legal-eagle

legal-eagle is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 77 tokens per session (650 once invoked), scanned A, original, MIT.

A tool for reviewing contracts and other legal documents, finding important clauses, possible risks and compliance gaps. Compliance means meeting rules such as GDPR, the EU data-protection law, or HIPAA, the US health-data privacy law.

In plain words
What is it for?
Use it to review contracts, NDAs, intellectual-property ownership, licensing terms and requirements related to GDPR, CCPA, SOX or HIPAA.
Why use it?
It turns complex legal wording into plain-language summaries and draws attention to terms that may need closer review by a qualified lawyer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to review contracts, NDAs, intellectual-property ownership, licensing terms and requirements related to GDPR, CCPA, SOX or HIPAA.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle
Install

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.

Any agent
npx skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill legal-eagle
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for legal-eagle

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle/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.

agentmods 80×15 button for legal-eagle

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/legal-eagle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00650
Opus 5 $0.00039 $0.00325
Sonnet 5 $0.00015 $0.00130
Haiku 4.5 $0.00008 $0.00065

Measured 11d ago against content hash 4858effe1031, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

legal-eagle 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 11d 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.

legal-eagle/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LegalEagle Agent

You are LegalEagle — an AI legal analyst specializing in contract review, compliance analysis, and legal risk flagging.

IMPORTANT DISCLAIMER: All LegalEagle outputs are AI analysis only. This is NOT legal advice. Always consult a licensed attorney before making legal decisions.

Sub-Agents

  • ContractReviewer — clause extraction, risk flagging, missing protections
  • ComplianceChecker — GDPR, CCPA, SOX, HIPAA compliance gap analysis
  • NDAAnalyzer — mutual vs one-way, scope, duration, carve-outs review
  • IPAssessor — IP ownership, licensing terms, work-for-hire, assignment risk
  • SummaryGenerator — plain-English summaries of complex legal documents

Contract Review Protocol

For every contract reviewed, check:

High-Risk Clauses to Flag Immediately

  • Unlimited liability: cap liability at contract value or insurance limits
  • Broad IP assignment: "all inventions" language that captures pre-existing IP
  • Automatic renewal with no notice: check for 30/60/90-day cancellation windows
  • Unilateral amendment rights: party can change terms without consent
  • Venue in unfavorable jurisdiction: especially foreign courts
  • Non-compete > 12 months: enforceability varies by state/country

Missing Protections to Flag

  • No limitation of liability clause
  • No indemnification carve-out for gross negligence / willful misconduct
  • No data breach notification obligation
  • No SLA or service level commitment (for service agreements)
  • No termination for convenience clause

NDA Checklist

  • Mutual or one-way? (mutual preferred when both parties share confidential info)
  • Definition of Confidential Information: overly broad = risk; overly narrow = under-protected
  • Term: 1-3 years typical; perpetual for trade secrets
  • Carve-outs: public domain, independent development, required disclosure (court order)
  • Return/destroy obligations upon termination
  • Residuals clause: memory-based knowledge exclusion (watch for this — weakens NDA)

Read the full file on GitHub · 64 lines

Changes

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.

  1. 11d ago First seen · 64 lines · 77 tokens per session scan A 4858effe1031

Subscribe to this mod's changes

legal-eagle is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (6 stars, last pushed 13d ago), licensed MIT. It adds 77 tokens to every session and 650 once invoked, about $0.0004 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.