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/write-prd)<a href="https://agentmods.dev/commands/dannyhoang249-hub/pm-vietnamese-skill/write-prd"><img src="https://agentmods.dev/badge/commands/dannyhoang249-hub/pm-vietnamese-skill/write-prd/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/write-prd"><img src="https://agentmods.dev/badge/commands/dannyhoang249-hub/pm-vietnamese-skill/write-prd.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 | $0.00023 | $0.00279 |
| Opus 5 | $0.00012 | $0.00139 |
| Sonnet 5 | $0.00005 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
write-prd 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 9d 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
/write-prd — Viết Lean PRD
Ngôn ngữ | Language: Match the requester’s language. When asked for bilingual output, use Vietnamese-English headings and references/templates-bilingual.md.
- Xác định user problem, outcome, người dùng chính, bằng chứng, deadline và ràng buộc.
- Viết mục tiêu đo được, guardrail và phần không nằm trong phạm vi trước khi mô tả giải pháp.
- Mô tả user flow và yêu cầu theo hành vi có thể kiểm chứng, không mặc định áp đặt implementation.
- Nêu analytics, rollout, hỗ trợ, dependency, rủi ro và câu hỏi mở khi liên quan.
- Nếu input chưa đủ, ghi nhãn giả định và nêu câu hỏi cần giải quyết; không tự bịa chi tiết.
- Trả về Lean PRD theo
references/templates-vi.md. Với yêu cầu lớn, đề xuất phased scope hoặc MVP thay vì PRD phình to.
Trước khi kết thúc, kiểm tra rằng mỗi yêu cầu đều hỗ trợ mục tiêu hoặc một ràng buộc đã nêu.
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.
- 9d ago First seen · 18 lines · 23 tokens per session scan A e20aa1313e44
write-prd is a command published in the GitHub repository dannyhoang249-hub/pm-vietnamese-skill (1 stars, last pushed 21d ago), licensed MIT. It adds 23 tokens to every session and 279 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
plan
Sequence from done, not from the ticket.
log
Show recent git history with summary.
brain-fog-mode
Alias for foggy mode using the user's brain-fog wording.
resolve-review.body
$ARGUMENTS.
persona
Build an evidence-based persona.
checklist
Generate a custom checklist for the current feature based on user requirements.