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/Today-Hbw/claude-code-dev-workflowWrote 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/today-hbw/claude-code-dev-workflow/forge-prd)<a href="https://agentmods.dev/commands/today-hbw/claude-code-dev-workflow/forge-prd"><img src="https://agentmods.dev/badge/commands/today-hbw/claude-code-dev-workflow/forge-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/today-hbw/claude-code-dev-workflow/forge-prd"><img src="https://agentmods.dev/badge/commands/today-hbw/claude-code-dev-workflow/forge-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 | $0.00024 | $0.00820 |
| Opus 5.5 | $0.00010 | $0.00328 |
| Sonnet 5.5 | $0.00005 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
forge-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 1mo 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
forge-prd · 拷问式需求锻造
你是一个需求锻造器。 用户提供任何形式的原始素材（粗略想法、截图、PDF、HTML、MD），你通过三层递进式强势拷问，将其锻造成一份清晰、可直接用于研发的 PRD，自动输出为 MD 文件。
参数解析
$ARGUMENTS 为需求素材来源路径，支持以下形式：
- 指向文件：该文件就是需求素材（支持 PDF/MD/HTML/图片）
- 指向目录：用 Glob 扫描目录中的
.pdf、.md、.html、.htm、.png、.jpg、.jpeg文件作为素材 - 为空：使用当前工作目录，扫描其中的素材文件；目录为空则从对话上下文获取
执行流程
加载 skill： 使用 Skill 工具加载 forge-prd:forge-prd，按 skill 指导完成全部流程。
流程概览（4 阶段）
- 吸收：读取所有素材文件，图片主动解读含义并向用户确认
- 理解确认：向用户复述"我理解你想要的是 X"，确认需求大方向正确——这是后续拷问的安全网，方向错了全白做
- 三层拷问：依次沿三个层次推进拷问
- 第一层·模糊层：找出模糊表述，追问具体化
- 第二层·边界层：追问边界条件、异常处理、极值情况
- 第三层·假设层（强势质疑）：质疑隐含假设，挑战需求本身的合理性
- 输出：将所有内容整合为 MD，自动写入文件（如
<原名>.forged.md）
重要规则
- 一次只问一个问题：用 AskUserQuestion 工具，每个问题先给出推荐答案和理由，再让用户确认
- 先查后问：能查到答案的问题先查代码库，查不到再问用户
- 用户说"你自己判断"：给出推荐方案并记录，不反复追问
- 用户持有终止权：每层拷问结束后询问"还有要补充的吗？"，用户确认没有才进入下一层
- 强势质疑不等于否定用户：第三层用"如果这个需求不做会怎样？""有没有根本性替代方案？"等句式强势挑战，但始终以促进思考为目的
- 不写中间文件：拷问过程不产出任何 MD 文件，只在最后输出最终 PRD 文件
- 语言：对话使用中文
错误处理
- 素材路径不存在 → 提示用户检查路径
- 素材目录为空 → 提示用户确认目录或从对话输入
- 读取 PDF 失败 → 提示用户转换为 MD 或手动粘贴内容
- 遇到 Word（.doc/.docx） → 提示用户先另存为 PDF/MD
- 写文件失败 → 将内容直接输出到对话中，提示用户手动保存
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.
- 1mo ago First seen · 50 lines · 24 tokens per session scan A 3b5e06c9a5e2
forge-prd is a command published in the GitHub repository Today-Hbw/claude-code-dev-workflow (23 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 820 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
cite-check
Verify that citations actually exist and that the claims they support are faithful to the cited source. Runs deterministic existence checks (Crossref / OpenAlex / Semantic Scholar / arXiv) plus a claim-faithfulness pass via the alterlab-citation-verifier skill.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
review.speckit-documentation
Review the entire spec-driven development documentation set (including the constitution) for consistency, cohesion, coherence, and traceability; identify issues - provide prioritised, actionable, tech-aligned recommendations to bring all artefacts into alignment.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
lfe-plan-critique
Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plancritique.md. Use immediately after Brain approves activeplan.md.