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 bart-statutory-reference-checkergit 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/bart-statutory-reference-checker)<a href="https://agentmods.dev/skills/legalquants/lq-skills/bart-statutory-reference-checker"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/bart-statutory-reference-checker/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/bart-statutory-reference-checker"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/bart-statutory-reference-checker.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 | $0.00032 | $0.01619 |
| Opus 5 | $0.00016 | $0.00809 |
| Sonnet 5 | $0.00006 | $0.00324 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
bart-statutory-reference-checker 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BART: Statutory Reference Checker
When to Use
- Auditing Singapore legal documents for statutory citation accuracy
- Verifying that cited Singapore statutes exist and are properly referenced
- Checking if statutory references have been amended or repealed
- Academic work on Singapore legislation
- Pre-filing review of submissions
How It Works
Backend (Python + Next.js frontend)
- Semantic search over Singapore statute text using Legal-BERT/GEMMA
- BM25 + reranker for precise citation matching
- ChromaDB vector store for fast retrieval
- Word Add-in integration for in-document checking
Word Add-in Features
- Scan entire document for statutory references
- Validate against live Singapore statute database
- Flag missing amendments or repealed provisions
- Suggest correct chapter/section references
- Hover tooltips with current text of cited provisions
Output
Report showing:
- All statutory references found
- Validation status (valid, amended, repealed, not found)
- Suggested corrections where needed
A verified or valid result means "the cited reference was found in the source statute database at the time of lookup" — not "this citation is authoritative" and not "this submission is fit to file." Every finding is a research aid that requires lawyer verification.
Audience and Work Shape
Audience: Singapore-qualified lawyers, paralegals, and academic users running a statutory cite-check on a Singapore-law document (typically a submission, opinion, or academic paper). Not for unsupervised drafting, non-lawyer use, or non-Singapore documents.
Work shape: Pattern-Matched Review. Claude (or the BART pipeline) surfaces candidate citation mismatches; the lawyer adjudicates. Output is a list of findings, not a sign-off.
Inputs and Halt-on-Missing
Required inputs before running:
- The target document (path or selection) containing the citations to check.
- The intended statute snapshot date (the version of the Singapore statute book the user wants citations checked against).
- The scope of the check (whole document, named section, or selection).
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 · 113 lines · 32 tokens per session scan A 78a1e95ed8e8
bart-statutory-reference-checker is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,619 once invoked, about $0.0002 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
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
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…
akf-trust-metadata-v2
AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…
software-copyright
A guided workflow for preparing Chinese software copyright registration materials from a real software project. It produces drafts such as application details, source-code documents, and a user manual.
court-sms
A workflow that reads court text messages or delivery links, extracts case details, downloads court documents, and files them in the matching case folder.
contract-gen
A legal drafting workflow that collects the key facts and generates a complete contract or agreement in Markdown, with an optional Word version. It can adapt terms to one party’s position within legal limits.