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/XRenSiu/claude-code-forgenpx agentmods add commands/xrensiu/claude-code-forge/reviewWrote 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/xrensiu/claude-code-forge/review)<a href="https://agentmods.dev/commands/xrensiu/claude-code-forge/review"><img src="https://agentmods.dev/badge/commands/xrensiu/claude-code-forge/review/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/xrensiu/claude-code-forge/review"><img src="https://agentmods.dev/badge/commands/xrensiu/claude-code-forge/review.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 | $0.01186 |
| Opus 5.5 | $0.00000 | $0.00474 |
| Sonnet 5.5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
review 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 1mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review Command
手动触发代码审查。
语法
/review [options] <path>
参数
| 参数 | 类型 | 必需 | 说明 |
|---|---|---|---|
path |
string | 是 | 要审查的代码路径（支持 glob） |
--type |
enum | 否 | 审查类型：design / spec / code / security / all (默认: code) |
--design-ref |
string | 否 | 设计参考：Figma URL 或截图/设计稿图片路径（type=design 时必需） |
--spec |
string | 否 | PRD 或规格文档路径 |
--plan |
string | 否 | 计划文档路径 |
--focus |
string | 否 | 重点关注领域（逗号分隔） |
--sha |
string | 否 | Git 提交范围 (base..head) |
使用示例
基本代码审查
/review src/auth/
对 src/auth/ 目录进行代码质量审查。
规格合规审查
/review --type spec --spec docs/prd/auth.md src/auth/
检查实现是否满足 PRD 中的所有需求。
安全审查
/review --type security --focus authentication,session src/auth/
针对认证和会话管理进行安全审查。
设计还原审查（Figma URL）
/review --type design --design-ref https://figma.com/design/abc123/MyProject?node-id=86-6167 src/views/Dashboard.vue
针对 Figma 设计稿进行视觉还原度审查。design-reviewer 会自动检测 Figma URL 并调用 Figma MCP 获取截图和设计上下文。
设计还原审查（截图/设计稿图片）
/review --type design --design-ref ./designs/homepage-mockup.png src/views/Home.vue
针对设计截图/mockup 图片进行视觉还原度审查。design-reviewer 会直接读取图片进行视觉对比。
完整审查
/review --type all --spec docs/prd/auth.md --plan docs/plans/auth.md src/auth/
依次进行设计（如有设计参考）、规格、代码、安全审查。
针对特定提交
/review --sha abc123..def456 src/
只审查两个提交之间的变更。
指定关注领域
/review --focus error-handling,performance src/services/
重点关注错误处理和性能方面。
执行逻辑
/review 命令执行流程
1. 解析参数
└── 确定审查类型、路径、关联文档
2. 预检查
├── 验证路径存在
├── 检查关联文档存在
└── 运行基本 lint/compile 检查
3. 按类型调用审查员
├── design → dispatch design-reviewer
├── spec → dispatch spec-reviewer
├── code → dispatch code-reviewer
├── security → dispatch security-reviewer
└── all → 依次调用所有适用的审查员
4. 汇总报告
└── 合并所有审查结果，生成统一报告
输出格式
## 审查结果
**审查类型**: [spec/code/security/all]
**审查路径**: [path]
**执行时间**: [timestamp]
---
### 设计审查 (如执行)
[design-reviewer 的输出]
---
### 规格审查 (如执行)
[spec-reviewer 的输出]
---
### 代码审查 (如执行)
[code-reviewer 的输出]
---
### 安全审查 (如执行)
[security-reviewer 的输出]
---
## 总结
| 审查类型 | 结果 | 关键发现 |
|----------|------|----------|
| 设计 | 🟢/🟡/🔴/⭕ | W 个问题 |
| 规格 | 🟢/🟡/🔴 | X 个问题 |
| 代码 | 🟢/🟡/🔴 | Y 个问题 |
| 安全 | 🟢/🟡/🔴 | Z 个问题 |
**总体评估**: 🟢 可以合并 / 🟡 需要小改动 / 🔴 需要大修改
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.
- 1mo ago First seen · 154 lines · 0 tokens per session scan A 5d118b393bf7
review is a command published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,186 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 2026-09-05.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).