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 legal-writing-mblauberggit 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/legal-writing-mblauberg)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/legal-writing-mblauberg"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/legal-writing-mblauberg/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/legal-writing-mblauberg"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/legal-writing-mblauberg.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 | $0.00056 | $0.01278 |
| Opus 5.5 | $0.00022 | $0.00511 |
| Sonnet 5.5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
legal-writing-mblauberg 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Australian legal writing
General Australian legal style, document-shape and source-discipline layer. Stricter project and forum instructions override it. This is drafting assistance, not legal advice: verify current law, forms and procedure against official sources and retain qualified or human review for filing-facing work.
This skill is a specialization of the natural-writing hub. The hub owns the
Australian English default, the anti-AI taxonomy and the condense pass; this
skill owns jurisdiction, forum, instrument and filing-facing rules. The Legal
Function Test is this skill's own claim-classification scheme and does not map
to the hub's observed/inferred evidence schema.
Scope
Use this skill when the output is an Australian legal instrument, filing-facing text or legal correspondence: court and tribunal forms, affidavits, statutory declarations, witness statements, submissions and outlines, proposed orders, chronologies, annexure indexes, deeds and agreements, letters of demand and pre-action correspondence, registry and party correspondence, non-filing legal decision overviews, and AGLC4 citation.
Legal subject matter alone is not the trigger. An article, chapter, summary or
plain-language explanation about law goes to natural-writing; a spec, README,
runbook or other engineering artefact goes to engineering-writing. This skill
joins either as a companion where legal status, authority, forum wording or
source altitude must survive the rewrite.
Workflow
- Read project instructions, live matter state and source-boundary rules. Load the matching jurisdiction, forum and document skill where one exists.
- Choose
draft,rewrite,condense,diagnose,correspondence,decision-overvieworfinal-scrub. Load legal concision for all prose; the reference map in validation-checklists.md gives the remaining reference each mode, document type or content type needs. - Classify each sentence by legal function before polishing. Affidavits and witness statements give evidence; submissions argue; orders command; chronologies organise; internal notes analyse; correspondence communicates. Move wrong-home material first.
- Lock legal status, source anchors, exact quotations, authorities, labels, offer terms, non-admission/non-waiver wording, deadlines, attachments, redactions and user-authority conditions.
- Draft the minimum complete text in Australian English. Front-load the relief, request, answer or next step; use one proposition per paragraph, one home per point and exact pinpoints. Cut padding, duplicate history, intensifiers and internal agent language.
What ships with it
21 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.
- agents/openai.yaml 273 B
- evals/regression_cases.yaml 4.3 KB
- evals/trigger_cases.yaml 2.1 KB
- LICENSE 1.0 KB
- references/aglc4-citation.md 5.1 KB
- references/argument-structure-and-paragraphing.md 21 KB
- references/australian-english-house-style.md 12 KB
- references/decision-overviews.md 1.2 KB
- references/deeds-and-agreements.md 5.9 KB
- references/demands-and-pre-action-correspondence.md 5.5 KB
- references/family-violence-and-redaction.md 3.6 KB
- references/forbidden-patterns.md 9.9 KB
- references/forum-and-document-recipes.md 8.3 KB
- references/legal-concision-and-anti-ai.md 17 KB
- references/legal-correspondence-style.md 4.9 KB
- references/source-boundary-and-citations.md 7.5 KB
- references/statutory-declarations.md 6.4 KB
- references/tribunals-and-merits-review.md 5.7 KB
- references/validation-checklists.md 13 KB
- references/verification-and-escalation.md 2.7 KB
- scripts/lint_legal_style.py 22 KB runs code
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 · 121 lines · 56 tokens per session scan A 1c963cfd9b6f
legal-writing-mblauberg is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,278 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…