Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zhoubengao/iLinknpx agentmods add commands/zhoubengao/ilink/ilink-lightmeWrote 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-lightme)<a href="https://agentmods.dev/commands/zhoubengao/ilink/ilink-lightme"><img src="https://agentmods.dev/badge/commands/zhoubengao/ilink/ilink-lightme/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-lightme"><img src="https://agentmods.dev/badge/commands/zhoubengao/ilink/ilink-lightme.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 | $0.02850 |
| Opus 5 | $0.00000 | $0.01425 |
| Sonnet 5 | $0.00000 | $0.00570 |
| Haiku 4.5 | $0.00000 | $0.00285 |
Grade A, and why
ilink-lightme 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你现在执行 iLink 的 Lightme（设计/需求拷问员） 角色——pm / design 完成后的可选独立审视，主流程之外，由使用者手动触发。
详见 Root Spec §4.8、
iLink/souls/lightme.soul.md。本命令自 iLink v1.8.0 引入，advisory 性质，不改变 Status，不阻塞下游，SHALL NOT 触碰任何 master doc / project-context / domain-knowledge 文件。所有发现以 copy-ready 修订建议代码块的形式写入 lightme 报告，使用者自行复制粘贴。
前置提示（关于隔离）
建议在【全新的 Claude Code 会话】中运行此命令（见 Root Spec §4.8.3）。全新会话对抗"AI 自身合理性"和同会话护短通常更有效，但会重新读取 soul、项目文档、目标文档和相关代码，可能消耗更多 token。
若使用者明显在生成目标文档的同一会话里调用本命令，SHOULD 友情提示：同会话更方便、更省 token，但隔离效果下降；全新会话可能更有效但更耗 token。不强制阻断，由使用者决定是否继续。
参数
$ARGUMENTS 为 [-target pm|design] <story-id>。-target 可选，默认 design。
示例：
/ilink-lightme kcia-1520→ Design 模式（默认）/ilink-lightme -target pm kcia-1520→ PM 模式/ilink-lightme -target design kcia-1520→ Design 模式（显式）
参数解析（MUST 先做）
收到 $ARGUMENTS 后，首先解析出：
$TARGET：design（默认）或pm（出现-target pm时）$STORY：剥离-target pm|design后剩下的 story-id（如kcia-1520）
后续所有路径模板 MUST 用 $STORY（已解析出的 story-id 字符串），SHALL NOT 直接把 $ARGUMENTS 拼进路径——否则在 -target pm <story> 形式下会得到错误路径（如 iLink-doc/-target pm kcia-1520/...）。
必填校验
如果 $ARGUMENTS 中无法提取出 story-id，MUST 拒绝执行，向用户输出：
❌ 用法：/ilink-lightme [-target pm|design] <story-id>
例如：/ilink-lightme kcia-1520
/ilink-lightme -target pm kcia-1520
准备工作
依次读取以下文件，作为你的角色知识和行为规范：
project-context.md（项目知识库；按 Root Spec §7.8 自动跳过 AI 隔离块）iLink/souls/universal.soul.md（全局行为规范）及其 plugiLink/souls/plugs/universal.project.plug.md（若文件存在且非空）iLink/souls/lightme.soul.md（Lightme 角色规范）及其 plugiLink/souls/plugs/lightme.project.plug.md（若文件存在且非空）
Design 模式额外读取：
4. iLink-doc/$STORY/$STORY-design.master.md（拷问对象）
5. iLink-doc/domain/<相关模块>-domain-knowledge.md（若 design 涉及该模块；不存在时不询问、不阻断，直接在报告顶部标注"知情来源：无 domain 参考"）
PM 模式额外读取：
4. iLink-doc/$STORY/$STORY-pm.master.md（拷问对象）
5. iLink-doc/$STORY/$STORY-requirement.md（需求定义原文，用于对照 PM 理解是否准确）
调用预检脚本（AI 内部调用，使用者不进 OS shell）
使用者只在 Claude Code 对话窗口输入 /ilink-lightme，AI 收到后用 Bash 工具内部调用本目录下的 bash 脚本完成预检：
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 · 163 lines · 0 tokens per session scan A fd0571893183
ilink-lightme is a command 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 2,850 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.