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 skills add Eysn0130/DeepLaw --skill research-chinese-lawgit 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/skills/eysn0130/deeplaw/research-chinese-law)<a href="https://agentmods.dev/skills/eysn0130/deeplaw/research-chinese-law"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/research-chinese-law/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/eysn0130/deeplaw/research-chinese-law"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/research-chinese-law.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 | $0.00094 | $0.01873 |
| Opus 5 | $0.00047 | $0.00937 |
| Sonnet 5 | $0.00019 | $0.00375 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
research-chinese-law 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepLaw 2.0 Chinese-Law Research
DeepLaw 2.0 is a read-only Agent legal-knowledge substrate. Use its official catalog to collect bounded, version-aware evidence. It may also read a physically separate user-private legal-reference library, but those results are user-provided and never official DeepLaw sources. Do not use either scope to decide case facts, replace legal review, or inject a general legal corpus into every conversation.
Enforce the invocation gate
Proceed only when the user explicitly invokes this skill:
- Codex:
$research-chinese-law - Claude Code:
/deeplaw:research-chinese-law - OpenCode: an explicit
@deeplawrequest that loadsresearch-chinese-law
If that gate is absent, continue the user's non-legal work without DeepLaw. Do not infer legal intent from a project name, a case existing in the workspace, or a lone domain word.
Even after explicit invocation, do not call DeepLaw for:
- application code, SQL, statistics, dashboards, or ordinary data work;
- OCR, PDF/DOCX extraction, summarization, rewriting, or translation alone;
- storing, searching, or summarizing case-private evidence or chat history;
- UI, session, SQLite, DuckDB, attachment, or project-management questions;
- a keyword that is only data, such as a
诈骗category orfraud_scorecolumn.
Use exactly one tool
Use the DeepLaw MCP tool whose leaf name is exactly law_support. Hosts may add
their own server or plugin prefix to that name. The prefix is not a second tool.
Do not use any other DeepLaw tool. If the server advertises a different leaf name or more than one tool, stop and report an adapter/runtime contract mismatch.
law_support routes thirteen read-only operations:
search: return a bounded evidence-card set;get: fetch one exact segment selected bysegment_id;verify: verify onesegment_idandreceipt_idpair;release_info: inspect the active immutable release.private_search: search only the user-private legal-reference snapshot;private_get: fetch one exact private segment;private_verify: verify one private snapshot receipt;private_info: inspect the current private snapshot;federated_context: compile separately admitted official, private, and explicitly enabled Agent-interpretation partitions under one bounded plan.capabilities: read deterministic evidence capabilities for one exactsegment_id;challenge_trace: build one bounded deterministic Authoritative Pack trace for aquery;challenge_get: fetch one exact retained trace bytrace_id;challenge_replay: replay and verify one supplied closedtrace.
What ships with it
1 file 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.
- 11d ago First seen · 153 lines · 94 tokens per session scan A af7fd2028760
research-chinese-law is a skill published in the GitHub repository Eysn0130/DeepLaw (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,873 once invoked, about $0.0005 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 skills, from other repositories
contract-guardian
A contract-review workflow that checks agreements for risks, links important findings to relevant laws, and produces a written review. It covers common agreements such as sales, leases, loans, services, contracting, and intellectual property.
法律周报
A legal-news briefing workflow that finds recent court and legal-practice articles, scores them against selected criteria, and archives chosen items in a local Obsidian notes folder. Obsidian is a local note-taking application.
legal-research
A Chinese-language legal research workflow for finding laws, regulations, court cases, compensation standards, and legal grounds.
legal-citation-comprehensive
A Chinese and foreign legal-citation tool for checking, completing, explaining, and formatting footnotes under the second edition of a legal citation manual. It handles laws, cases, legal documents, and academic sources when the relevant source material is provided.
legal-fact-checker
A Chinese-language fact-checking guide for legal documents such as contracts, case analyses, legal opinions, and legal assignments. It checks provided drafts against factual and legal support without inventing laws, cases, or facts.
workflow-overview
A workflow guide for handling complex legal matters through assessment, issue identification, source research, reasoning, fact checking, and document output.