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/Yoruto/prd-kitWrote 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/rules/yoruto/prd-kit/prd-workflow)<a href="https://agentmods.dev/rules/yoruto/prd-kit/prd-workflow"><img src="https://agentmods.dev/badge/rules/yoruto/prd-kit/prd-workflow/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/rules/yoruto/prd-kit/prd-workflow"><img src="https://agentmods.dev/badge/rules/yoruto/prd-kit/prd-workflow.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 | $0.00000 | $0.01029 |
| Opus 5.5 | $0.00000 | $0.00412 |
| Sonnet 5.5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
prd-workflow 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
PRD 转实现工作流
当用户要求「根据 PRD 实现」「实现此功能」或正在编辑 config/PROJECT.md 所描述的 PRD 目录下的文档时,按以下步骤执行。总规则见 00-prd-kit.mdc 与项目 config/PROJECT.md。
Globs 说明:本文件默认匹配
docs/prd/**/*.md。若你项目的 PRD 根路径不同,请同时修改本文件头部的globs与config/PROJECT.md中的 PRD 目录。
无 Stack Profile 时:项目未从本工具包复制任何
examples/<stack>/的架构/命名 mdc 时,PRD 必须自行写明文件路径、模块划分、命名与验收标准;仅依赖本工作流 + 通用项目配置。
Composer / 自动模式
- 在 Composer 中 @ 对应 PRD(如
@docs/prd/active/xxx.md),并 @00-prd-kit.mdc与本prd-workflow.mdc;若已启用 profile,@ 对应framework/ 命名等 mdc(以你.cursor/rules/中实际文件名为准)。 - 用户开启高自主执行时:仍先列出将创建/修改的文件清单(可一段话),再执行;若 PRD 缺验收标准或关键行为,先补问或补写 PRD,不要凭空虚构业务规则。
- 涉及编辑器/资源绑定/场景与脚本关联等工具链专属步骤时,在说明中提醒用户在对应 IDE 中人工确认(例如游戏引擎中场景与脚本的引用)。
1. 分析阶段
1.1 阅读 PRD
- 理解目标与验收标准。
- 识别涉及的模块/场景/子系统。
- 明确新增/修改的文件清单与依赖。
1.2 检查规范
- 阅读
config/PROJECT.md中的技术栈、验证命令、补充架构链接。 - 若已启用 Stack Profile:阅读对应 架构 与命名/分层 规则;识别仓库内相似实现作参考。
1.3 列出文件清单
向用户确认,例如:
将创建以下文件:
- path/to/new/module_a.ext
- path/to/new/module_b.ext
将修改以下文件:
- path/to/existing/file.ext
确认后开始实现。
2. 实现阶段
- 严格遵守
config/PROJECT.md与已启用的 Stack Profile;二者与 PRD 冲突时,先向用户确认。 - 无 profile 时:以 PRD 中给出的路径、数据结构与风格为准,并与现有代码库风格对齐。
- 不引入 PRD 未要求的跨模块副作用;需要新增系统级能力时,先与用户对齐。
3. 验证阶段
3.1 自检
根据 PRD 验收条 与 profile/团队约定 做静态检查(类型、风格、安全相关约束等,依项目而定)。
3.2 执行验证
- 运行
config/PROJECT.md中列出的构建/测试/检查命令,并记录结果。 - 无自动化命令时,说明已完成的手动物理步骤与结论。
4. 禁止事项(通用)
- 不要为「省事」在 PRD 外发明业务规则或数据契约。
- 不要混用与团队约定/ profile 相冲突的命名与分层(若 profile 有定义)。
- 不要省略「将改动哪些文件」的确认,除非用户明确允许直接改。
5. 报告格式
实现完成后,向用户报告,例如:
功能实现完成
已创建文件:
- `path/a`
- `path/b`
已修改文件:
- `path/c`
验证结果:
- 命令/步骤:…
- 结果:通过 / 未通过(说明原因)
后续建议(若有):
- 人工在 IDE/产品内验证的条目
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 · 93 lines · 0 tokens per session scan A c81b92ca3307
prd-workflow is a cursor rule published in the GitHub repository Yoruto/prd-kit (1 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,029 tokens. 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 cursor rules, from other repositories
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.