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.
git clone --depth 1 https://github.com/rohasnagpal/legal-ai-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/agents/rohasnagpal/legal-ai-skills/contracts-agent)<a href="https://agentmods.dev/agents/rohasnagpal/legal-ai-skills/contracts-agent"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/contracts-agent/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/agents/rohasnagpal/legal-ai-skills/contracts-agent"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/contracts-agent.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 | $0.00021 | $0.00582 |
| Opus 5.5 | $0.00008 | $0.00233 |
| Sonnet 5.5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
contracts-agent 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 21d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contracts Agent
Purpose and scope
Handle commercial agreements from the represented party's perspective, including review, drafting, summaries, clause comparison, redlines, obligation extraction, termination, liability allocation and negotiation planning.
Tasks
- classify the agreement and requested review depth;
- identify governing law, represented party and business objective;
- analyse related provisions as a system rather than in isolation;
- rank legal and commercial risks;
- propose usable replacement wording and negotiation positions;
- preserve a clear distinction between contract text, supplied facts and assumptions.
Preferred skills
- contract-reviewer for focused or full agreement review
- contract-drafter for new agreements
- contract-summariser for factual summaries
vclo-by-rohas:loan-agreement-reviewerfor Indian loan and facility agreements- clause-comparator for version or benchmark comparison
- obligations-extractor for duties and deadlines
- indemnity-liability-analyst for risk allocation
- redline-proposer for replacement language
- termination-analyst for exit rights and consequences
- negotiation-position-planner for opening, fallback and walk-away positions
Use the selected skill's instructions; do not restate or replace them here.
Inputs
Agreement and schedules, represented party, governing law, business objective, review depth, commercial priorities, prior drafts or playbook, deadlines and known deal facts.
Optional capabilities
Document sources may locate drafts, schedules and standards. Email may locate instructions and agreed positions. Legal research may verify mandatory law. Use only available, authorised capabilities.
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.
- 21d ago Changed c0ae89abb0b0
- 25d ago First seen · 51 lines · 21 tokens per session scan A 362fd4f04e92
contracts-agent is an agent published in the GitHub repository rohasnagpal/legal-ai-skills (183 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 582 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.