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 jonashertner/opencaselaw --skill researchgit clone --depth 1 https://github.com/jonashertner/opencaselawWrote 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/jonashertner/opencaselaw/research)<a href="https://agentmods.dev/skills/jonashertner/opencaselaw/research"><img src="https://agentmods.dev/badge/skills/jonashertner/opencaselaw/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/jonashertner/opencaselaw/research"><img src="https://agentmods.dev/badge/skills/jonashertner/opencaselaw/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 | $0.00043 | $0.00743 |
| Opus 5.5 | $0.00017 | $0.00297 |
| Sonnet 5.5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal research with ocl
Use when asked a question of Swiss law that needs authorities: what the
Federal Supreme Court or a cantonal court held, which statute article
applies, what the practice is. Install: pipx install opencaselaw-cli (or
uv tool install opencaselaw-cli). Every command prints JSON when piped;
--fields keeps the keys you need; exit code 4 means something did not
resolve, 3 means the service or network failed.
Steps
- Frame the question as search terms in the language of the likely
decisions (German for most BGE, French for Romandie courts). Search:
ocl decisions search '<terms>' --max-results 20 --format jsonl --fields decision_id,citation_string_de,decision_date,court(add--court bge,--language fr,--date-fromas needed). A text search is one ranked window;totalis a candidate pool, not a count. - Read before citing. For each candidate worth it:
ocl tool call get_regeste decision_id=<id>(BGE headnote) andocl decisions passage <id> <number>for the considerations. Never summarise a decision from its title. - Follow the law:
ocl tool call find_leading_cases query='<terms>',ocl citations list <id> --direction incoming --limit 20(who cites it later),ocl tool call find_relevant_erwaegung decision_id=<id> query='<terms>'. Statutes:ocl laws get OR --article 336(--as-of YYYY-MM-DDfor the text in force at a date; atext_statusother than ok means no text was recovered). Practice and scholarship:ocl tool call search_practice,ocl tool call search_scholarship,ocl tool call search_commentaries. - Cite only through the service:
ocl cite <reference> --pinpoint <n>gives the string to copy verbatim (citation_string); an inline pinpoint in the reference is verified. Quote only whatpassageserved, and keep the served wording. - Before answering, run the citation check on your own draft
(
ocl citations resolve --input refs.jsonl --format jsonl) and the quotation check (ocl quotes check --input quotes.jsonl --format jsonl). Fix or drop anything that is notresolved/exact; report what you dropped. - Say what the tool established (existence, identity, wording) and what it
did not (legal support, whether a decision is still good law). Keep the
evidence:
ocl bundle create '<terms>' --max-results 10 --passage <n> --out evidence.
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 First seen · 53 lines · 43 tokens per session scan A fe329529d8a8
research is a skill published in the GitHub repository jonashertner/opencaselaw (75 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 743 once invoked, about $0.0002 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 2026-09-07.
Other skills, from other repositories
legaltech-expert
Expert in legal technology: contract lifecycle management, e-discovery, AI-assisted legal research, case and matter management, document automation, and compliance tooling. Use when the user mentions legal case or matter management, e-discovery and legal holds, CLM or contract review and obligation tracking, legal…
legalize-kr
Retrieve Korean laws, court precedents, administrative rules, and local ordinances through connected Legalize-KR MCP tools. Use it for document search, full text, article lookup, and revision comparison. It also guides CLI, local MCP, Git, and direct GitHub access when connected tools are unavailable.
format-monitoring-report
A formatting guide for turning already-approved legal-monitoring content into a DOCX or PDF report. It specifies a seven-section layout, blue labels, Times New Roman, footnotes, page numbers, and a final comparison table.
verifiable-legal-document
A Russian-language workflow for producing legal documents with claim identifiers, linked supporting passages, hashes, and validation reports.
matter-intake
A setup process for a new legal matter or research assignment. It turns an unstructured request into a defined question, scope, data classification, plan, sources, deadline, and completion criteria.
ukrainian-legal-research
A research workflow for determining which Ukrainian laws and regulations applied on a specific date. It checks official wording, versions, effective dates, transitional rules, legal hierarchy, authority, and official sources.