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-bootstrapgit 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-bootstrap)<a href="https://agentmods.dev/skills/zhoubengao/ilink/ilink-bootstrap"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-bootstrap/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-bootstrap"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-bootstrap.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 | $0.05103 |
| Opus 5 | $0.00000 | $0.02551 |
| Sonnet 5 | $0.00000 | $0.01021 |
| Haiku 4.5 | $0.00000 | $0.00510 |
Grade A, and why
ilink-bootstrap 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 9d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你现在执行 iLink 的 项目 Bootstrap（冷启动） 操作。
目标：让当前项目具备运行 iLink 流水线的完整环境。执行完毕后，无论哪个 AI 平台（Claude / Codex / Qoder / Gemini）的用户打开本项目，都能被引导到 iLink 工作体系。
前置检查
步骤 1：检查 iLink 框架文件
确认以下文件存在，缺失则告知用户需要先复制 iLink 框架文件到项目：
iLink/iLink-root-spec.md（根规范）iLink/souls/universal.soul.mdiLink/souls/pm.soul.mdiLink/souls/design.soul.mdiLink/souls/coder.soul.mdiLink/souls/qa.soul.mdiLink/souls/domain.soul.md（认知模式角色规范）iLink/souls/coach.soul.md（协作认知角色规范，v1.6.0+）iLink/souls/lightme.soul.md（可选设计/需求拷问命令，v1.8.0+）
如果以上文件全部缺失，停止执行，提示用户先复制 iLink 框架。
步骤 2：检查 Command 文件
确认 .qoder/commands/ 下存在以下文件：
ilink-initilink-pmilink-designilink-coderilink-qailink-refineilink-approveilink-statusilink-domain（认知模式入口）ilink-pull（Issue System 拉取）ilink-lightme（可选设计/需求拷问命令，v1.8.0+）ilink-bootstrap
缺失时给出警告（不阻塞，因为可能使用其他平台）。
步骤 3：Soul plug 体系初始化（v1.8.0+）
本步骤自 iLink v1.8.0 引入。详见 Root Spec §4.7、Implementation Guide §1.5。
通过 Bash 工具，确保 iLink/souls/plugs/ 目录及 6 个角色空模板存在（已存在则不覆盖）：
mkdir -p iLink/souls/plugs- 对 pm / design / coder / qa / domain / lightme 六个角色，逐一检查
iLink/souls/plugs/<role>.project.plug.md是否存在 - 若不存在 → 写入 Implementation Guide §1.5.2 定义的空模板内容（含顶部 4 行注释 + 分隔线 + italic 占位说明，
<role>替换为具体角色名） - 若已存在 → SHALL NOT 覆盖（可能含项目已积累的规则）
universal.project.plug.md SHALL NOT 由 bootstrap 主动创建（由项目按需自建，参见 Root Spec §4.7.5）。
完成后在最终报告（步骤 10）中追加一行： "已确保 iLink/souls/plugs/ 下含 6 个角色 plug 模板；Leader 可按需填入项目级规则，universal.project.plug.md 按需自行创建。"
生成 project-context.md
步骤 4：检查现有 project-context.md
读取 project-context.md，如果已存在且内容完整（包含技术约束、模块职责等章节），跳到步骤 6。
如果不存在或内容为空/模板状态，执行步骤 5。
步骤 5：分析项目并生成 project-context.md
主动探索项目结构，使用 Glob/Grep/Read 工具分析：
- 项目基本信息：
- 查找
pom.xml、package.json、build.gradle、Cargo.toml等构建文件，确定技术栈 - 查找
README.md，获取项目概述 - 查找已有的
CLAUDE.md和AGENTS.md，对每个文件分别判断内容类型：- 如果是 iLink 引导（包含
iLink 协作协议关键词）→ 视为已有 iLink 配置，仅作版本检查 - 如果是手写或其他 AI 工具（Claude
/init、Qoder/init、Codex/init等）生成的项目说明文件 → 必须将其中的项目信息完整迁移到project-context.md（注意：是迁移而非引用，因为原文件将在步骤 6/7 中被替换为 iLink 薄路由，原文件会被备份） - 迁移时按照 project-context.md 的标准结构（项目概述、技术约束、模块职责、架构原则、构建测试等）重新组织内容
- 两个文件的内容可能有重叠也可能互补，MUST 合并去重后写入 project-context.md
- 如果是 iLink 引导（包含
- 查找
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.
- 9d ago First seen · 360 lines · 0 tokens per session scan A d0dba81fa4e4
ilink-bootstrap is a skill published in the GitHub repository zhoubengao/iLink (22 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,103 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…