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 skills add zuoyebang/aiweave --skill design-solutiongit clone --depth 1 https://github.com/zuoyebang/aiweaveWrote 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/zuoyebang/aiweave/design-solution)<a href="https://agentmods.dev/skills/zuoyebang/aiweave/design-solution"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/design-solution/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/skills/zuoyebang/aiweave/design-solution"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/design-solution.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 | $0.00084 | $0.02468 |
| Opus 5.5 | $0.00034 | $0.00987 |
| Sonnet 5.5 | $0.00017 | $0.00494 |
| Haiku 4.5 | $0.00008 | $0.00247 |
Grade A, and why
design-solution 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
根据 $ARGUMENTS 把一句需求过一遍 design-spec/ 七大决策视角，产出技术方案(TRD)。严格按以下步骤执行。
本 Skill 是 AIWeave 的【设计类】Skill（第 5 类 · A0 设计阶段）——
design-spec/支柱的唯一执行器，位于 docs ↔ 代码生命周期的最上游。它不生成代码、不写 docs/，只产出"架构决策 + 落地索引"的 TRD；TRD 再进 A1 forward / B1 sync 落地为 docs/ 与代码。公共步骤模板见 skills-spec/01_skill_authoring_guide.md §A-§E。本 Skill 不生成业务代码，第 5 步测试同步不适用（见末尾"测试同步"）。
与 PRD→TRD 流的关系：本 Skill 聚焦"架构决策"，产出 TRD 的技术决策主体。若上游已有 PRD→TRD 流程，可把本 Skill 作为其中"架构设计"环节，把七视角结论填入既有 TRD 的对应章节，而非另起一份。
第 0 步：拒绝规则与启用检查（公共模板见 §A，本 Skill 特定填充）
- ⛔ 拒绝规则（§A.1）：需求触碰
BUILD_STATUS.md§0 中 🚫 暂不实现模块 → 立即停止 - 启用检查：读
INDEX.md§0 采纳进度——design-spec/*标 ⬜ 未启用 → 提示"本工程未启用 design-spec 决策方法论，可先启用或跳过本 Skill" - 输入完整性：需求过于模糊（无业务场景 / 无数据形态 / 无读写量级）→ 用苏格拉底式追问补齐最小决策输入：① 读多还是写多？② 数据规模量级？③ 一致性 / 延迟有无硬指标？
第 1 步：读取设计文档（公共必读见 §B）
1.1 读方法论（决策真相源）：
- design-spec/00（总纲 + 四大元方法 + 统一 lens 骨架 + §6 TRD 结构）
- design-spec/01..07（七视角：IO / 数据建模 / 并发 / 事务 / 缓存 / 稳定性 / 尾延迟与过载）
1.2 读硬规则真相源（仅被引用，过决策树时按需查）：
- docs-spec/25(IO 三铁律) / 05(Schema) / 20(并发) / 21(事务) / 06(缓存) / 12(熔断) / 22(性能) / 24(跨服务) / 27(部署)
1.3 读本工程现状：
- docs/INDEX.md §0（哪些规范已启用）+ docs/BUILD_STATUS.md（🚫 / 已实现）+ CLAUDE.md
1.4 读用户需求：$ARGUMENTS + 关联需求 / 业务文档（如有）
第 2 步：识别命中的决策视角（Skill 特定）
对需求逐一比对七视角各自的 §2 输入信号，列出命中视角清单：
| 视角 | 命中信号（摘自各 lens §2） |
|---|---|
| IO（01） | "对每个… / 同时要… / 高频读 / 高频写 / 纯追加 / 扇出调用"——只要涉及数据访问即强制命中 |
| 数据建模（02） | 新实体 / 关系建模 / 高频检索 / 数据量增长 / 海量小映射 / 字段演进 |
| 并发（03） | 共享状态 / 并行 fan-out / 后台协程 / 取消传播 / 嵌入式库并发 |
| 事务（04） | 多写聚合 / 跨数据源 / 高频数值变更 / 重试场景 / 读写混杂判定 |
| 缓存（05） | 读热点 / 计算昂贵 / 跨实例 / 一致性敏感 / 海量小映射 / 近静态小表 / 对外 ID |
| 稳定性（06） | 外部依赖 / 热路径 / 过载风险 / 多资源接入 / 凭据 / 危险开关 |
| 尾延迟与过载（07） | P99≫P50 长尾 / 高扇出取最慢 / 共享资源排队 / 过载雪崩 / 重试放大 / 冷启尾延迟 / 严格端到端 SLA |
第 3 步：逐视角过决策树产出结论（Skill 特定 / 核心）
对每个命中视角，按其 §3 决策树 → §4 默认与升级 → §5 权衡 → §6 反模式 走一遍，得出该视角的决策结论：
对每个命中视角：
① 识别需求落入该视角的哪一种【形态】（§3 决策树叶子）
② 选定【方案】：默认选最简（§4 默认列），逐条核对升级触发是否成立 → 决定是否升级
③ 记录【关键权衡】（§5 矩阵）与【规避的反模式】（§6 速查 + grep 锚）
④ 标注该结论对应的【硬规则真相源】（如 IO → docs-spec/25 §2；只引用不复制）
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 · 113 lines · 84 tokens per session scan A c3c4bd041c73
design-solution is a skill published in the GitHub repository zuoyebang/aiweave (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,468 once invoked, about $0.0003 per session on Opus 5.5. 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
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
context-exclusion
Maintain .agent-no-read.md markers for approved generated directories using deterministic scripts. Use when configuring generated-code context exclusion or restoring markers after regeneration, not for ordinary ignore rules or OS permissions.
build-executor
Execute an active direct request or approved planned change. Native continuous implementation is the default; existing legacy changes retain their recorded contract obligations.
contract-builder
Maintain an execution contract only for an existing legacy change that requires one. New direct/planned changes do not invoke this skill when a contract is absent.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.