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-refinegit 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-refine)<a href="https://agentmods.dev/skills/zhoubengao/ilink/ilink-refine"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-refine/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-refine"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-refine.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 | $0.01044 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
ilink-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你现在执行 iLink 的 STAGING 修订对话(ilink-refine) 操作。
准备工作
依次读取以下文件:
project-context.mdiLink/souls/universal.soul.mdiLink/iLink-root-spec.md§6.3(ilink-refine 修订协议)
步骤 1:确认 Story 存在
检查 iLink-doc/$ARGUMENTS/ 目录是否存在,不存在则提示用户先执行 /ilink-init $ARGUMENTS。
步骤 2:识别 STAGING 文档
按优先级依次检查以下文档的 Metadata Status:
iLink-doc/$ARGUMENTS/$ARGUMENTS-review.master.mdiLink-doc/$ARGUMENTS/$ARGUMENTS-design.master.mdiLink-doc/$ARGUMENTS/$ARGUMENTS-pm.master.md
找到第一个 Status 为 STAGING 的文档,即为本次修订目标。
如果没有找到 STAGING 文档,告知用户当前 Story 无需修订,建议执行 /ilink-status $ARGUMENTS 查看状态。
步骤 3:加载上下文,进入修订模式
根据 STAGING 文档的角色,读取对应 Soul 文件:
- pm.master.md →
iLink/souls/pm.soul.md - design.master.md →
iLink/souls/design.soul.md - review.master.md →
iLink/souls/qa.soul.md
读取完整的 STAGING 文档内容。
进入修订模式:你的职责是"定点修改",不是"重新生成"。
步骤 4:汇总阻塞项
根据文档类型,找到所有阻塞项:
| 文档 | 阻塞项位置 |
|---|---|
| pm.master.md | B5 中的 [待确认] 项 + C1 的 NOTIFY_ITEMS |
| design.master.md | [DESIGN_DECISIONS] 中高风险项的 [待确认] 标记 |
| review.master.md | [UPSTREAM_BLOCKERS] 中的所有条目 |
以列表形式逐条呈现给用户,格式示例:
检测到 STAGING 文档:$ARGUMENTS-pm.master.md
共 N 个阻塞项需要决策:
1. [B5-风险-1] 第三方支付回调超时处理方式未确认
当前标记:[待确认]
风险等级:H
2. [B5-风险-3] 并发场景下的幂等方案
当前标记:[待确认]
风险等级:M
请针对第 1 项给出决策:
步骤 5:逐条决策
每次只呈现一项,等待用户给出决策后:
- 将
[待确认]更新为[已确认 <YYYY-MM-DD>: <用户给出的决策依据>] - 根据决策内容调整风险等级(H → M 或 M → L)
- 使用 Edit 工具就地更新文档对应位置
- 明确告知用户:"已更新第 X 项"
- 继续呈现下一项
修订模式约束(MUST 严格遵守):
- MUST 保留文档所有已有内容,仅更新被讨论的阻塞项
- SHALL NOT 重新生成整个文档
- SHALL NOT 修改未被讨论的条目
- MUST 在每次修改后明确告知用户已更新的条目编号
步骤 6:清理 NOTIFY_ITEMS(仅限 pm.master.md)
每确认一项后,从 C1 的 NOTIFY_ITEMS 列表中移除对应条目。
所有 NOTIFY_ITEMS 条目均被确认后,写入 NOTIFY_ITEMS: NONE。
步骤 7:清理阻塞项(不修改 Status)
所有阻塞项处理完毕后:
- 若所有
[待确认]项已消解 → 移除文档中残留[待确认]标记,更新 B5/C1 中的风险标记 - 若仍有未解决的 H 级项 → 维持文档 STAGING 状态不变
注意:
ilink-refine只修订文档内容,不修改 Status。状态推进由ilink-approve统一负责。
使用 Edit 工具就地更新文档中被讨论的条目。
步骤 8:提示下一步
修订完成。所有阻塞项已消解。
下一步:执行 `/ilink-approve $ARGUMENTS` 正式推进流水线。
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 · 103 lines · 0 tokens per session scan A 9af1d0593d64
ilink-refine 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 1,044 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…