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-data-breach-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-data-breach-l0cka)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/assess-australian-data-breach-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/assess-australian-data-breach-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-data-breach-l0cka"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/assess-australian-data-breach-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 | $0.00135 | $0.02050 |
| Opus 5.5 | $0.00054 | $0.00820 |
| Sonnet 5.5 | $0.00027 | $0.00410 |
| Haiku 4.5 | $0.00014 | $0.00205 |
Grade A, and why
assess-australian-data-breach-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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Australian Data Breach
Prepare a privileged-workstream-ready preliminary assessment for a lawyer. Do not conclude that a breach is notifiable merely because a security incident occurred, and do not delay urgent human escalation while researching.
Read references/breach-assessment-method.md before starting. It defines the fact schema, regime prompts, deadline controls and source rules.
Workflow
- Escalate and protect.
- Flag immediate safety, ongoing compromise, destructive activity, material service disruption or an apparently running statutory clock for urgent human attention.
- Ask only for the minimum de-identified facts. Do not request credentials, live malware, exploit code, unnecessary identifiers or complete datasets.
- Do not take containment action, contact a threat actor, make a payment, notify a person or regulator, or submit a report. Preserve the lawyer's approval boundary and the forensic evidence-preservation plan.
- Establish the incident record.
- Separate known facts, source of each fact, estimates, inferences, assumptions, disputed facts and unknowns.
- Record detection and awareness times with timezone; suspected occurrence window; systems and custodians; data types and protections; affected and potentially affected people; location; actors; containment/remediation; recipients; vendors; critical services; ransom demand or payment; and existing notices.
- Do not equate detection, confirmation, containment, assessment completion or occurrence. Record each timestamp independently.
- Map candidate regimes.
- Test the Privacy Act Notifiable Data Breaches scheme and each applicable State, Territory, health, critical-infrastructure, cyber-extortion, telecommunications, financial-services or contractual regime.
- Distinguish mandatory notice, assessment duties, voluntary reports, contractual notice, insurance conditions and internal escalation.
- Treat numerical thresholds, triggering knowledge standards, recipients, content requirements and time periods as propositions requiring current verification.
- Invoke
$route-australian-privacy-jurisdictionfor every State or Territory nexus and$map-australian-cyber-incident-obligationsfor the concurrent Commonwealth and sectoral matrix.
- Verify law and calculate cautiously.
- Invoke
$check-commonwealth-legislationfor every material Commonwealth title or provision and the relevant incident date. Invoke$check-nsw-legislationfor every material NSW title or provision. - Invoke
$check-australian-privacy-principleswhen security, retention, use, disclosure or another APP issue is material. Keep this Schedule 1 check separate from verification of the Notifiable Data Breaches scheme. A detected or unverified APP-framework change blocks the APP conclusion, but must not delay urgent containment or independently verified incident duties. - Invoke
$assess-statutory-privacy-tortindependently of APP coverage when intentional or reckless intrusion, surveillance, misuse, disclosure or publication may be material. - For another State or Territory, inspect its official legislation source.
If a version or commencement point cannot be established, use
NOT VERIFIEDand escalate the check. - Calculate a deadline only after verifying the trigger, period, counting rule and relevant facts. Show the trigger time, timezone, calculation and uncertainty. Never invent a date from an incomplete record.
- State that case law was not considered. Do not search for or rely on it.
- Invoke
- Assess and hand off.
- Address reasonable-likelihood, serious-harm, remedial-action and multi-entity issues only against verified text and stated facts.
- Build one row per possible obligation. Give the earliest plausible deadline prominence without describing an uncertain date as final.
- Identify the decision owner, evidence needed and next action. Reserve all notification and legal conclusions for a lawyer and authorised incident lead.
What ships with it
3 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 · 181 lines · 135 tokens per session scan A e593b232fba9
assess-australian-data-breach-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 135 tokens to every session and 2,050 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…