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-ai --skill contract-snapshotgit clone --depth 1 https://github.com/LegalQuants/lq-aiWrote 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-ai/contract-snapshot)<a href="https://agentmods.dev/skills/legalquants/lq-ai/contract-snapshot"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/contract-snapshot/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-ai/contract-snapshot"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/contract-snapshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.01519 |
| Opus 5 | $0.00047 | $0.00759 |
| Sonnet 5 | $0.00019 | $0.00304 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
contract-snapshot 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 13d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Snapshot
A reference skill for the M3-C output_format: table mode. Produces a side-by-side grid of the same questions across N contracts — the in-house lawyer's "compare clauses across N agreements" workflow. Each cell carries a citation back to the source document, and failed extractions render as not found rather than confidently-wrong text.
When this skill applies
Apply when the user wants to compare a small number of well-defined questions across a corpus of similar contracts:
- "What is the term, survival, and governing law across these 5 NDAs we're tracking?"
- "Pull out the payment terms, IP ownership, and termination triggers across these 10 MSAs."
- "For my Q3 portfolio review, I need a grid of these 30 vendor contracts' liability caps."
Do not apply this skill to:
- Single-document review — use the appropriate document-specific skill (
nda-review,msa-review-saas, etc.). - Free-form chat against contracts — that's the regular Chat surface.
- Tasks where the questions aren't well-defined upfront — the column queries must be specific enough to extract from each row's source document; vague queries produce poor cells.
Inputs
The skill takes a set of documents (selected via the Tabular Review UI from a Knowledge Base, a Project, or a free file selection). The four columns above run as Citation Engine-grounded extractions against each document.
To adapt this skill for a different contract type (e.g., MSAs), fork the skill and rewrite the four column queries. Keep them short, specific, and quote-asking — the Citation Engine works best when the model is encouraged to quote rather than paraphrase.
Per-column overrides
This skill demonstrates the two per-column overrides M3-C1 supports:
ensemble_verification: trueon the Survival column. Survival is the load-bearing economic term in confidentiality agreements (a 3-year confidentiality term with a 10-year survival is very different from one with no survival), so cells in this column run through Stage 4 of the Citation Engine cascade — three judges debating whether the cell value is faithful to its citation. Higher cost, higher confidence.minimum_inference_tier: 3on the Governing Law column. The skill-level floor is Tier 2 (commercial inference). Governing-law extraction is the column most likely to surface counterintuitive answers (e.g., a contract drafted under California law but with a Delaware forum-selection clause); routing this column to Tier 3+ avoids the cheapest models' tendency to collapse the two into one answer.
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.
- 13d ago First seen · 116 lines · 94 tokens per session scan A 8dc4ddce064b
contract-snapshot is a skill published in the GitHub repository LegalQuants/lq-ai (136 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 1,519 once invoked, about $0.0005 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
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
handbook-updates
Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…