Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add timzaak/web-dev-skills/plugin install t-toolsWrote 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/timzaak/web-dev-skills/t-prd)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-prd"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-prd.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.03255 |
| Opus 5 | $0.00009 | $0.01628 |
| Sonnet 5 | $0.00003 | $0.00651 |
| Haiku 4.5 | $0.00002 | $0.00326 |
Grade A, and why
t-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 草稿维护
运行时边界：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md（判断产物写入位置或项目事实与插件默认冲突时读）
决策连续性和用户决策暴露：${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md（提问、更新决策账本或处理决策暴露门禁时读）
若本 skill、spec 或既有文档之间冲突，停止、说明冲突并等待澄清；不要平均折中。
目标
基于 Decision Brief、现有 user story、正式 PRD、已有 PRD 草稿和用户补充信息，先补齐必要的 draft user story，再创建或更新一份 PRD 草稿，供人类快速审阅。.ai/prd 和 .ai/user-stories 是实现前和实现期间的临时候选需求工作区，不是长期权威源。
输出文件：
.ai/prd/<domain>/[feature].md— PRD 草稿，至少包含：相关用户故事引用、范围界定、需求概述、业务规则与状态、功能需求与验收目标、API 相关约束 / 前端交互约束（各标明适用或不适用）、已确认决策及 Decision ID、参考资料.ai/user-stories/<domain>/[feature].md— draft user story，按需新增或补齐.ai/decision-log/[feature].md— 存在，或产生用户决策、问题状态变化或重要 AI 决策时创建或更新
参数要求
[feature]必须是 feature 名称；文件名仅允许英文、数字、空格、下划线、连字符- 缺失或非法时终止并提示参数格式
核心约束
路径与域：
<domain>只能是auth、billing、core、integration；父目录缺失且目标域已明确时才创建对应.ai/子目录/t-prd不写入docs/prd/和docs/user-stories/- PRD、用户故事和技术预研的读取与写入边界统一参考
${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
PRD 内容边界：
- 聚焦产品边界与规则，不承载接口 schema、数据库建表或技术方案
- 可以写：接口能力范围、访问控制原则、租户/realm 边界、兼容性要求、前端页面入口、关键交互、状态反馈约束
- 禁止写：具体端点（
GET/POST /api/...）、请求/响应参数表、HTTP 状态码列表、数据库表结构/迁移方案、Rust/TypeScript 类型定义
更新行为：
- 已有同名草稿 → update 路径，以草稿为基底逐章更新
- 无草稿但有同名正式 PRD → draft-from-published 路径，以正式 PRD 为基线创建草稿，不覆盖正式 PRD
- 无草稿且无正式 PRD → create 路径，使用 template.md
- 已有同名 draft user story 文件 → 追加到合适章节，不重建
user story 引用：
- PRD 只引用相关用户故事（ID、标题、优先级、来源文件），不复制完整验收文本
- 已发布 user story 足够覆盖时，PRD 可直接引用
docs/user-stories/... - 缺少或需要补齐的本轮用户故事写入
.ai/user-stories/<domain>/<feature>.md；draft user story 可以按角色分组组织在同一 feature 文件中
提问与澄清门禁
写入 PRD 草稿前必须完成轻量澄清门禁。运行时维护临时 PRD Grill Snapshot（澄清工具，不是交付物，不写入 PRD 正文）：
PRD Grill Snapshot
- Problem statement: [一句话说明要解决的问题或目标能力]
- Success criteria: [可验收的成功信号，至少 1 条]
- Facts: [来自现有文档、代码、tech research 或当前对话的事实]
- Confirmed decisions: [用户已确认的产品决策]
- Open questions: [仍阻塞 PRD 的判断题]
提问纪律：
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -105 lines c88f3e2ab12f
- 6d ago First seen · 277 lines · 17 tokens per session scan A 54b249e26fa6
t-prd is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 3,255 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 2026-08-30.
Other skills, from other repositories
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
executing-plans
当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用.
workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。.