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-design)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-design"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-design.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 | $0.00021 | $0.04715 |
| Opus 5 | $0.00010 | $0.02357 |
| Sonnet 5 | $0.00004 | $0.00943 |
| Haiku 4.5 | $0.00002 | $0.00471 |
Grade A, and why
t-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术设计文档生成
运行时边界：${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）
需求来源边界：${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md（区分草稿与已发布需求来源、处理两者并存裁决时读）
决策连续性和用户决策暴露：${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）
子 agent 调用：${CLAUDE_PLUGIN_ROOT}/protocols/subagent-dispatch.md（调度设计 agent 前 read 其对应角色规范）
设计 agent 输出：${CLAUDE_PLUGIN_ROOT}/protocols/design-agent-output-contract.md（解析 subagent 返回前读）
设计生成状态：${CLAUDE_PLUGIN_ROOT}/protocols/design-state-contract.md（写入或校验 .state.json 时读）
设计生成应保持简单、当前必需、可追溯；如果需求、spec、代码或本 skill 冲突，停止并说明冲突。
决策纪律（全文只在此声明一次，各步骤直接引用）：影响目标范围、业务规则、权限/安全边界、API 契约、数据模型、迁移/兼容性、验收标准、显著成本、风险接受或测试策略的缺口，按 Decision Exposure Gate 分类。needs_user_answer 先按 Topic 查决策账本，仍未解决时用 AskUserQuestion 提问，回答前不得把问题写成风险、待确认事项或假设后继续生成；用户回答后先更新账本，再更新对应产物。
适用范围
仅在以下场景使用：
- 用户明确要求"技术设计""方案设计""架构设计""API 设计""数据模型设计"
- 用户明确执行
/t-design [方案名称] - 已经确认这是新功能或较大能力扩展，需要正式设计文档进入 DDD 流程
不要因为用户只是问"怎么实现""大概怎么做"就自动触发本 skill。
目标
基于用户故事、PRD 草稿、已发布 PRD 基线、技术预研、用户已准备的仓库内资料和现有代码，生成可实施、可追踪、可用于 /t-task 的技术设计。/t-prd-check 是推荐的可选上游检查；未运行时，本 skill 必须自行完成关键需求来源混合验证。
设计拆分为一份主文档加按端拆分的分端设计文档；每个适用端由对应设计 subagent 生成，主会话负责编排、跨端裁决和汇总。不适用端不创建分端文档，只在主文档 §4.2 标记"不适用"及原因。
如果未传方案名称，立即终止并提示：
请提供方案名称。例如：/t-design <feature>
Input Contract
上游输入（按设计类型选择；读取顺序：先索引，再 .ai/decision / .ai/decision-log，再需求来源，最后 guides）：
- 业务功能设计：
.ai/decision/<feature>.md— 产品立项决策简报（如存在，作为 PRD 之前的方向约束）.ai/decision-log/<feature>.md— 跨阶段决策账本（存在时必须读取）.ai/prd/<domain>/<feature>.md— PRD 草稿（如存在，作为当前候选需求）docs/prd/<domain>/<feature>.md— 已发布 PRD 基线（如存在，作为正式需求基线）.ai/user-stories/**/*.md— draft 用户故事（如存在，作为当前候选需求）docs/user-stories/**/*.md— 已发布相关用户故事docs/prd/00-index.md、docs/user-stories/00-index.md— 索引
- 纯技术方案设计：
.ai/tech-research/<feature>.md— 技术预研报告，可作为唯一上游需求来源- 仅适用于不涉及业务逻辑、产品规则、用户可见流程或验收目标变动的设计
可选输入：
${CLAUDE_PLUGIN_ROOT}/guides/core/environment-and-testing-guide.md— 环境与测试指南${CLAUDE_PLUGIN_ROOT}/guides/backend/development.md— 后端开发规范${CLAUDE_PLUGIN_ROOT}/guides/frontend/development.md— 前端开发规范${CLAUDE_PLUGIN_ROOT}/guides/flutter/development.md— Flutter 开发规范（目标项目启用 Flutter 时）${CLAUDE_PLUGIN_ROOT}/guides/flutter/demo-testing.md— Android Patrol 用户故事演示规范（设计要求 Flutter Demo 时）${CLAUDE_PLUGIN_ROOT}/guides/core/quality.md— 质量规范
What ships with it
4 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.
- yesterday Changed · -113 lines 376982d0a2a2
- 6d ago First seen · 344 lines · 21 tokens per session scan A 6e2c4dc3f167
t-design is a skill published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 4,715 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-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 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。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 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.
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。.
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.