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 StefanCHEN2026/foreign-law-research-skill- --skill foreign-law-researchgit clone --depth 1 https://github.com/StefanCHEN2026/foreign-law-research-skill-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.
[](https://agentmods.dev/skills/stefanchen2026/foreign-law-research-skill-/foreign-law-research)<a href="https://agentmods.dev/skills/stefanchen2026/foreign-law-research-skill-/foreign-law-research"><img src="https://agentmods.dev/badge/skills/stefanchen2026/foreign-law-research-skill-/foreign-law-research/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/stefanchen2026/foreign-law-research-skill-/foreign-law-research"><img src="https://agentmods.dev/badge/skills/stefanchen2026/foreign-law-research-skill-/foreign-law-research.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 | $0.00219 | $0.06067 |
| Opus 5.5 | $0.00088 | $0.02427 |
| Sonnet 5.5 | $0.00044 | $0.01213 |
| Haiku 4.5 | $0.00022 | $0.00607 |
Grade A, and why
foreign-law-research 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 7d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foreign Law Research & Ascertainment Skill
This skill guides lawyers and legal professionals through the systematic ascertainment of foreign law (statutes, case law, and international treaties of any jurisdiction outside mainland China). Version 2.0 aligns the whole workflow with the evidentiary standards applied by PRC courts — modeled on the Shanghai Financial Court's Guidelines on the Ascertainment of Foreign Law (2025) and the SPC judicial interpretations of the Law on the Application of Laws to Foreign-Related Civil Relations — so that research output is ready for submission and cross-examination in court: an Ascertainment Opinion plus a Research Log.
Data layer: 121 free legal databases plus an open-source data layer (git-versioned law corpora, open legal data collection scripts, and MCP servers).
Overview
Ascertaining foreign law is more than "finding the provision". In PRC cross-border practice, an ascertainment result must survive cross-examination and judicial review (Guidelines Art. 14): authenticity of the text, validity status, relevance to the dispute, and completeness of the search. This skill organizes the work as Scoping → Six research steps → Dual deliverables:
Step 0 Scoping ───────────┐
Step 1 Identify jurisdiction │
Step 2 Map sources of law │ Research
Step 3 Identify instruments │ (log as you go)
Step 4 Locate specific rules │
Step 5 Quality assurance ───┘
Step 6 Deliver ──→ Ascertainment Opinion (six-part structure)
Research Log (search audit trail)
AI-tool disclosure (tools / stages / human verification)
Reference map
Four reference files support the workflow. Consult them on demand:
| File | Purpose | When to read |
|---|---|---|
references/database-index.md |
121 free legal databases by jurisdiction, three authority tiers | After Step 1, to pick research databases |
references/open-source-data.md |
Open-source data layer: git law corpora, collection scripts, MCP servers | When you need version history, validity verification, bulk endpoints, or a jurisdiction covered by an MCP |
references/opinion-template.md |
Fill-in skeleton of the six-part Ascertainment Opinion | At Step 6, when producing the final opinion |
references/research-log-template.md |
Search audit-trail table | Open it when research begins; deliver it with the opinion at Step 6 |
What ships with it
4 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.
- 7d ago First seen · 378 lines · 219 tokens per session scan A b7efb3049c51
foreign-law-research is a skill published in the GitHub repository StefanCHEN2026/foreign-law-research-skill- (15 stars, last pushed 7d ago), licensed MIT. It adds 219 tokens to every session and 6,067 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-11-07.
foreign-law-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| foreign-law-researchStefanCHEN2026/foreign-law-research-skill- | Skill | 15 | 7d ago | MIT | A | 219 | Claude Code, Codex |
| contract-drafterrohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 192 | Claude Code, Codex |
| negotiation-position-plannerrohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 118 | Claude Code, Codex |
| redline-proposerrohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 118 | Claude Code, Codex |
| citation-integrity-checkerrohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 180 | Claude Code, Codex |
| client-intakerohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 186 | Claude Code, Codex |
| contract-summariserrohasnagpal/legal-ai-skills | Skill | 207 | 2d ago | MIT | A | 162 | Claude Code, Codex |