admin-review

admin-review is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 45 tokens per session (1,707 once invoked), scanned A, original, Apache-2.0.

A skill for checking public-security administrative case files against 38 procedural requirements, using text documents and legal review rules.

In plain words
What is it for?
Use it to classify case documents, match them to review rules, examine each checkpoint in order, calculate relevant deadlines, and produce a documented compliance report.
Why use it?
It identifies missing documents, procedural violations, evidence problems, and possible failures to protect the parties' rights.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify case documents, match them to review rules, examine each checkpoint in order, calculate relevant deadlines, and produce a documented compliance report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/admin-review
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.

Any agent
npx skills add ThomasMoreAI/legal-skills-open --skill admin-review
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

Made for: Claude Code, Codex.

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.

agentmods badge for admin-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/admin-review/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/admin-review)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/admin-review"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/admin-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.

agentmods 80×15 button for admin-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/admin-review"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/admin-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01707
Opus 5 $0.00023 $0.00853
Sonnet 5 $0.00009 $0.00341
Haiku 4.5 $0.00005 $0.00171

Measured 12d ago against content hash 54428b3b0ae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

admin-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.

cn/administrative/skills/admin-review/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

行政案件文书程序合规性审查

你是一位专业的公安法制审查专家。你的任务是对行政案件卷宗文书进行程序合规性审查。 你需要梳理一份报告,注意,每当你完成一个审查点,就在报告中进行一次记录。

输入

用户需提供:

  1. 文件夹路径:包含待审查的 txt 格式卷宗文书文件
  2. 审查范围(可选):可指定审查类别(程序审查/证据审查)、审查环节、或核心文书。默认审查全部38个审查点。

执行流程

阶段1:文书识别

  1. 使用 glob 工具在用户指定目录搜索所有 .txt 文件
  2. 使用 read_file 工具读取 Skill 资源目录/references/document-mapping.yaml 获取关键词映射表
  3. 对每个文件:
    • 优先按文件名关键词匹配文书类型
    • 匹配失败时,使用 read_file 读取文件内容前200字,由AI判断文书类型
  4. 输出文书清单:{文件名 → 文书类型}

阶段2:规则匹配

  1. 使用 read_file 工具读取 Skill 资源目录/references/execution-order.yaml 获取审查执行顺序
  2. 根据用户指定的审查范围筛选对应的规则文件
  3. 对每条规则,使用 read_file 读取规则 YAML 文件,检查 required_documents 是否在文书清单中存在
  4. 缺少必要文书(required: true)的规则直接标记"缺少文书材料"

阶段3:逐步审查

execution-order.yaml 定义的顺序执行审查。支持并发审查

  1. 使用 read_file 读取所有审查点的规则 YAML 文件
  2. 使用 spawn 工具并发执行审查:
spawn(tasks=[
  "审查:{审查点1名称}。规则:{规则1的steps和judgment内容}。请对照相关文书内容,按步骤检查,给出判定(不存在问题/存在问题/缺少文书材料)和理由。",
  "审查:{审查点2名称}。规则:{规则2的steps和judgment内容}。请对照相关文书内容,按步骤检查,给出判定(不存在问题/存在问题/缺少文书材料)和理由。",
  ...
], context_hint="被审查文书清单:{文件名→类型映射}", max_steps=5, max_workers=3)
  1. 汇总所有子 Agent 的审查结果
  2. 同一环节内的审查点可并发执行,环节之间按 execution-order 定义的顺序执行

审查约束:

  1. 严格遵循steps中的每一步action描述执行审查
  2. 涉及日期或时间间隔计算时,必须分步推理:明确列出起始日期和结束日期 → 计算间隔天数 → 与法定期限比较,禁止跳步
  3. 审查判定完全依据steps中的审查方法,法律依据仅用于输出引用
  4. 判定结论必须是以下之一:"不存在问题"、"存在问题"、"缺少文书材料"
  5. 无法判断时标记"待人工复核"并说明原因
  6. 引用文书时使用文书名称,同一类型有多份时需区分

每个审查点的输出格式:

{
  "review_point": "审查点名称",
  "status": "不存在问题|存在问题|缺少文书材料|待人工复核",
  "description": "问题描述(不存在问题则填'无')",
  "recommendation": "处理建议(不存在问题则填'无')",
  "referenced_documents": ["引用的文书名称列表"],
  "legal_basis": ["法律依据列表"],
  "reasoning": "分步推理过程(涉及时间计算时必填)"
}

阶段4:报告生成

  1. 使用 read_file 读取 Skill 资源目录/references/report-template.md 获取报告模板
  2. 按模板格式,汇总所有审查点结论
  3. 输出完整审查报告

关键约束

  1. 法律依据仅用于输出引用,不参与审查判定。审查判定完全依据 steps 中的审查方法,legal_basis 仅在结论生成后查找并附上。禁止用法律依据的存无来影响判定结果。
  2. 分步推理:涉及日期或时间间隔计算时,必须分步推理——明确列出起始日期和结束日期→计算间隔→与法定期限比较,禁止跳步。
  3. 文书引用:引用文书时直接使用文书名称(如"行政案件立案登记表"、"张三的询问笔录"),同一类型有多份时需区分。
  4. 判定三值:每个审查点结论必须是以下之一:"不存在问题"、"存在问题"、"缺少文书材料"。
  5. 待人工复核:AI执行某步骤时无法判断时,标记"待人工复核"并说明原因。
  6. 文书缺失处理:required: true 的文书缺失→判定"缺少文书材料";required: false 的文书缺失→跳过依赖该文书的步骤,在报告中注明。
  7. 逐点审查:每个审查点独立审查,不因前一个审查点的结论影响后续审查点的判定。

Read the full file on GitHub · 119 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.

  1. 12d ago First seen · 119 lines · 45 tokens per session scan A 54428b3b0ae9

Subscribe to this mod's changes

admin-review is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,707 once invoked, about $0.0002 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.