A quality-review command for an iLink Story. It checks the planned work, design, code-change summary, and the actual source files against the project's review rules.

Use it to review one Story after planning, design, and coding, using the Story ID and the current usage value.

It catches missing files and problems that may be hidden when reviewing only documents. It also records review findings and uses a usage value to track the review session's resource use.

ilink-qa — Command for Claude Code by zhoubengao

Install

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.

Clone the repo

git clone --depth 1 https://github.com/zhoubengao/iLink

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/zhoubengao/ilink/ilink-qa.svg)](https://agentmods.dev/commands/zhoubengao/ilink/ilink-qa)

Your own site

<a href="https://agentmods.dev/commands/zhoubengao/ilink/ilink-qa"><img src="https://agentmods.dev/badge/commands/zhoubengao/ilink/ilink-qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,668 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01668
Opus 5	$0.00000	$0.00834
Sonnet 5	$0.00000	$0.00334
Haiku 4.5	$0.00000	$0.00167

Measured 8d ago against content hash a3ff0651223a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ilink-qa 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 8d 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.

src/.claude/commands/ilink-qa.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 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 QA（质量审查员） 角色。

参数解析

$ARGUMENTS 包含两个由空格分隔的参数：<story-id> <usage-value>。

<story-id>：本次要 QA 审查的 Story ID
<usage-value>：执行本命令前，用户在 Claude Code 中执行 /usage 查看到的"当前 session 已使用百分比"数值（仅数字，不含 % 号）

必填校验

如果 $ARGUMENTS 解析后不包含两个参数（即缺少 <usage-value>），MUST 拒绝执行，向用户输出：

❌ 缺少 usage-value 参数。请先在 Claude Code 中执行 /usage 查看"session 已用百分比"，然后以下列格式重试：

  /ilink-qa <story-id> <已用百分比数字>

例如，/usage 显示 "35%" 已用，则执行：/ilink-qa kcia-1520 35

无法查询时允许传入 0（语义为"故意跳过"，文件正常追加但 delta 标注不可信）。

允许 <usage-value> 为 0，语义为"用户故意跳过查询"。

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/qa.soul.md（QA 角色规范）

前置检查

依次读取以下文档（任一缺失则提示用户先执行对应角色）：

iLink-doc/<story-id>/<story-id>-pm.master.md（PM 文档，B4 验收标准）
iLink-doc/<story-id>/<story-id>-design.master.md（Designer 设计）
iLink-doc/<story-id>/<story-id>-code.master.md（Coder 变更摘要）

读取源码

从 code.master.md 的变更清单中提取所有文件路径，逐一读取磁盘上的实际源码文件（不是 markdown 中的代码块，而是 Coder 直接写入磁盘的文件）。

如果某个文件不存在，记录为 HIGH severity Issue（文件缺失）。

执行审查

严格按照 QA Soul 定义的五步流程执行：

第一步：消费 [REVIEW_HANDOFF]

检查 code.master.md 是否包含 [REVIEW_HANDOFF]
缺失则记录 MISSING_HANDOFF 高优先级 Issue

第二步：设计符合性审查

对照 design.master.md，逐项检查类结构、方法签名、接口实现、数据层
审查 [DEVIATIONS] 中的偏离是否合理

第三步：AC 覆盖验收

以 pm.master.md B4 验收标准为基准，逐条核对
每个 AC-ID 检查：正向场景实现、负向场景处理、测试覆盖、边界条件

第四步：代码质量审查

对照 project-context.md 中的技术约束逐项检查（如语言版本兼容性、框架约束、命名规范等）
硬约束落地验证

第五步：回流复核（仅回流时）

如果存在上一轮的 review.master.md，优先复核 [RECHECK_SCOPE] 中的 Issue
逐条验证 [FIX_RESPONSE] 的修复是否有效
检查修复是否引入新问题

输出审查报告

按照 QA Soul 定义的结构输出：

审查概述
设计符合性审查
AC 覆盖验收
结论
[REVIEW_FINDINGS]（每个问题必须有 Issue-ID / Severity / Category / Root_Cause_Layer / Evidence / Blocking）
[FIX_REQUESTS]（仅 CODER 根因的 Blocking Issue）
[UPSTREAM_BLOCKERS]（DESIGNER/UPSTREAM 根因的 Blocking Issue）
[NON_BLOCKING_NOTES]
[RECHECK_SCOPE]

将输出写入：iLink-doc/<story-id>/<story-id>-review.master.md

Metadata 印章

输出 review.master.md 时，请在文档末尾添加 Metadata 区块：

Read the full file on GitHub · 132 lines

Changes

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.

8d ago First seen · 132 lines · 0 tokens per session scan A a3ff0651223a

Subscribe to this mod's changes

ilink-qa is a command 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 1,668 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.

Code review

ilink-qa