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 ThomasMoreAI/legal-skills-open --skill verify-hca-judgment-l0ckagit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/verify-hca-judgment-l0cka)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/verify-hca-judgment-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/verify-hca-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.
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/verify-hca-judgment-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/verify-hca-judgment-l0cka.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 | $0.00122 | $0.01229 |
| Opus 5.5 | $0.00049 | $0.00492 |
| Sonnet 5.5 | $0.00024 | $0.00246 |
| Haiku 4.5 | $0.00012 | $0.00123 |
Grade A, and why
verify-hca-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 22d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify HCA Judgment
Use hcourt.gov.au as the controlling source. Produce a provenance record,
not a bare assertion that a case "exists".
The website's coverage (checked 2026-08-26) is four collections, and nothing
else: judgments 1998 to current, Commonwealth Law Reports volumes 1–100
(roughly 1903–1959), unreported judgments 1906–1994 (an incomplete set, per
the Court), and single Justice judgments since January 2024. Judgment
summaries (since December 2002) are not judgments and are not a
verification source.
Reported decisions from roughly 1959 to 1997 — CLR volumes above 100 — are
not published there. A citation in that gap is UNVERIFIABLE at the
official publisher, never NOT FOUND. Note also that the High Court only
began issuing medium-neutral citations in 1998; an earlier [YEAR] HCA N
citation is a retrospective identifier that the official publisher does not
index, so verify such cases by case name and reported citation instead.
Read ../../references/case-law-verification-method.md before verifying. It defines the outcome semantics, access rules and restriction handling.
Workflow
- Fix the scope.
- Accept medium-neutral
[YEAR] HCA Ncitations, CLR citations within volumes 1–100, ALJR citations, and High Court case names. - Return
OUTSIDE SCOPEfor other courts, transcripts (HCATrans), special-leave dispositions unless published as judgments, treatment analysis or advice.
- Accept medium-neutral
- Place the citation inside or outside coverage.
- Determine which collection should hold the decision. If none can —
most reported decisions from roughly 1959 to 1997 — return
UNVERIFIABLEwith the coverage boundary stated and a manual path (the Court registry or a library copy of the report series).
- Determine which collection should hold the decision. If none can —
most reported decisions from roughly 1959 to 1997 — return
- Resolve the citation at the official publisher.
- Search the matching collection's keyword search by distinctive case
name terms, then match the result row's displayed
Citation:field exactly. The keyword index does not match bracketed citation strings, so never conclude anything from a citation-string search alone. - The 1998–current collection publishes each judgment PDF at a
deterministic path (
/sites/default/files/eresources/YEAR/HCA/N.pdf); a resolved and opened PDF corroborates the citation, but cite it only after it resolved and was inspected. - Make one targeted lookup per citation. Do not crawl listings.
- Search the matching collection's keyword search by distinctive case
name terms, then match the result row's displayed
- Confirm identity.
- Match the case name, year, citation number and decision date as published. Record the case name exactly as the Court publishes it.
- Treat a supplied case name that differs materially from the published name as a qualification, and say which differs.
- Check restrictions before reproducing anything.
- Look for suppression or non-publication notations and pseudonymised parties on the judgment page. Preserve any found.
- Report using the result contract.
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.
- 22d ago First seen · 102 lines · 122 tokens per session scan A 490931a90aad
verify-hca-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 122 tokens to every session and 1,229 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 2026-10-06.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…