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 au-tax-research-ryanduguidgit 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/au-tax-research-ryanduguid)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/au-tax-research-ryanduguid"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/au-tax-research-ryanduguid/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/au-tax-research-ryanduguid"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/au-tax-research-ryanduguid.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 | $0.00052 | $0.01803 |
| Opus 5.5 | $0.00021 | $0.00721 |
| Sonnet 5.5 | $0.00010 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
au-tax-research-ryanduguid 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 7d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax research file note
Inputs
The question in the client's or requester's words, the established facts with the evidence for each, the entity type, the income year or event date the answer applies to, any earlier file note or advice on the same issue, and the firm's research and review policy.
Workflow
-
Frame one answerable question before searching. Name the entity type, the income year or event date, the facts the answer turns on and the provision or topic in issue. List every fact not yet established. Where a missing fact could change the answer, ask for it and never assume it. If it stays unavailable, carry on with the parts the established facts support, record it under
facts_not_establishedand keep every conclusion that depends on it conditional. -
Read the operative law first. Open the provision on the Federal Register of Legislation in the compilation in force for the period, and record the compilation number and date. Read the definitions it relies on and any commencement, application or transitional provision. Note a later compilation or an uncommenced amendment; do not apply it to an earlier period.
-
Add the Commissioner's view and the cases, each labelled by what it is. A public ruling binds the Commissioner for an entity it applies to that relies on it (TR 2006/10 paragraph 30). A practical compliance guideline states how the ATO will allocate compliance resources; it is not the law. A decision impact statement gives the ATO's response to a decision. An edited version of private advice binds nobody: taxpayers cannot rely on it and the Commissioner is not bound by it (PS LA 2008/4, "Taxpayer reliance on edited versions"), because it records advice given to someone else on other facts. A court or tribunal decision carries the weight of its court and turns on its facts, and a dissent is not the decision. For each decision, record its medium neutral citation in AGLC4 form with the paragraph relied on, and check its later history before relying on it: an appeal, a later decision that departs from it, or a decision impact statement. Open each document's Legal Database page and record any withdrawal, addendum, draft status or "being reviewed" notice it shows.
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.
- 7d ago First seen · 109 lines · 52 tokens per session scan A ea51d0cee450
au-tax-research-ryanduguid is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (88 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,803 once invoked, about $0.0002 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…