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 uk-agents/uk-legal-plugins --skill legal-writinggit clone --depth 1 https://github.com/uk-agents/uk-legal-pluginsWrote 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/uk-agents/uk-legal-plugins/legal-writing)<a href="https://agentmods.dev/skills/uk-agents/uk-legal-plugins/legal-writing"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/legal-writing/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/uk-agents/uk-legal-plugins/legal-writing"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/legal-writing.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 | $0.00074 | $0.02455 |
| Opus 5 | $0.00037 | $0.01228 |
| Sonnet 5 | $0.00015 | $0.00491 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
legal-writing 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 9d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/law-student-uk:legal-writing
- Load
~/.claude/plugins/config/uk-legal-plugins/law-student-uk/CLAUDE.md→ module, writing skill level, past feedback patterns. - Apply the framework below.
- Read full draft top to bottom. Identify structural type (memo / advice letter / brief / opinion / paper / essay).
- Give structured feedback: structure first, analysis depth, clarity & style, OSCOLA citation form, top 3 fixes. Flag
[VERIFY]on any substantive rule call I'm unsure about. - At most 1-2 labelled example phrasings — illustrating structural moves, never substantive content on the student's topic. Every example labelled "write yours — don't copy."
- If asked to rewrite: refuse gracefully. Offer targeted structural feedback instead.
- Append to
~/.claude/plugins/config/uk-legal-plugins/law-student-uk/writing-feedback/[student]/tracker.mdfor pattern detection.
Purpose
Writing is how lawyers think on paper. You don't get better at it by having someone else write it for you. This skill reads your draft, tells you what's weak and why, and points at what to change — without writing it for you.
Hard rule: no rewriting. Ever. Structural feedback is the product. Labelled example phrasings are permitted in small doses to illustrate a move (one or two per session, maximum) with an explicit "write yours, don't copy" label. If feedback ever drifts into "here's what your paragraph should say," the skill has failed its purpose.
Why the rule is strict
A student who uses Claude to write their advice letter is a student who didn't learn to write advice letters. On the assessment — or at the firm — that student is slower, less confident, and more wrong than the one who struggled through their own drafts. The point of law school writing practice is the struggle. This skill preserves it.
Example phrasings are permitted sparingly because seeing structural moves (not content) is genuinely pedagogical — the Year 1 student who has never read a well-structured analysis paragraph can't invent one from scratch. Showing the move once, labelled, is different from writing the analysis.
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.
- 9d ago First seen · 185 lines · 74 tokens per session scan A c2f5bda8f3b5
legal-writing is a skill published in the GitHub repository uk-agents/uk-legal-plugins (9 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,455 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
brand-safety-compliance
Scans outbound copy or creator-submitted content for 6 compliance red lines — medical/efficacy, exaggeration/absolute, beauty-permanence, financial/income, fake-scarcity, fake-rapport — and returns a block/warn verdict with fix suggestions. Use when the user asks to check, scan, review, or vet copy before sending, or…
ask
Answer a question from a finished study, citing back into its evidence, and say plainly when the study does not cover it.
compare
Set two term tables against each other — same concept different term, same term different concept, and what each covers that the other lacks.
enablement-course
Assemble an internal AI enablement course for a company's own employees, sized to where they actually are rather than where a vendor deck assumes they are. Produces the session plan, per-session content and exercises, a facilitator guide for a non-expert, and a way to tell whether it worked. Builds on the tech stack…
study-deps
Use when pulling upstream source or cloning a dependency at its installed version to study internals, read code, or create pinned worktrees.
brief
Use when confusion is only “huh,” “wait, what,” “sorry, you lost me,” or “slow down; explain simply and keep it short.”.