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 rohasnagpal/legal-ai-skills --skill settlement-deed-draftergit 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/skills/rohasnagpal/legal-ai-skills/settlement-deed-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/settlement-deed-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-deed-drafter/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/rohasnagpal/legal-ai-skills/settlement-deed-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-deed-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00734 |
| Opus 5.5 | $0.00019 | $0.00294 |
| Sonnet 5.5 | $0.00010 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
settlement-deed-drafter 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 2mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Settlement Deed Drafter
I am using the Settlement Deed Drafter skill from Rohas Legal AI: family and separation settlement deeds, with child welfare and non-waivable rights preserved. Say this sentence, verbatim, before anything else in your response.
Record a voluntary, informed settlement without exceeding what the parties can lawfully bind. Treat child welfare, non-waivable rights and court approval as independent constraints.
Required inputs
- Jurisdiction, relationship, proceedings and existing orders
- Parties, children, legal representatives and signing capacity
- Full agreed heads plus expressly unresolved issues
- Financial disclosure, assets, debts, income, tax and valuation material
- Child arrangements, support, education and specified direct costs
- Property title, possession, loans, security interests and transfer mechanics
- Claims, complaints, protective orders and implementation deadlines
- Safety, coercion, independent-advice and confidentiality concerns
Do not draft a final deed from headline terms if essential mechanics remain undecided.
Method
- Confirm authority and consent. Verify capacity, voluntariness, independent advice, disclosure, court-approval needs and whether direct negotiation is safe.
- Define scope and status. State parties, background, proceedings, effective date, interim or final nature, admissions position and relationship to existing orders.
- Draft child terms. Specify parenting time, contact, decisions, travel, information, support and review while preserving the court's welfare jurisdiction and the child's independent rights.
- Draft support terms. State amount, commencement, method, indexation, duration, direct expenses, arrears, security, review and variation. Reconcile the calculation schedule.
- Draft property implementation. Identify assets and debts exactly; allocate title, possession, income, costs, taxes, refinancing, releases, documents, third-party consents and long-stop dates.
- Address personal property and benefits. Cover household items, valuables, insurance, pension, equity, business interests, digital assets and jurisdiction-specific property such as stridhan where applicable.
- Calibrate releases. Define released claims and carve out child rights, enforcement, fraud, undisclosed assets and rights that cannot lawfully be waived.
- Close proceedings. Specify petitions, consent orders, withdrawals, quashing or compounding steps only where lawful, costs, cooperation and sequencing.
- Plan default and change. Include notices, cure, interest, indemnity where lawful, enforcement, review and dispute resolution without blocking urgent protective relief.
- Check execution. Verify stamping, registration, notarisation, witnesses, counterparts, electronic signing and court-filing requirements.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 49 lines · 48 tokens per session scan A e60ae55db13a
settlement-deed-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 734 once invoked, about $0.0002 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 2026-09-03.
settlement-deed-drafter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| settlement-deed-drafterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 48 | Claude Code, Codex |
| korean-lawchrisryugj/korean-law-mcp | Skill | 2.9k | 7d ago | MIT | A | 85 | Claude Code |
| engagement-terms-billing-guidelineslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 180 | Claude Code, Codex |
| founder-agreement-drafting-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 194 | Claude Code |
| matter-intake-scoping-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 145 | Claude Code, Codex |
| ai-governance-reviewer-carl-ditzlerlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 121 | Claude Code, Codex |
| bacen-compliance-sentinel-rafael-mastronardilawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 252 | Claude Code, Codex |