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 australian-legal-research-acor8826git 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/australian-legal-research-acor8826)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/australian-legal-research-acor8826"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/australian-legal-research-acor8826/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/australian-legal-research-acor8826"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/australian-legal-research-acor8826.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 | $0.00248 | $0.06254 |
| Opus 5.5 | $0.00099 | $0.02502 |
| Sonnet 5.5 | $0.00050 | $0.01251 |
| Haiku 4.5 | $0.00025 | $0.00625 |
Grade A, and why
australian-legal-research-acor8826 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Australian Legal Research (multi-agent)
Overview
This skill does two things. It retrieves Australian primary law (case law, legislation, topical searches) from the freely available legal databases — AustLII (austlii.edu.au), CaseLaw NSW (caselaw.nsw.gov.au), the Federal Register (legislation.gov.au), NSW legislation (legislation.nsw.gov.au), and BarNet Jade's free tier (jade.io — judgment text and citator leads; access mechanics in references/retrieval-mechanics.md), with web search as a first-class discovery path; and it researches — running an orchestrated, red-teamed, multi-agent pass over a legal question and self-validating every authority before it is reported, with AGLC4-formatted citations (references/aglc4-citation.md).
The skill ships no MCP server, but it prefers one if present: when the optional jurisd MCP server is registered, its tools are the Layer-0 retrieval path (authority-ranked AustLII search, clean full-text fetch, deterministic provision lookup, an offline citation-graph tool, AGLC4 formatting). Otherwise it drives the runtime's own primitives (web_fetch/WebFetch, web_search, Claude in Chrome). Either way the skill works — jurisd is preferred, never required. The full mechanics — Layer-0 precedence and fallback, URL patterns, which tool to use where, recovery when a fetch fails — live in references/retrieval-mechanics.md. Every agent reads that file before fetching anything. The orchestrator owns strategy; the reference owns mechanics.
CRITICAL: Verification Principle
Never cite an Australian case, quote a judgment, reproduce statutory text, or state case metadata (bench, dates, jurisdiction, parties, catchwords) from memory alone. Always verify by fetching the source. Training data contains wrong citations, outdated legislation, and fabricated quotes. Citing a non-existent or overruled case in court has severe consequences — and the user is a self-represented litigant who files these results.
What ships with it
11 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.
- LICENSE 1.0 KB
- references/agent-caselaw.md 11 KB
- references/agent-evidence.md 8.8 KB
- references/agent-jurisdiction.md 6.9 KB
- references/agent-legislation.md 4.9 KB
- references/agent-redteam.md 4.0 KB
- references/agent-secondary.md 3.4 KB
- references/agent-validation.md 8.4 KB
- references/aglc4-citation.md 6.0 KB
- references/retrieval-mechanics.md 20 KB
- references/templates.md 21 KB
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.
- 19d ago First seen · 199 lines · 248 tokens per session scan A 0958ff295dec
australian-legal-research-acor8826 is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 248 tokens to every session and 6,254 once invoked, about $0.0010 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.
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…