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.
npx agentmods add skills/ryanzhao1011/workframe/technical-designnpx skills add ryanzhao1011/workframe --skill technical-designgit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00050 | $0.02176 |
| Opus 5 | $0.00025 | $0.01088 |
| Sonnet 5 | $0.00010 | $0.00435 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
technical-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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术方案设计与实施技能
产物去向
技术方案 / 实施说明默认只在响应中呈现（response-output.md：响应优先于文件写入）——
多数方案讨论完就落进代码，不需要再留一份文档。
用户明确要求存档时才落盘，归属查 skill: document-norms §1：跨模块的架构方案 →
projects/specs/plans/<YYYY-MM-DD>-<plan-name>.md；单模块的技术决策 →
projects/modules/<basic>/<sub>/decisions/。不要默认写文件，也不要写完才问。
适用场景
拿到 specs / board task 后准备开始实施时调用。涵盖代码 / 配置 / Schema / 部署的变更。
不适用：bug 调试（用 systematic-debugging）/ 代码审查（用 code-review）/ Prompt 相关（用 prompt-design）。
路径选择（轻量 vs 完整）
| 维度 | 轻量路径 | 完整路径 |
|---|---|---|
| 改动范围 | 单文件 / 配置调整 / 文档级修改 | 多文件 / 跨模块 / 架构调整 |
| 风险级别 | 低（无破坏性、不影响现有数据/接口） | 中-高（引入新依赖 / 改 Schema / 影响线上行为） |
| 数据/API | 不动 | 改 Schema / 改 API 签名 |
| 不确定性 | 需求清晰、实现路径明确 | 需要选型 / 多方案对比 / 影响面不明 |
任一维度命中"完整"列 → 走完整路径。 模糊时倾向走完整。
轻量路径（Lightweight Path）
适用：单文件 / 配置 / 文档级修改 / 小修小补。
- 快速理解：读需求 + 当前相关文件状态
- 声明假设：响应中列出 1-3 条隐含假设（如"假设这个常量没在其他地方被引用"），让用户能截停
- 直接改动 + 自测：
- Lint + 类型检查（若语言适用）
- 关键路径手动验证
- 简短交付说明：响应中 1-3 行说"改了什么 + 风险点（若有）"
轻量路径不强制等待用户确认；不强制六步流程；不固定改动顺序。
完整路径（Full Path）
适用：架构变更 / 新增依赖 / Schema 迁移 / 多文件协调 / 高风险变更。
入口前置阅读：进入完整路径前，先 Read
./reference/engineering-discipline.md（工程纪律：DRY / 副作用边界 / 异常处理 / 文档同步等），把其中的判断标准带入第 2-3 步的方案设计与风险评估。轻量路径不强制读，但若涉及架构敏感修改也建议参考。
第 1 步：需求理解
读取需求来源（projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/prd.md、task description、issue 等），提取：
- 功能范围（做什么、不做什么）
- 验收标准（AC，GWT 或规则式）
- 实质性约束（性能、安全等）——从 PRD「需求背景与目标 · 边界」与对应功能模块的就近规则提取（PRD 不设独立非功能章）
- 依赖关系（依赖哪些已有功能、外部服务）
信息不足时使用 [待确认: {说明}] 占位，严禁编造需求内容。
第 2 步：方案设计
输出完整技术方案：
| 维度 | 内容 |
|---|---|
| 涉及文件 | 新建/修改的文件清单（项目相对路径） |
| API 变更 | 新增/修改的 API 接口签名、请求/响应结构（若适用） |
| 数据结构 | 新增/修改的数据模型、字段变更（若适用） |
| 依赖关系 | 依赖的外部库、内部模块、上下游接口 |
| 技术选型 | 关键技术决策和替代方案权衡 |
第 3 步：风险评估
列出技术风险和影响面（Blast Radius）：
| 风险类型 | 具体描述 | 缓解措施 |
|---|---|---|
| 技术风险 | 新技术未经验证 / 性能瓶颈 / 并发问题 | 预研、压测、降级方案 |
| 影响面 | 改动波及哪些模块 | 回归测试范围 |
| 兼容性 | 对现有数据/接口的破坏性 | 迁移方案、版本控制 |
| 安全 | 注入、越权、数据泄露风险 | 输入校验、权限校验 |
What ships with it
1 file 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.
- 2d ago First seen · 172 lines · 50 tokens per session scan A d103394dc5fe
technical-design is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 15d ago), licensed MIT. It adds 50 tokens to every session and 2,176 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
eval-hooks
Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.