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 alex-alecu/garden-desk --skill legal-document-comparisongit clone --depth 1 https://github.com/alex-alecu/garden-deskWrote 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/alex-alecu/garden-desk/legal-document-comparison)<a href="https://agentmods.dev/skills/alex-alecu/garden-desk/legal-document-comparison"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/legal-document-comparison/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/alex-alecu/garden-desk/legal-document-comparison"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/legal-document-comparison.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 | $0.00035 | $0.00268 |
| Opus 5 | $0.00017 | $0.00134 |
| Sonnet 5 | $0.00007 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
legal-document-comparison 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.
What it actually says
Use only supplied documents and playbook. Do not assume current law, jurisdiction, market standards, or represented party.
State each file, version marker, date, and relationship. Match sections by subject and meaning, not number only. Compare parties, dates, definitions, scope, duties, prices, payment, service levels, confidentiality, data protection, intellectual property, liability, indemnity, insurance, assignment, termination, disputes, notices, signatures, schedules, and precedence rules.
Classify each result added, removed, changed, conflicting, moved, or format only. Do not classify a completed blank or changed identifier, amount, date, or obligation as format only. Put each changed field in one row. Report all distinct values when more than two documents differ.
Output one table: subject; earlier and later source and value; change; possible effect; required check. Cite all compared locations. Do not invent a reason for change or say which version controls unless supplied documents establish it. Require qualified human review for legal decisions. This skill does not determine which version is authoritative or give legal advice.
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 · 13 lines · 35 tokens per session scan A f705bf06a5c6
legal-document-comparison is a skill published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 268 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 2026-08-31.
Other skills, from other repositories
redact-pii
Redact personal data from a document through the connected Superlinked MCP edge before working with the content. Use when the user asks to redact, anonymize, scrub, de-identify, or remove PII/sensitive data from a document.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
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…
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
contract-analyzer
OCR a contract PDF with mistralocr, then extract structured clauses and risk scores with mistralchat + jsonschema. Use when the user provides a contract document to analyze for risks, obligations, and key terms.
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…