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-check)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-design-check"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-design-check.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 | $0.00024 | $0.01519 |
| Opus 5 | $0.00012 | $0.00759 |
| Sonnet 5 | $0.00005 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
t-design-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术设计质量检查
运行时边界：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md（判断产物写入位置或脚本入口与插件默认冲突时读）
需求来源边界：${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md（区分草稿与已发布需求来源或处理两者冲突时读）
决策连续性和用户决策暴露：${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）
设计生成状态：${CLAUDE_PLUGIN_ROOT}/protocols/design-state-contract.md（校验设计 .state.json 时读）
评分维度、Clarification Gate、严重级别、报告结构与 Pass Gate：${CLAUDE_PLUGIN_ROOT}/protocols/design-check-rubric.md（评分或生成分级结论前读）
本检查为可选，不作为 /t-task 的硬性前置；质量结论只约束本次检查报告，是否跳过修复继续 /t-task 由用户按风险决定。
输入范围
- 设计主文档：
.ai/design/[feature].md - 分端设计文档（适用端必须存在）：
.ai/design/[feature]/backend.md、.ai/design/[feature]/frontend.md、.ai/design/[feature]/flutter.md - 设计生成状态：
.ai/design/[feature]/.state.json（存在时必须为complete） - 决策账本：
.ai/decision-log/[feature].md（存在时必须读取） - 需求来源：
.ai/user-stories/**/*.md、docs/user-stories/**/*.md、.ai/prd/**/*.md、docs/prd/**/*.md、.ai/tech-research/**/*.md - 规范来源：
${CLAUDE_PLUGIN_ROOT}/guides/core/environment-and-testing-guide.md${CLAUDE_PLUGIN_ROOT}/guides/core/quality.md${CLAUDE_PLUGIN_ROOT}/guides/backend/development.md${CLAUDE_PLUGIN_ROOT}/guides/frontend/development.md${CLAUDE_PLUGIN_ROOT}/guides/flutter/development.md（目标项目启用 Flutter 时）AGENTS.md
执行流程
- 校验主文档是否存在，并按主文档 §4.2 交付端范围校验适用端的分端文档是否存在。
.ai/design/[feature]/.state.json存在但状态不是complete时停止，提示先恢复/t-design [feature]。- 从设计文档提取引用的用户故事、PRD、技术预研、接口、数据库变更、各端范围、测试策略。
- 运行
python ${CLAUDE_PLUGIN_ROOT}/scripts/check-design.py ".ai/design/[feature].md" --require-complete；失败时先按结构化结果修正文档，不进入评分。 - 对主文档和全部适用分端文档运行决策闭合扫描；
needs_user_answer和澄清处理按 rubric 的 Clarification Gate 执行（先查 Decision Log，未解决时AskUserQuestion阻塞提问，回答后更新 Decision Log 和设计文档再重新扫描）。 - 核对设计文档与需求来源的一致性。设计引用
.ai/user-stories时确认其为 draft 候选来源且路径存在；同时存在相关docs/user-stories时检查是否有未说明冲突。纯技术方案可接受.ai/tech-research/[feature].md作为唯一需求来源，不得因缺少 PRD/用户故事扣 P0。 - 核对设计文档与项目规范的一致性。
- 按 rubric 的维度和 Detailed Checks 分别检查：主文档（需求追溯、跨端契约与汇总）、backend 分端（API、数据库、领域逻辑）、frontend 分端（页面、状态与数据流）、flutter 分端（分层、状态管理、导航）与测试策略。
- 评估设计方案的章节组织是否内聚：若同一业务闭环、同一数据模型或同一外部契约被拆分为多个独立章节，应在设计阶段合并，避免
/t-task产出颗粒度过细的 item；分端文档内部不得重复其他端的设计内容。 - 按 rubric 的归一化规则生成评分与问题清单，并按其 Pass Gate 输出
PASS / CONDITIONAL PASS / FAIL，不得只凭总分宣布通过。 - 输出下一步建议：通过或风险可接受时进入
/t-task [feature]；修复后可重新运行/t-design-check [feature]。 - 写入报告：
.ai/quality/design-check-[feature]-[YYYYMMDD-HHMMSS].md。
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.
- 3d ago Changed · -39 lines 746e8c8b0ea0
- 8d ago First seen · 109 lines · 24 tokens per session scan A abf2811414b4
t-design-check is a skill published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,519 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
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
workflow-runner
A procedure for running agency-orchestrator YAML workflows directly inside Claude Code, OpenClaw, or Cursor. The current AI session performs each named role, so no separate API key is needed.
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.