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.
npx agentmods add instructions/eysn0130/deeplaw/agents-mdgit clone --depth 1 https://github.com/Eysn0130/DeepLawWrote 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/eysn0130/deeplaw/agents-md)<a href="https://agentmods.dev/instructions/eysn0130/deeplaw/agents-md"><img src="https://agentmods.dev/badge/instructions/eysn0130/deeplaw/agents-md.svg" alt="Measured on agentmods" 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 | $0.03701 | $0.03701 |
| Opus 5 | $0.01851 | $0.01851 |
| Sonnet 5 | $0.00740 | $0.00740 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
DeepLaw AGENTS.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 3d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepLaw Repository Guide
This file contains durable, repository-wide instructions for agents working on DeepLaw. It is an
execution guide, not the complete product specification. Keep it concise. Put subsystem-specific
rules in the nearest relevant documentation or a nested AGENTS.md; a nested file governs only its
subtree and may refine this guide.
Product Definition
DeepLaw is a local-first Agent Knowledge OS that compiles source materials into a governed Living Wiki and returns verifiable, bounded knowledge context to any Agent.
DeepLaw is a Source-to-Knowledge Compiler. It preserves source identity and evidence, compiles sources into durable, typed, governed, and evolvable Knowledge Objects, projects those objects into a Living Wiki that humans and Agents can use, and selects a small verified Knowledge Capsule for the task at hand.
DeepLaw is not:
- a generic RAG or document-chunk search application;
- a Markdown converter or note-taking tool;
- an Obsidian replacement;
- a law-only question-answering system or legal adjudicator;
- a memory plugin for one Agent;
- an Agent runtime, model host, conversation orchestrator, or general tool executor;
- a remote canonical database, multi-tenant SaaS, or team control plane.
The Legal Pack is a first-party governed domain of the broader Knowledge OS, not the definition of the whole product. DeepLaw may serve Codex, Claude Code, OpenCode, and other explicitly integrated Agent hosts without transferring model, session, or general tool ownership to DeepLaw.
Core Entry Points
- The
deeplawCLI is the first-party owner and operator interface. It remains a core product surface even if a GUI is added. - MCP is the first-party Agent interface. It remains a core product surface alongside the CLI.
- A future GUI must be a client of the same domain services. It must not become the sole control plane or introduce a second implementation of persistence, governance, retrieval, or mutation.
- Markdown, YAML frontmatter, Wikilinks, Obsidian, Tolaria, and JSON Canvas are open human/Agent work surfaces. They do not independently establish identity, Authority, or permission.
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.
- 3d ago First seen · 322 lines · 3,701 tokens per session scan A e8d14f80295a
DeepLaw AGENTS.md is an instructions file published in the GitHub repository Eysn0130/DeepLaw (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,701 tokens to every session, about $0.0185 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
Legal-Workflow-Chain CLAUDE.md
Instructions for lawyerllsx-dotcom/Legal-Workflow-Chain, covering claude.md — llm wiki schema（开源模板）, 核心原则, 文件处理规则, 文书完成前自检清单 and 知识存储规则.
Legal-Agent-Skills CLAUDE.md
Instructions for code-lawyer/Legal-Agent-Skills, covering claude.md, 本仓库是什么, 先读：作者宪章（principles.md）, 常用命令 and 结构校验——改动任一 skill 的 references/ 或 rules/ 后必跑，绿了才提交.
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Gemini CLI instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.