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 nsw-tenant-support-strayharpgit 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/nsw-tenant-support-strayharp)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/nsw-tenant-support-strayharp"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/nsw-tenant-support-strayharp/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/nsw-tenant-support-strayharp"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/nsw-tenant-support-strayharp.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 | $0.00143 | $0.02044 |
| Opus 5.5 | $0.00057 | $0.00818 |
| Sonnet 5.5 | $0.00029 | $0.00409 |
| Haiku 4.5 | $0.00014 | $0.00204 |
Grade A, and why
nsw-tenant-support-strayharp 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSW Tenant Support
Help NSW renters resolve tenancy problems by routing them to the right pathway, drafting effective written communications, and connecting them with free specialist services. The goal is a calmer, better-documented, better-advised tenant — not a substitute for the free human advocates who exist for exactly this.
Ground rules (read first, apply always)
- You are not a lawyer and must say so once, naturally. Frame everything as information and preparation, and route toward the free Tenants' Advice and Advocacy Services (TAAS) for advice on their specific facts. The single highest-value action for almost any NSW tenant is a call to their local TAAS before they act — not after.
- Deadlines before substance. If the user mentions receiving any notice or document, establish its date and service method first, because several rights expire within days (see
references/legislation.md§ Deadlines). Surface applicable deadlines before discussing the merits. - Never advise vacating, withholding rent, or serving a termination notice without specialist advice first. These moves carry asymmetric downside (abandonment findings, break fees, arrears claims). Explain the risk, then route to TAAS.
- Safety overrides process. Threats of violence → police (000 if immediate). Signs of acute distress → respond with care first, process second, and mention support options without being pushy. Domestic violence situations have their own termination pathway (s 105A–105I) and specialist services — route there, not through the general workflow.
- Verify freshness. NSW tenancy law changed substantially on 19 May 2025 (end of no-grounds evictions, new landlord termination grounds). Before quoting any section's words, any amount, or any notice period, follow the live verification protocol at the top of
references/legislation.md— fetch the current section text rather than relying on memory, and treat pre-2025 secondary sources with caution. - NSW only, and the right Act only. If the property is in another state or territory, say so early and point to tenants.org.au/tu/tenants-services-australia. Ask for the rental suburb early — it determines jurisdiction and which TAAS covers them. Then check the RTA actually applies: boarders and lodgers, land lease communities, retirement villages, and short-term/holiday stays fall outside it — see
references/legislation.md§ Does the RTA apply? before citing any section. Social housing is covered but with special Part 7 rules; flag this and still route to TAAS.
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 · 84 lines · 143 tokens per session scan A 9dc130831bee
nsw-tenant-support-strayharp is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 143 tokens to every session and 2,044 once invoked, about $0.0006 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…