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/zhou210712/claude-for-legal-ZHnpx agentmods add skills/zhou210712/claude-for-legal-zh/tabular-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/skills/zhou210712/claude-for-legal-zh/tabular-review)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/tabular-review"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/tabular-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/skills/zhou210712/claude-for-legal-zh/tabular-review"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/tabular-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 | $0.00146 | $0.04474 |
| Opus 5 | $0.00073 | $0.02237 |
| Sonnet 5 | $0.00029 | $0.00895 |
| Haiku 4.5 | $0.00015 | $0.00447 |
Grade A, and why
tabular-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 12d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tabular-review
- 加载
~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md→ 尽调结构、阈值、内部格式。 - 确认:什么文件、什么列、输出到哪里。
- 构建类型化模式。写入
.review-schema.yaml。与用户确认。 - 样本运行(3-5份文件)。调整模式。确认。
- 展开——每份文件一个子代理,并行。每格:值 + 状态 + 逐字引文 + 位置。
- 归一化遍。标记异常和不一致。
- 输出:
.xlsx或在线表格(询问),外加.csv+_sources.csv+ markdown 始终输出。工作成果页眉。 - 摘要:核实工作量(每列 not_present / unclear / needs_review 的计数)、标记的列、文件位置、提醒每个单元格是线索而非发现。
/corporate-legal:tabular-review
/corporate-legal:tabular-review --schema .review-schema.yaml --docs ./vdr/02-Contracts/
/corporate-legal:tabular-review --template ma-diligence
--schema <路径>: 使用已有的模式文件而非新建。用于重新运行和增量添加。
--template <名称>: 从 references/ 中的模板开始。目前有:ma-diligence。
--docs <路径>: 文件来源。本地文件夹、云文档文件夹ID或数据室路径。如省略,询问。
--output <xlsx|在线表格|csv>: 输出格式。如省略,询问。
--sample <n>: 模式检查的样本量。默认5。
事项上下文
事项上下文。 检查实务级 CLAUDE.md 中的 ## 事项工作区。如果 Enabled 为 ✗(企业法务用户的默认值),跳过本段其余内容——技能使用实务级上下文,事项机制不可见。如果已启用且无活跃事项,询问:"这是哪个事项?运行 /corporate-legal:matter-workspace switch <事项简称> 或说 实务级。"加载活跃事项的 matter.md 获取事项特定上下文和覆盖规则。输出写入事项文件夹 ~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/<事项简称>/。除非 跨事项上下文 为 开,否则绝不读取其他事项的文件。
目的
你有一摞文件和一个需要跨每份文件一致回答的问题清单。一份尽调需求清单。一次供应商合同审计。一次租赁组合审查。产出是一张表:文件为行、数据点为列,每个单元格可追溯到来源中的确切文字。
这不是问题识别。diligence-issue-extraction 找到藏在2,000份文件中的30个问题。本技能对全部2,000份文件回答同样的15个问题。两者都是合法的;它们回答不同的问题。
这也不是替代人工阅读文件。本技能产出的每个单元格是一个需要核实的线索,不是发现。输出设计为使核实更快速,而非跳过核实。
加载上下文
~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md→ 尽调结构、重要性阈值、内部格式偏好~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[代码]/deal-context.md(如处理特定交易)- 用户已有的模式文件(
.review-schema.yaml)
列类型系统
使表格审查有用的是:C列在第1行和第200行中含义相同。自由文本会产生漂移。类型保持不变。
每列有一个类型来约束答案格式:
| 类型 | 返回什么 | 用于 |
|---|---|---|
verbatim |
文件中的确切引文,逐字逐符 | 定义术语、操作性条款语言、任何文字本身重要的地方 |
classify |
来自你定义的固定列表中的一个值 | 是/否、存在/不存在、条款变体(如"须经同意"/"不得无理拒绝同意"/"未提及") |
date |
ISO 格式日期 | 生效日期、到期日、解除通知截止日 |
duration |
数字 + 单位 | 期限长度、通知期、存续期 |
currency |
数字 + 货币代码 | 上限、阈值、费用、购买价格引用 |
number |
裸数字 | 计数、百分比、页码 |
free |
简短自由文本摘要 | 少量使用——这是会漂移的类型。仅在其他类型确实不适合时使用。 |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 234 lines · 146 tokens per session scan A 7664ab0d1608
tabular-review is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 146 tokens to every session and 4,474 once invoked, about $0.0007 per session on Opus 5. 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
large-file-parquet-analysis-and-highlight
A workflow for processing large Excel workbooks by counting their rows, converting them to Parquet when needed, and finding maximum values. Parquet is a data-file format designed for efficient reading.
excel-basic-statistics-and-routing
An Excel workflow for filtering grouped data, calculating averages, extracting row ranges, removing duplicates, and adding totals.