What is judgment-search?

A search tool for finding published Taiwanese court judgments on the Judicial Yuan website and reading their full text. The Judicial Yuan is Taiwan's central judicial administration, and a 字號 is a court case number.

Searching judgments by keywords, court, date range, or case number, and retrieving the reasoning and full text of a specific ruling.

It helps legal researchers find relevant rulings without manually searching the court portal, while keeping research separate from legal advice or predictions.

judgment-search — 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 judgment-search

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/judgment-search/github.svg)](https://agentmods.dev/skills/lawchat-oss/taiwan-legal-plugin/judgment-search)

Your own site

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

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,857 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	$0.00123	$0.01857
Opus 5.5	$0.00049	$0.00743
Sonnet 5.5	$0.00025	$0.00371
Haiku 4.5	$0.00012	$0.00186

Measured 1mo ago against content hash 8b6921b8e38b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

judgment-search 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/judgment-search/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/taiwan-legal:judgment-search

Searches Taiwan's open judgment database and returns structured results or full text.

Audience

Legal researchers, attorneys, paralegals, in-house counsel, and law students working in or with the Taiwanese legal system. Assumes familiarity with Taiwan court structure (最高法院 / 高等法院 / 地方法院 / 行政法院 / 智慧財產及商業法院) and the 字號 case-ID convention. 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 default court levels, date windows, and citation style. If the file does not exist, say: "Run /taiwan-legal:cold-start-interview first to set defaults — or shall I proceed with no defaults?"
Scope check. Before running the tool, confirm the request falls inside scope (see "What this skill does NOT do" below). If the user is asking for a legal opinion, prediction, or recommendation on a case → do not silently produce one; surface the limitation and offer a research-only path instead.
Identify intent from the user's query.
- "search" / keyword / topic → use search_judgments(keyword, court, case_type, year_from, year_to, ...) from the taiwan-legal-db MCP server. Years are ROC years (民國; 2026 = 115), so a date window like "last 5 years" becomes year_from=111, year_to=115.
- 字號 given / "read full text" → use get_judgment(jid=...).
- URL given → use get_judgment(url=...).
- "Which later judgments cite this case / 釋字?" → search_judgments(keyword="<full 字號>"), e.g. keyword="108年度台上大字第2680號" or keyword="釋字第748號"; the hits are judgments whose text mentions that 字號.
- Ambiguous → ask which the user wants.
Execute the MCP tool call with profile defaults applied only when the user did not specify (e.g., default court level, default date range). Explicit user-provided values override defaults.
Apply confidence bands (see below) when characterizing results.

Read the full file on GitHub · 104 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 · +3 lines 8b6921b8e38b
2mo ago First seen · 101 lines · 123 tokens per session scan A 45f8fc8d8765

Subscribe to this mod's changes

judgment-search is a skill published in the GitHub repository lawchat-oss/taiwan-legal-plugin (43 stars, last pushed 18d ago), licensed MIT. It adds 123 tokens to every session and 1,857 once invoked, about $0.0005 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 2026-08-30.

Legal and compliance

judgment-search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
judgment-searchlawchat-oss/taiwan-legal-plugin	Skill	43	18d ago	MIT	A	123	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