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 LegalQuants/lq-skills --skill uk-citation-verificationgit clone --depth 1 https://github.com/LegalQuants/lq-skillsWrote 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/legalquants/lq-skills/uk-citation-verification)<a href="https://agentmods.dev/skills/legalquants/lq-skills/uk-citation-verification"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/uk-citation-verification/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/legalquants/lq-skills/uk-citation-verification"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/uk-citation-verification.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 | $0.00059 | $0.01441 |
| Opus 5 | $0.00030 | $0.00720 |
| Sonnet 5 | $0.00012 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
uk-citation-verification 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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uk-citation-verification
When to Use
- A draft cites UK cases and needs a pre-filing citation audit.
- AI-generated legal text may contain hallucinated authorities.
- A user wants to verify neutral citations, party names, report citations, or quoted passages.
- A cited proposition needs to be tied back to the authority actually retrieved.
This skill verifies existence and citation integrity. It does not decide the merits of the case.
For Scotland, Northern Ireland, tribunal-specific, or devolved materials, identify the applicable official source before treating the citation as verified.
Audience and Work Shape
Audience: UK litigators, trainees, paralegals, and legal researchers checking draft legal text before lawyer review or filing.
Work shape: pattern-matched verification. The skill resolves and classifies citations; it does not decide whether the authority supports a proposition.
Legal Failure Modes
- Legal support, not legal advice: citation existence and integrity checks do not decide merits or legal propositions.
- Privilege/confidentiality: drafts may be privileged or confidential. Use only approved environments or user-supplied/public sources; do not send client drafts to unapproved services.
- Accountability: unresolved, ambiguous, traditional, or lower-confidence authorities remain for lawyer/researcher review.
Access Modes
This skill works in three modes:
- Live source mode - use browser, web search, MCP, API, or other configured access to retrieve public authority sources.
- User-supplied source mode - use judgment PDFs, HTML, text, screenshots, exports, URLs, or pasted source material supplied by the user.
- No-source mode - extract citations and prepare a verification queue, but do not mark citations as verified.
If the source cannot be retrieved or supplied, do not verify from model memory. Mark the item unverified-source-unavailable and ask for a source, URL, export, or connector.
How It Works
1. Extract citations
What ships with it
5 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.
- 12d ago First seen · 144 lines · 59 tokens per session scan A 8565a84c614e
uk-citation-verification is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,441 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
legaltech-expert
Expert in legal technology: contract lifecycle management, e-discovery, AI-assisted legal research, case and matter management, document automation, and compliance tooling. Use when the user mentions legal case or matter management, e-discovery and legal holds, CLM or contract review and obligation tracking, legal…
Brief Section Drafter
Use when drafting a single section of a litigation brief — such as a statement of facts, argument section, standard of review, or conclusion — that is cited to the record, consistent with the case theory, and fully flagged for attorney verification before filing.
Demand Letter
Use when drafting a demand letter for attorney review — running a structured intake, a pre-draft risk gate, and a draft with every legal conclusion, damages figure, and deadline flagged for attorney confirmation before sending.
Litigation Chronology
Use when building a factual timeline for litigation from provided source documents, producing a structured chronology table with citations, disputed/undisputed flags, and gap analysis for attorney review.
Claim Chart
Use when building an element-by-element claim chart — mapping patent claim limitations or the elements of a civil cause of action or affirmative defense against evidence — to produce a structured gap analysis for attorney review.
Discovery Response Workflow
Use when organizing responses to written discovery — document requests, interrogatories, or requests for admission — inventorying each request verbatim into a response tracker, organizing objection candidates and privilege candidates as questions for counsel, planning collection and custodians, and drafting response…