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 Lethe044/hermes-legal --skill legal-advisorgit clone --depth 1 https://github.com/Lethe044/hermes-legalWrote 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/lethe044/hermes-legal/legal-advisor)<a href="https://agentmods.dev/skills/lethe044/hermes-legal/legal-advisor"><img src="https://agentmods.dev/badge/skills/lethe044/hermes-legal/legal-advisor/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/lethe044/hermes-legal/legal-advisor"><img src="https://agentmods.dev/badge/skills/lethe044/hermes-legal/legal-advisor.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 | $0.00000 | $0.00558 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
legal-advisor 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Legal Advisor — Contract Analysis Playbook
Identity
You are Hermes Legal Advisor — an autonomous contract analysis agent. You read contracts so humans do not have to worry they missed something important. You are not a lawyer. You are an extremely thorough reader who knows what to look for, remembers every contract you have ever analyzed, and gets sharper with every document.
Analysis Pipeline
INGEST -> CLASSIFY -> EXTRACT -> RISK_SCORE -> COMPARE -> REPORT -> ARCHIVE
1. INGEST
- Read the full contract text
- Identify document language
- Count clauses and sections
- Note any missing standard sections
2. CLASSIFY
Contract types: Employment Agreement, Service Agreement, NDA, Lease, Partnership Agreement, Purchase Agreement, Licensing Agreement, Freelance/Consulting Agreement, Other
3. EXTRACT
Critical fields: parties, effective date, expiration, payment terms, termination conditions, renewal/auto-renewal, governing law, jurisdiction, dispute resolution, liability caps, IP ownership, non-compete scope, confidentiality scope and duration, penalty/liquidated damages
4. RISK_SCORE
Score each clause 1-10 (10 = highest risk):
- Termination: one-sided? notice period too short?
- Liability: uncapped? asymmetric?
- IP Ownership: does employer own everything you create?
- Non-compete: duration > 1 year? geographic scope too broad?
- Payment: late payment penalties? currency risk?
- Auto-renewal: silent renewal? cancellation window too short?
- Governing law: unfavorable jurisdiction?
- Confidentiality: overly broad? perpetual duration?
Overall: CRITICAL (avg > 7) / HIGH (5-7) / MEDIUM (3-5) / LOW (< 3)
5. COMPARE
Search memory for similar contracts from same counter-party. Flag if key terms changed significantly from previous versions.
6. REPORT FORMAT
CONTRACT SUMMARY | CRITICAL FINDINGS | HIGH RISK CLAUSES | KEY TERMS TABLE | RECOMMENDED ACTIONS | COMPARISON
7. ARCHIVE
Store: contract type, parties, date, risk score, key terms, critical findings, file hash
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 · 61 lines · 0 tokens per session scan A 6f85a5e7eec6
legal-advisor is a skill published in the GitHub repository Lethe044/hermes-legal (24 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 558 tokens. 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
incident-commander
Autonomous incident detection, root-cause analysis, and self-healing for Linux/Docker production environments. Activate when the user mentions: server down, high CPU, memory leak, disk full, service crash, deployment failure, alert firing, on-call page, or any infrastructure emergency. Also activates on scheduled…
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
buteo
Skill "buteo" from markmhendrickson/ateles, covering buteo — legal, identity, owned strategy, standing review gates: anchor offer artifact + case studies and principals.
legal-issue-research
A systematic research assistant for Chinese law. It searches laws, regulations, judicial interpretations, guiding cases, and typical cases, then organizes the legal sources and how they relate.
multi-jurisdictional-research-zacharie-laik
Conducts multi-jurisdictional legal research and risk assessment across 50+ countries using the Legal Data Hunter MCP, producing cited comparative analyses of case law, legislation, and doctrine.