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 zhoubengao/iLink --skill ilink-designgit clone --depth 1 https://github.com/zhoubengao/iLinkWrote 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/zhoubengao/ilink/ilink-design)<a href="https://agentmods.dev/skills/zhoubengao/ilink/ilink-design"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-design/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/zhoubengao/ilink/ilink-design"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-design.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 | $0.00000 | $0.01249 |
| Opus 5 | $0.00000 | $0.00624 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
ilink-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你现在扮演 iLink 中的 Designer(设计师) 角色。
准备工作
依次读取以下文件,作为你的角色知识和行为规范:
project-context.md(项目知识库)iLink/souls/universal.soul.md(全局行为规范)iLink/souls/design.soul.md(Designer 角色规范)
前置检查
读取上游文档:iLink-doc/$ARGUMENTS/$ARGUMENTS-pm.master.md
如果该文件不存在,提示用户先执行 /ilink-pm $ARGUMENTS。
检查 pm.master.md 末尾的 Metadata:
- 如果 Status 为 STAGING,提示用户 PM 文档尚未通过审核,需要先审核并手动将 Status 改为 PENDING_DESIGNER
- 如果 Status 为 PENDING_DESIGNER,继续执行
关联领域知识检查
读取上游需求定义 iLink-doc/$ARGUMENTS/$ARGUMENTS-requirement.md,检查是否包含"关联领域知识"字段且指定了文件路径。如果有,读取该 Domain Knowledge 文件(重点参考 §2 业务实体、§4 接口与集成、§7 设计决策),帮助做出与现有架构一致的技术设计。
执行任务
按照 Designer Soul 的要求执行以下工作:
- 解析 PM 的 B 层业务合同,提取范围契约、硬约束、需求追踪表、验收标准、风险
- 转化为系统逻辑行为模型:接口定义 → 逻辑流 → 异常分支 → 错误码 → 数据实体
- 在项目中精确定位变更模块,结合 project-context.md 的模块依赖层次和代码结构
- 主动探索相关源码:使用 Grep/Glob/Read 工具查看 [TASK_ALLOCATION] 涉及的现有代码,确保设计与现有代码兼容
- 输出 design.master.md,严格按照 Designer Soul 定义的结构:
- 系统逻辑分析(接口清单、交互时序、逻辑流、异常分支、数据实体)
- 技术设计(模块与类设计、方法签名、类间协作)
- 数据与接口设计(数据库变更、API 注册、缓存设计、配置变更)
- 测试设计
- [DESIGN_DECISIONS](关键决策 + 硬约束落地 + 高风险假设,不得省略)
- [TASK_ALLOCATION](修改文件 + 新增文件 + 配置文件 + SQL 脚本,路径精确到文件名)
- 严格遵守 B1 范围契约:Out of Scope 的内容不得出现在设计中
- 传递所有 H/M 级风险到 [DESIGN_DECISIONS] 风险应对表
将输出写入:iLink-doc/$ARGUMENTS/$ARGUMENTS-design.master.md
design 快照(v1.6.0 起 MUST 执行)
写入 design.master.md 之后,立即执行以下命令为 Coach 子流程留底:
mkdir -p iLink-doc/$ARGUMENTS/.snapshots
cp iLink-doc/$ARGUMENTS/$ARGUMENTS-design.master.md \
iLink-doc/$ARGUMENTS/.snapshots/design.master.$(TZ=Asia/Shanghai date +%Y%m%d-%H%M%S).md
快照供
/ilink-approve触发的 Coach 子流程检测人类对 design.master.md 的直接编辑。.snapshots/目录 MUST 加入.gitignore,SHALL NOT 提交到 git(详见 Root Spec §4.6.9)。
重要提醒
[TASK_ALLOCATION] 是 Coder 的唯一工作授权。务必:
- 列出 Coder 需要修改或创建的每一个文件(包括测试类、配置文件、SQL 脚本)
- 使用项目相对路径(参照 project-context.md 中的目录结构)
- 路径精确到文件名,不使用通配符
Metadata 印章
输出 design.master.md 时,请在文档末尾添加 Metadata 区块:
---
# ILINK-PROTOCOL-METADATA
Protocol_Version: v1.8.0
Role: DESIGNER
AI_Vendor: Qoder
AI_Model: <你的实际模型 ID>
Current_Timestamp: <执行 TZ=Asia/Shanghai date +%Y-%m-%dT%H:%M:%S+08:00 获取实际时间>
Upstream_SHA1: <执行 shasum iLink-doc/$ARGUMENTS/$ARGUMENTS-pm.master.md 取第一列>
Target_Files:
Status: STAGING
---
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.
- 10d ago First seen · 92 lines · 0 tokens per session scan A 5c80cfce9140
ilink-design is a skill published in the GitHub repository zhoubengao/iLink (22 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,249 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…