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.
git 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/commands/zhoubengao/ilink/ilink-bootstrap)<a href="https://agentmods.dev/commands/zhoubengao/ilink/ilink-bootstrap"><img src="https://agentmods.dev/badge/commands/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/commands/zhoubengao/ilink/ilink-bootstrap"><img src="https://agentmods.dev/badge/commands/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 | $0.06077 |
| Opus 5.5 | $0.00000 | $0.02431 |
| Sonnet 5.5 | $0.00000 | $0.01215 |
| Haiku 4.5 | $0.00000 | $0.00608 |
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 2mo 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 — 412 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(设计/需求拷问员角色规范,v1.8.0+,启用/ilink-lightme时 MUST)
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 .claude/commands/ 下存在以下文件:
ilink-init.mdilink-pm.mdilink-design.mdilink-coder.mdilink-qa.mdilink-refine.mdilink-approve.mdilink-status.mdilink-domain.md(认知模式入口)ilink-pull.md(Issue System 拉取入口 AI 薄壳)ilink-pull.sh(Issue System 拉取 bash 脚本本体;由 ilink-pull.md 调用)ilink-lightme.md(设计/需求拷问员入口 AI 薄壳,v1.8.0+)ilink-lightme.sh(设计/需求拷问员 bash 预检脚本,v1.8.0+;由 ilink-lightme.md 调用)
缺失时给出警告(不阻塞,因为可能使用其他平台)。ilink-pull.sh 缺失时除 warn 外还要提示用户:缺该脚本则 /ilink-pull 不可用,但其他流水线命令不受影响。ilink-lightme.* 缺失时同样 warn 并提示:缺则 /ilink-lightme 不可用,但其他流水线命令不受影响。
注意:v1.6.0 起
ilink-approve.md升级为含 Coach 子流程的 Slash Command(Coach 不需要单独的ilink-coach.md)。
Soul plug 体系初始化
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。"
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.
- 2mo ago First seen · 412 lines · 0 tokens per session scan A 7c9041a2bef4
ilink-bootstrap is a command published in the GitHub repository zhoubengao/iLink (23 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,077 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.
ilink-bootstrap compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ilink-bootstrapzhoubengao/iLink | Command | 23 | 4mo ago | Apache-2.0 | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |