verify-nsw-judgment-l0cka

verify-nsw-judgment-l0cka is a skill for Codex from ThomasMoreAI/legal-skills-open. It costs 130 tokens per session (1,223 once invoked), scanned A, original, Apache-2.0.

A case-verification tool for checking whether a New South Wales court or tribunal decision appears on the official NSW Caselaw website. It resolves legal citation formats and creates a record showing the source and any publication restrictions.

In plain words
What is it for?
Use it to verify NSW case names, medium-neutral citations, and NSW Law Reports citations, and to preserve provenance and restriction notices for later legal writing.
Why use it?
It helps avoid citing a case that cannot be found, using the wrong decision, or confusing an unpublished decision with one that does not exist. It also marks cases outside the site's coverage as unverifiable rather than treating them as missing.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to verify NSW case names, medium-neutral citations, and NSW Law Reports citations, and to preserve provenance and restriction notices for later legal writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka
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 ThomasMoreAI/legal-skills-open --skill verify-nsw-judgment-l0cka
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

Made for: Codex.

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.

agentmods badge for verify-nsw-judgment-l0cka

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka/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.

agentmods 80×15 button for verify-nsw-judgment-l0cka

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/verify-nsw-judgment-l0cka.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00130 $0.01223
Opus 5.5 $0.00052 $0.00489
Sonnet 5.5 $0.00026 $0.00245
Haiku 4.5 $0.00013 $0.00122

Measured 19d ago against content hash 6966205c6c3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-nsw-judgment-l0cka 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 19d 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.

au/criminal/skills/verify-nsw-judgment-l0cka/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify NSW Judgment

Use caselaw.nsw.gov.au as the controlling source. NSW Caselaw is the official publisher for the Supreme Court, Court of Appeal, Court of Criminal Appeal, Land and Environment Court, District Court, Local Court, NCAT and other NSW courts and tribunals, with coverage from 1999 onward (earlier for some courts). Produce a provenance record, not a bare assertion that a case "exists".

Read ../../references/case-law-verification-method.md before verifying. It defines the outcome semantics, access rules and restriction handling.

Workflow

  1. Fix the scope.
    • Accept medium-neutral NSW citations (NSWSC, NSWCA, NSWCCA, NSWDC, NSWLC, NSWLEC, NSWCATAP, NSWCATAD and other NSW identifiers), NSWLR reported citations, and NSW case names.
    • Return OUTSIDE SCOPE for other jurisdictions, treatment analysis or advice. Note that decisions before a court's NSW Caselaw coverage start may exist without being published there; that is an UNVERIFIABLE boundary, not NOT FOUND.
  2. Resolve the citation at the official publisher.
    • Use the advanced search's Medium Neutral Citation field. The citation must include the square brackets, as the form itself states.
    • The search executes only when the request carries the form's full query string, including the site's courts and tribunals identifier parameters — a bare mnc parameter returns the empty form. Submit the search through the site's own form (directly or in a browser) rather than a hand-built minimal URL, and read the Displaying X - Y of Z marker for the result count.
    • Make one targeted lookup per citation; never crawl or bulk-download listings.
    • For an NSWLR citation, resolve to the medium-neutral citation through the site's search before concluding anything.
  3. Confirm identity.
    • Match the case name, citation, court and decision date as published, and record the NSW Caselaw decision URL.
    • A direct fetch of a decision page returns the metadata header only — citation, case name, dates, before, catchwords and the Restrictions field — which is sufficient for existence and identity. The judgment body loads in a browser session; quote checks need the rendered page or the site's document download, not the bare HTML fetch.
    • Treat a supplied case name that differs materially from the published name as a qualification, and say which differs.
  4. Respect the publisher's conditions.
    • The Copyright in Judicial Decisions Notice 1995 (NSW) permits reproduction conditioned on accuracy and proper context. Reproduce nothing inaccurately, and do not republish party names into contexts a search engine indexes.
    • Check the decision page for restriction, suppression or non-publication notations before quoting anything. Preserve any found and treat them as qualifications.
  5. Report using the result contract.

Read the full file on GitHub · 102 lines

Files

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.

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.

  1. 19d ago First seen · 102 lines · 130 tokens per session scan A 6966205c6c3e

Subscribe to this mod's changes

verify-nsw-judgment-l0cka is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 130 tokens to every session and 1,223 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 2026-10-09.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens