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 agentmods add skills/docketdrafter/docketdrafter-plugins/oh-lawsnpx skills add DocketDrafter/docketdrafter-plugins --skill oh-lawsgit clone --depth 1 https://github.com/DocketDrafter/docketdrafter-pluginsWhat 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 | $0.00035 | $0.00442 |
| Opus 5 | $0.00017 | $0.00221 |
| Sonnet 5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
oh-laws 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 3d 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.
What it actually says
Ohio Laws
Use this skill for Ohio statutory and constitutional research. The corpus is generated from the official Ohio Laws website maintained by the Ohio Legislative Service Commission.
On the first lookup, read_section.py resolves the latest Ohio release, downloads its corpus from DocketDrafter's public S3 bucket, verifies its SHA-256 checksum, and installs it under ~/Documents/DocketDrafter Library/corpora/oh-laws/. The reader never checks for updates after installation; subsequent research is local and works offline. Set DOCKETDRAFTER_DATA_DIR to use a different library directory.
Lookup
python scripts/read_section.py "ORC 2903.01"
python scripts/read_section.py "Ohio Rev. Code § 149.43"
python scripts/read_section.py "Ohio Const. art. I, § 1"
python scripts/read_section.py --search "public record"
Use --format json or --format markdown for structured output, and --max-bytes N to limit displayed text. Results include links to the official section pages. Revised Code metadata also retains effective dates, latest-legislation descriptions, and authenticated PDF URLs when supplied by Ohio.
Corpus installation and updates
Always use scripts/read_section.py for lookups and searches. It installs the latest corpus automatically if needed; do not download or extract the artifact manually.
Repository maintainers refresh the corpus with the builder in the content repository and publish a new immutable versioned artifact. Existing installations remain stable; fresh Cowork sessions receive the latest release.
Sources:
The Legislative Service Commission updates the Revised Code on an ongoing basis. Treat the corpus as current only as of the retrieval timestamp in references/index.json and use the linked official publication when source authority or very recent amendments matter.
What ships with it
2 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.
- 3d ago First seen · 35 lines · 35 tokens per session scan A b25af4acfffd
oh-laws is a skill published in the GitHub repository DocketDrafter/docketdrafter-plugins (9 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 35 tokens to every session and 442 once invoked, about $0.0002 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
data-court-auction
대법원 법원경매정보(courtauction.go.kr) 부동산 매각공고를 매각기일·법원·기일/기간 입찰 기준으로 조회하고, 각 공고를 사건번호·용도·주소·감정평가액·최저매각가로 펼쳐서 보여줍니다. 법원사무소 코드와 사건번호로 단건 직접 조회도 지원합니다. read-only이며 IP 차단 방지를 위해 호출당 약 2초 지연을 둡니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "오늘 어디서 부동산 경매 열려?", "내일 매각공고 보여줘" "서울중앙지방법원 2026-04-27 매각공고", "기일입찰만 보여줘" "사건번호 2024타경100001 진행 상황 알려줘"…
prawo-eu-eurlex
Odpytuje OFICJALNE repozytorium prawa UE — CELLAR/EUR-Lex Urzędu Publikacji (SPARQL + REST, bez klucza): wyszukiwanie aktów, pełny tekst PO POLSKU i w 23 innych językach, WERSJE SKONSOLIDOWANE, pojedyncze artykuły, metadane, nowelizacje, uchylenia, sprostowania, podstawa prawna — po numerze CELEX lub ELI. Używaj przy…
prawo-pl-eli
Odpytuje OFICJALNE API ELI Sejmu (api.sejm.gov.pl/eli) — źródło pierwotne prawa polskiego (Dziennik Ustaw, Monitor Polski): wyszukiwanie aktów, TEKST JEDNOLITY, pojedyncze artykuły, metadane, nowelizacje, podstawa prawna, sygnatury Dz.U./M.P. Używaj przy KAŻDYM pytaniu z prawa polskiego — TAKŻE gdy przepis nie jest…
prawo-pl-cbosa
Przeszukuje CBOSA — Centralną Bazę Orzeczeń Sądów Administracyjnych (orzeczenia.nsa.gov.pl): wyroki, postanowienia i uchwały NSA oraz 16 WSA (2,4 mln orzeczeń od 2004 r.). Używaj przy KAŻDYM pytaniu o orzecznictwo sądów administracyjnych: skargi na decyzje organów, interpretacje podatkowe, „jak NSA/WSA interpretuje…"…
prawo-pl-edzienniki
Odpytuje API ELI 16 WOJEWÓDZKICH DZIENNIKÓW URZĘDOWYCH — PRAWO MIEJSCOWE: uchwały rad gmin, powiatów i sejmików województw, rozporządzenia i zarządzenia wojewody, akty prawa miejscowego. Używaj przy KAŻDYM pytaniu o prawo konkretnej gminy/powiatu/województwa: „uchwała rady gminy/miasta…", „miejscowy plan…
prawo-pl-rejestr-umow
Odpytuje publiczne API Centralnego Rejestru Umów JSFP (rejestrumow.gov.pl) — jawny rejestr umów zawieranych od 1.07.2026 przez jednostki sektora finansów publicznych: urzędy, gminy, szpitale, uczelnie, sądy. Używaj przy pytaniach „jakie umowy zawarł urząd/gmina/szpital X", „z kim i na ile ma umowę…", „kto dostał…