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.
git clone --depth 1 https://github.com/dannyhoang249-hub/pm-vietnamese-skillWrote 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/commands/dannyhoang249-hub/pm-vietnamese-skill/decision-check)<a href="https://agentmods.dev/commands/dannyhoang249-hub/pm-vietnamese-skill/decision-check"><img src="https://agentmods.dev/badge/commands/dannyhoang249-hub/pm-vietnamese-skill/decision-check/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/commands/dannyhoang249-hub/pm-vietnamese-skill/decision-check"><img src="https://agentmods.dev/badge/commands/dannyhoang249-hub/pm-vietnamese-skill/decision-check.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 | $0.00029 | $0.00513 |
| Opus 5 | $0.00015 | $0.00257 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
decision-check 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 10d ago.
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.
What it actually says
/decision-check — Kiểm tra chất lượng quyết định
Nguồn cảm hứng | Inspiration: chuyển bốn nguyên tắc của multica-ai/andrej-karpathy-skills thành workflow cho product management.
Ngôn ngữ | Language: Match the requester’s language. When asked for bilingual output, use paired Vietnamese-English headings and a single shared set of facts, assumptions, and numbers.
- Nghĩ trước khi làm | Think before acting: tách facts, assumptions và unknowns. Nếu có nhiều cách hiểu hợp lý, trình bày chúng cùng tác động đến quyết định; không âm thầm chọn một cách hiểu.
- Đơn giản trước | Simplicity first: xác định phiên bản nhỏ nhất có thể kiểm chứng outcome. Loại bỏ scope, abstraction, metric hoặc process được thêm chỉ để phòng xa.
- Phạm vi có chủ đích | Surgical scope: đối chiếu từng hạng mục với user outcome hoặc constraint đã nêu. Đánh dấu phần ngoài scope và dependency chưa được chứng minh cần thiết.
- Thực thi theo mục tiêu | Goal-driven execution: định nghĩa success criteria, failure/stop condition, cách đo, owner và bước xác thực kế tiếp. Viết kế hoạch theo dạng
bước → tín hiệu kiểm chứng. - Kết luận bằng một trong ba khuyến nghị: proceed, simplify then proceed, hoặc validate before committing.
Trả về format sau:
# Decision quality check — [Tên] | Kiểm tra chất lượng quyết định — [Tên]
## Decision and intended outcome | Quyết định và outcome mong muốn
## Facts, assumptions, and unknowns | Sự thật, giả định và điều chưa biết
## Simpler viable path | Phương án đơn giản hơn vẫn khả thi
## Scope and trade-offs | Phạm vi và đánh đổi
## Success criteria and verification loop | Tiêu chí thành công và vòng lặp kiểm chứng
| Step / Bước | Verify with / Kiểm chứng bằng | Owner | Decision triggered / Quyết định được kích hoạt |
| --- | --- | --- | --- |
## Recommendation | Khuyến nghị
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.
- 10d ago First seen · 33 lines · 29 tokens per session scan A e28599ef9f4e
decision-check is a command published in the GitHub repository dannyhoang249-hub/pm-vietnamese-skill (1 stars, last pushed 22d ago), licensed MIT. It adds 29 tokens to every session and 513 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
close
They operate it without you.
bootstrap
Bootstrap a new project with design system, CI/CD, i18n, SEO, and deploy pipeline.
orient-status
Report where the project stands — current focus, in progress, blocked.
align
Align cross-functional stakeholders.
prioritize
Command "prioritize" from Dragoon0x/product-skills, covering /prioritize, usage and related skills.
roadmap
Command "roadmap" from Dragoon0x/product-skills, covering /roadmap, usage and related skills.