp lại vào design system |
/impeccable shape |
[feature] |
Lên UX/UI trước khi viết code, có phỏng vấn nhiều vòng |
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 · 166 lines · 59 tokens per session scan A d279994c8c4b
dym-impeccable-chat-commands is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 2,391 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-chat-commands compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-impeccable-chat-commandsRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 59 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |