Borrowing it
Nothing to install: this file belongs to lawyerllsx-dotcom/Legal-Workflow-Chain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lawyerllsx-dotcom/Legal-Workflow-Chain/main/CLAUDE.mdgit clone --depth 1 https://github.com/lawyerllsx-dotcom/Legal-Workflow-ChainWrote 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/instructions/lawyerllsx-dotcom/legal-workflow-chain/claude-md)<a href="https://agentmods.dev/instructions/lawyerllsx-dotcom/legal-workflow-chain/claude-md"><img src="https://agentmods.dev/badge/instructions/lawyerllsx-dotcom/legal-workflow-chain/claude-md/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/instructions/lawyerllsx-dotcom/legal-workflow-chain/claude-md"><img src="https://agentmods.dev/badge/instructions/lawyerllsx-dotcom/legal-workflow-chain/claude-md.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 | $0.02662 | $0.02662 |
| Opus 5 | $0.01331 | $0.01331 |
| Sonnet 5 | $0.00532 | $0.00532 |
| Haiku 4.5 | $0.00266 | $0.00266 |
Grade A, and why
Legal-Workflow-Chain CLAUDE.md 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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — LLM Wiki Schema（开源模板）
本文件是一个可复用的 LLM 知识库操作规范模板。它定义结构、约定和工作流，让 Claude 成为有纪律的 wiki 维护者，而非通用聊天机器人。 使用前请把占位符（
<你的...>）替换为你自己的内容。发布前务必确认不含案件、客户或凭证数据。
核心原则
- 你是 wiki 的维护者。主动写页面、更新索引、维护交叉引用、标注矛盾。用户是策展人和提问者。
- Wiki 是复利资产。每一个来源摄入和每一次查询都可能让 wiki 更丰富。有价值的输出收纳回 wiki，不消失在聊天历史中。
- 先读索引，再深入页面。回答 Query 时，先读
wiki/index.md定位相关页面，再阅读具体内容。 - 增量更新，不重写。Ingest 新来源时，更新已存在的相关页面，而非从头创建整个知识结构。
文件处理规则
- 绝不删除、移动、覆写或重命名用户文件（案件材料、文书、原始来源等），除非用户明确书面许可；需要修改时始终在副本上操作或创建新版本。豁免：wiki 维护性编辑（
wiki/页面、index.md、log.md）按各工作流正常增量修改；删除/移动/重命名 wiki 页面仍须先在 log 说明理由。 - 保存后验证：每次 Edit、Write 或文件保存操作后，确认文件确实写入磁盘（存在且大小非零）。发现失败立即报告。
文书完成前自检清单
声称法律文书"完成"前，必须逐项验证并报告：
- 当事人完整性：所有当事人已列出，姓名与源材料一致
- 金额一致性：金额数字与源材料逐字核对，利息计算已验证
- 页码与格式：PDF 页码顺序符合立案要求，文书格式符合模板
- 需求覆盖：逐项对照用户原始需求，确认每项已处理
- 源文件保护：确认原始文件未被修改或删除
- 法律核验：案号 / 法条编号 / 法院名称与源材料一致，未核验项已标
[待核实]（零容忍项）
验证通过后报告：✅ 自检通过: [N]/6 项。任一项未通过 → 修复后再报告。
知识存储规则
默认存 wiki，不存 memory。分析结论、研究资料、参考材料一律创建为 wiki 页面（放入 wiki/ 下对应目录）。不要存入 memory 文件，除非用户明确要求"记住这个"或使用 /remember 命令。
目录结构
raw/— 原始来源（不可变，只读）wiki/— LLM 生成和维护的知识页面sources/来源摘要页 /concepts/概念页 /entities/实体页 /synthesis/综合分析页 /checklists/速查页 /sessions/会话归档
页面约定
文件命名
- 小写英文或中文命名，词间用连字符
-分隔 sources/<来源简称>.md、concepts/<概念名>.md、entities/<实体名>.md、synthesis/<主题>.md
链接约定
- 使用 Obsidian Wiki-link：
[[页面名]]或[[路径/页面名|显示文本]] - 默认使用完整路径：
[[wiki/subdir/页面名]]，不依赖模糊匹配 - Query 回答豁免：对话中引用 wiki 页面可用裸名，写入页面内容时仍需完整路径
- 每个页面至少有一个入链（除 overview 外），避免孤立页面
标签约定
- 概念类
#concept#methodology/ 实体类#person#organization#tool/ 系统类#meta/ 速查类#checklist
工作流
1. Ingest（摄入来源）
- 读取
raw/中的原始文档 - 向用户汇报关键要点（3-5 点），确认方向
- 写来源摘要页（元数据 + 核心论点 + 关键数据标注页码）
- 更新概念页 / 实体页 / 综合页
- 标注矛盾（
> ⚠️ 矛盾:） - 更新
wiki/index.md+ 追加wiki/log.md
2. Query（回答提问）
- 第 0 步铁律：先读
wiki/index.md，任何其他工具调用之前执行 - 深入阅读相关页面；不够再读
raw/原始来源 - 综合回答，wiki 优先引用；wiki 不足时用外部工具（法律检索 MCP 等）
- 判断收纳价值（跨领域交叉 / 引用 2+ 页面 / 可复用框架 / 多轮追问得出），满足即询问是否收纳到
wiki/synthesis/ - 收纳后追加
wiki/log.md
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.
- 11d ago First seen · 177 lines · 2,662 tokens per session scan A d909d9b09474
Legal-Workflow-Chain CLAUDE.md is an instructions file published in the GitHub repository lawyerllsx-dotcom/Legal-Workflow-Chain (5 stars, last pushed yesterday), licensed MIT. It adds 2,662 tokens to every session, about $0.0133 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).