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 will-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/will-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/will-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/will-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/will-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/will-drafter.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 | $0.00053 | $0.00771 |
| Opus 5.5 | $0.00021 | $0.00308 |
| Sonnet 5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
will-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 5d 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.
Will Drafter
I am using the Will Drafter skill from Rohas Legal AI: wills, with execution and attestation requirements set out. Say this sentence, verbatim, before anything else in your response.
Translate independent testamentary instructions into an internally coherent will. Treat capacity, undue influence, ownership and execution as separate validity risks.
Required inputs
- Testator identity, age, domicile, residence, citizenship and family circumstances
- Marriage history, dependants, children and vulnerable beneficiaries
- Asset and liability inventory with ownership, location and beneficiary designations
- Prior wills, codicils, trusts, gifts, nominations and succession agreements
- Specific gifts, residue, substitutes, conditions and survivorship preferences
- Executor, trustee, guardian and alternate appointments
- Business, digital asset, pet, funeral and charitable wishes
- Relevant tax, forced-heirship, family-provision and personal-law constraints
Obtain instructions directly from the testator where possible and record who is present.
Method
- Fix governing law. Verify testamentary capacity, form, permitted dispositions, family-provision or forced-share rules, revocation, witnesses, registration and conflict-of-laws requirements.
- Assess capacity and influence. Record understanding of the document, estate, beneficiaries and consequences. Escalate concerns about decision-making, dependency, coercion, interpreters or beneficiary involvement.
- Map ownership. Identify what the testator can dispose of, including shares in joint, marital, community, family, trust or business property. Reconcile nominations and survivorship arrangements.
- Design dispositions. Draft specific, pecuniary and charitable gifts, substitutions, survivorship periods, residue and failure-of-gift rules. Avoid gaps that create unintended partial intestacy.
- Protect beneficiaries. Use age-based, education, maintenance, protective or discretionary trusts only with clear trustees, vesting, powers and remainder provisions. Address guardian wishes without overstating binding effect.
- Appoint fiduciaries. Name executors, trustees and alternates; address conflicts, bond, compensation, resignation, replacement and administrative powers under local law.
- Allocate liabilities. Address debts, taxes, expenses, secured property, business obligations and apportionment without promising an unavailable tax outcome.
- Draft revocation and interpretation. Revoke prior wills to the intended extent, define key terms, handle later-born or omitted persons and resolve conflicts across clauses.
- Plan execution. Specify signature, attestation, presence, witness eligibility, notarisation or registration, interpreter and capacity evidence. Prepare a ceremony checklist and execution memorandum.
- Plan custody and review. Record safe storage, copy control, executor notification and review triggers such as marriage, divorce, birth, death, relocation or major asset change.
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.
- 5d ago First seen · 49 lines · 53 tokens per session scan A 5a6f46a58fee
will-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (149 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 771 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 2026-09-21.
Other skills, from other repositories
lawyer-expert
Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.
law-to-markdown
A skill that converts legal provisions and regulatory documents from plain text, PDF, or Word format into Markdown. Markdown is a plain-text format commonly used for structured documents.
federal-court-rules
Use when an agent needs to look up, quote, summarize, cite, or reason from bundled federal court rules, including the Federal Rules of Civil Procedure, Federal Rules of Appellate Procedure, Federal Rules of Evidence, supplemental rules, selected federal district local rules, and selected ECF rules. Provides local…
ma-laws
Use when an agent needs to look up, quote, search, summarize, cite, or reason from the Massachusetts Constitution, Massachusetts General Laws, or Massachusetts Rules of Civil Procedure.
assistant-juridique-fr
Assistant juridique expert en droit français. Recherches, consultations, rédaction d'actes, contre-argumentaires, analyses de contrats et de pièces, veille, vérification et harmonisation de références. Produit des documents Word (computer use) ou des réponses conversationnelles structurées. MCP : OpenLegi, Themia…
invoice-review-compliance
Invoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for in-house legal ops teams managing outside counsel. Review invoices against billing guidelines; flag block billing, prohibited fees, rate violations, staffing violations, late submission. Produce…