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 vignesh2027/Claude-Agentic-Skills2.0-version --skill legal-eaglegit clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-versionWrote 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/vignesh2027/claude-agentic-skills2.0-version/legal-eagle)<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.
<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>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 | $0.00077 | $0.00650 |
| Opus 5 | $0.00039 | $0.00325 |
| Sonnet 5 | $0.00015 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
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.
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)
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.
- 11d ago First seen · 64 lines · 77 tokens per session scan A 4858effe1031
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.
Other skills, from other repositories
compliance-checker
Check compliance with standards — ISO 27001, SOC 2, PCI-DSS, HIPAA, and NIST frameworks.
contract-generator
Draft professional legal contracts — NDAs, service agreements, employment contracts, and SaaS terms with customizable clauses.
gdpr-helper
Navigate GDPR compliance — data mapping, DPIAs, consent flows, breach notification templates, and privacy policies.
policy-drafter
Draft organizational policies — HR policies, data governance, acceptable-use, and regulatory compliance documents.
security-policy
Write information security policies — acceptable-use, incident response, data classification, and access control.
soc2-helper
Prepare for SOC 2 audits — control mapping, evidence collection, gap analysis, and audit narrative writing.