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 assess-australian-privacy-issues-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/assess-australian-privacy-issues-l0cka)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/assess-australian-privacy-issues-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/assess-australian-privacy-issues-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/assess-australian-privacy-issues-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/assess-australian-privacy-issues-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 | $0.00132 | $0.01744 |
| Opus 5.5 | $0.00053 | $0.00698 |
| Sonnet 5.5 | $0.00026 | $0.00349 |
| Haiku 4.5 | $0.00013 | $0.00174 |
Grade A, and why
assess-australian-privacy-issues-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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Australian Privacy Issues
Produce a preliminary issue-and-law map for an Australian lawyer. Do not state that a duty applies until its threshold facts and current legislative text have been checked.
Read references/source-and-issue-method.md before starting. It defines the source hierarchy, legislation routing, issue taxonomy and treatment of Harvey Labs patterns.
Read references/current-commonwealth-privacy-map.md when Commonwealth privacy law is potentially relevant. Treat its dated entries as prompts requiring current verification.
Workflow
- Protect the material and fix scope.
- Ask for de-identified facts or the minimum necessary extracts. Do not request credentials, exploit code, unnecessary identifiers or complete client files.
- Record the Australian jurisdiction or jurisdictions, relevant dates,
entity types, sector, data subjects, data types, conduct and requested
deliverable. Use today's
Australia/Sydneydate when no as-at date is given and say so. - State that case law is outside scope. Do not search for, cite, summarise or
rely on cases, tribunal decisions or case-derived tests. Mark a request
requiring them
OUTSIDE SCOPEfor that component.
- Build a fact and applicability map.
- Separate supplied facts, reasonable inferences, assumptions and missing facts. Never invent an entity, data flow, contract term or jurisdiction.
- Identify possible roles and thresholds without deciding them silently: APP entity or exemption; Commonwealth, State or Territory body; health or other sector; controller-like or service-provider role; overseas actor; critical-infrastructure or regulated-entity status.
- Identify collection, use, disclosure, security, access/correction, retention/destruction, direct marketing, automated decision-making, cross-border, vendor and incident-response issues raised by the facts.
- Invoke
$route-australian-privacy-jurisdictionwhenever a State or Territory nexus is possible. Preserve its public/private, health, government-contractor, breach and surveillance distinctions.
- Identify candidate law.
- Use the trigger table in the reference. Treat it as an issue-spotting aid, not authority or a statement that every listed law applies.
- Distinguish legislation, delegated legislation, regulator guidance, contractual requirements and voluntary standards. Do not present guidance or standards as legislation.
- Keep foreign-law analysis outside scope. Record a foreign nexus only as a referral or separate-workstream issue.
- Verify legislation.
- For each Commonwealth candidate, invoke
$check-commonwealth-legislationwith the title, relevant provision and as-at date. Preserve its Register IDs, version period, currency flags and qualifications. - If the question spans legislative change, a future deployment date or
more than one applicable compilation, invoke
$trace-commonwealth-legislative-changeand keep future or transitional law separate from law in force at the as-at date. - For each NSW candidate, invoke
$check-nsw-legislationin the same way. - Whenever an APP may apply, invoke
$check-australian-privacy-principlesfor the as-at date and decision horizon. Do not use a static APP list as authority. - If the APP result is
APP FRAMEWORK CHANGE DETECTED – LEGAL CONTENT REVIEW REQUIRED, stop reuse of earlier APP analysis and identify each affected mapping for lawyer refresh. If it isAPP FRAMEWORK NOT VERIFIED – DO NOT RELY, make no APP conclusion. - Invoke
$assess-statutory-privacy-tortindependently of APP coverage for surveillance, recording, scraping, profiling, inference, deepfakes, disclosure, publication or intimate, location, health or financial data. - Invoke
$assess-automated-decision-transparencyfor automated or AI-assisted decisions, including any horizon crossing 10 December 2026. - Invoke
$map-australian-cyber-incident-obligationsfor a suspected incident, cyber-extortion payment, outage or material control weakness. - If a legislation skill or official source is unavailable, do not fill the
gap from memory, a search snippet or secondary commentary. Label it
NOT VERIFIEDand identify the exact follow-up check.
- For each Commonwealth candidate, invoke
- Analyse and report.
- Apply verified text to stated facts provisionally. Expose threshold uncertainty and plausible alternatives.
- Give each issue a practical consequence, missing fact and concrete next step. Do not assign false numerical risk scores.
- Include favourable or compliant features as well as gaps when reviewing a document or program.
What ships with it
4 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.
- 19d ago First seen · 155 lines · 132 tokens per session scan A 3b4c67009091
assess-australian-privacy-issues-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 132 tokens to every session and 1,744 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.
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…