What is research-materials?

A research tool for finding Taiwanese legal articles, reports, theses, statistics, and other material from official and open sources. It is aimed at legal research rather than personal legal advice.

It helps locate Judicial Yuan reports, periodical articles, research projects, open-access law journals, and related statistics.

It brings several Taiwanese legal information sources into a defined search process, reducing the need to search each catalogue or archive separately.

research-materials — Skill for Claude Code by lawchat-oss

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 lawchat-oss/taiwan-legal-plugin --skill research-materials

Clone the repo

git clone --depth 1 https://github.com/lawchat-oss/taiwan-legal-plugin

Made for: Claude Code.

Or install taiwan-legal, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lawchat-oss/taiwan-legal-plugin/research-materials/github.svg)](https://agentmods.dev/skills/lawchat-oss/taiwan-legal-plugin/research-materials)

Your own site

<a href="https://agentmods.dev/skills/lawchat-oss/taiwan-legal-plugin/research-materials"><img src="https://agentmods.dev/badge/skills/lawchat-oss/taiwan-legal-plugin/research-materials/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lawchat-oss/taiwan-legal-plugin/research-materials"><img src="https://agentmods.dev/badge/skills/lawchat-oss/taiwan-legal-plugin/research-materials.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,644 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.

Model	Per session	Once invoked
Fable 5.1	$0.00203	$0.01644
Opus 5.5	$0.00081	$0.00658
Sonnet 5.5	$0.00041	$0.00329
Haiku 4.5	$0.00020	$0.00164

Measured 1mo ago against content hash a8360f21763d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research-materials 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 1mo 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.

taiwan-legal/skills/research-materials/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/taiwan-legal:research-materials

Retrieves scholarship and statistics on Taiwanese law from official and open-access sources.

Audience

Law professors, legal researchers, judges and their clerks, in-house counsel, attorneys, and students who need secondary sources or empirical data. Not designed for end-consumers seeking legal advice.

Instructions

Load practice profile. Read ~/.claude/plugins/config/taiwan-legal-plugin/taiwan-legal/CLAUDE.md for the user's citation style. If the file does not exist, proceed without defaults. Do not apply the profile's judgment date window to literature or statistics.
Scope check. Confirm the request is a research query, not an advice request (see "What this skill does NOT do").
Identify intent and pick the tool.
- Articles, reports, theses on a topic or by an author → search_legal_literature(keyword=..., source=...); leave source empty to search every source, or name one (司法研究年報, 期刊, GRB, 開放期刊). Then get_legal_literature(literature_id=...) for the abstract and, where published openly, the full text.
- Court caseload / case outcomes / prosecution and conviction figures → search_statistics(keyword=..., source=..., year=...) with a term from the table title (收結, 上訴, 民事, 有罪 …), then get_statistics(statistics_id=...) for the table (pipe-separated rows) or report text.
- Historical sentence ranges → get_sentencing_statistics(crime=...) first to see the available law_options and factor_options, then narrow with law=, court=, factors="累犯=是", year_from=, year_to=. Only ten offence types are covered.
- Years are ROC years (民國; 2026 = 115).
Present results.
- Literature: author, title, venue (journal + volume/issue, or 司法研究年報第 N 輯), year, id. Mark which items have full text.
- Statistics: quote the figures with the table title, period and source URL; do not extrapolate beyond the table.
- Sentencing: report the count of judgments matched, the average / minimum / maximum per penalty type, and the filters used. Always add the tool's note: this describes past judgments in the system's sample, not a sentencing guideline.

Read the full file on GitHub · 92 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.

1mo ago Changed · +9 tokens per session a8360f21763d
1mo ago First seen · 92 lines · 194 tokens per session scan A f5a4a50137c7

Subscribe to this mod's changes

research-materials is a skill published in the GitHub repository lawchat-oss/taiwan-legal-plugin (43 stars, last pushed 18d ago), licensed MIT. It adds 203 tokens to every session and 1,644 once invoked, about $0.0008 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 2026-10-03.

Legal and compliance Research

research-materials next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
research-materialslawchat-oss/taiwan-legal-plugin	Skill	43	18d ago	MIT	A	203	Claude Code
fto-triageanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	81	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	68	Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	today	MIT	A	49	Claude Code
regulatory-research-fallbackHKUDS/OpenSpace	Skill	7.9k	2d ago	MIT	A	20	Claude Code, Codex
terms-of-servicegenspark-ai/genoffice	Skill	12k	today	Apache-2.0	A	32	Claude Code, Codex
x-scorecardx-cmd/x-cmd	Skill	4.7k	8d ago	Apache-2.0	A	57	Claude Code, Codex