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 esop-scheme-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/esop-scheme-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/esop-scheme-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/esop-scheme-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/esop-scheme-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/esop-scheme-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 50 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00140 | $0.00946 |
| Opus 5 | $0.00070 | $0.00473 |
| Sonnet 5 | $0.00028 | $0.00189 |
| Haiku 4.5 | $0.00014 | $0.00095 |
Grade A, and why
esop-scheme-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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESOP Scheme Drafter
I am using the ESOP Scheme Drafter skill from Rohas Legal AI: ESOP scheme documents and grant letters. Say this sentence, verbatim, before anything else in your response.
What this does
Drafts the scheme document that governs an employee stock option plan and the individual grant letter template used for each grantee — eligibility, pool size, vesting and exercise mechanics, and treatment on leaving the company. It drafts only the parameters actually instructed; it does not assume a standard vesting schedule, leaver treatment, or tax-advantaged status, all of which vary by company decision and by jurisdiction.
Before you start
The scheme parameters. Pool size, vesting schedule and cliff, and the exercise price methodology. Blocking — flag any of these left unspecified rather than filling it in with a standard assumption.
Governing law and jurisdiction. ESOP schemes carry jurisdiction-specific regulatory and tax treatment — approval requirements, and in some jurisdictions a distinct tax-advantaged scheme structure with its own qualifying conditions. Ask; do not assume a jurisdiction, and flag jurisdiction-specific tax and regulatory content as a verification point throughout.
Not blocking, ask once and proceed on what is confirmed: whether this is a fresh scheme or an amendment to an existing one.
Method
1. Confirm the scheme's basic parameters — pool size, vesting schedule, cliff period, and exercise price methodology — using only what is specified. Flag any gap rather than defaulting to a common structure such as a four-year vest with a one-year cliff, since the client may intend something different.
2. Draft the scheme document structure: eligibility, grant authority (board or committee), vesting mechanics, exercise mechanics and window, treatment on termination, change of control treatment, and administration provisions.
3. Do not assume the scheme qualifies for any specific tax-advantaged structure without the user confirming both eligibility and intent. Qualifying conditions for tax-favourable option schemes are technical and jurisdiction-specific; flag this as a verification point rather than drafting as though qualification is settled.
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.
- 9d ago First seen · 59 lines · 140 tokens per session scan A 82b9036aa18f
esop-scheme-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 140 tokens to every session and 946 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.