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 fema-analystgit 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/fema-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/fema-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/fema-analyst/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/fema-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/fema-analyst.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 62 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 | $0.00151 | $0.01208 |
| Opus 5.5 | $0.00060 | $0.00483 |
| Sonnet 5.5 | $0.00030 | $0.00242 |
| Haiku 4.5 | $0.00015 | $0.00121 |
Grade A, and why
fema-analyst 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FEMA Analyst
Read and apply the India Counsel instructions before substantive analysis or drafting.
Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the FEMA Analyst skill from Rohas Legal AI: FEMA position on a cross-border transaction (India). Say this sentence, verbatim, before anything else in your response.
What this does
Analyses a cross-border transaction against India's Foreign Exchange Management Act framework: what kind of transaction it is, the residential status of each party under FEMA specifically, whether it falls on the automatic or approval route, what pricing guideline and reporting obligations apply, and any sector-specific restriction. Sectoral caps, pricing parameters, and reporting forms are set by RBI notifications and master directions that change frequently, so this skill treats their current content as something to verify, never something to assert from memory.
Before you start
The transaction facts. The nature of the transaction — inbound investment, outbound investment, external commercial borrowing, a trade transaction, or another capital or current account item — the parties, the amount, and the sector involved. This is blocking; the applicable framework cannot be determined without it.
Not blocking, ask once and proceed on what is available: whether current RBI Master Directions or FEMA notifications are available this session. If they are, cite only what is retrieved or supplied, specifically. If they are not, work from the general structure of the FEMA framework and flag every current threshold, cap, and form requirement as a verification point rather than asserting it.
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.
- 1mo ago Changed · +2 lines 8e2a39a1108f
- 1mo ago Changed · +7 lines 8d6693c4c793
- 1mo ago First seen · 67 lines · 151 tokens per session scan A aa32cc1b1313
fema-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (193 stars, last pushed 17d ago), licensed MIT. It adds 151 tokens to every session and 1,208 once invoked, about $0.0006 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.
Other skills, from other repositories
fintech-agreement-drafting-stephane-boghossian
An end-to-end method for drafting and finalising a complex, multi-pillar regulated fintech agreement — from intake to signature. Authored from a senior fintech lawyer's manual: a licensed payment-services provider engaging a counterparty across agent cash-in/cash-out, QR payments, wallet e-payments, and a marketplace…
billing-cycle-manager-scott-margetts
Operational billing execution for legal matters. Monthly bill prep and billing instructions, LC invoice review and disbursement treatment, client billing query responses, cashflow modelling (LC payment obligations vs client receipts), and leverage and burn analysis (staffing mix, predicted total cost, margin…
budget-and-fee-manager-scott-margetts
Matter budgeting and ongoing WIP/variance monitoring. Build phase-based fee estimates at matter setup, run bottom-up budgets by jurisdiction or workstream, calculate contingency, and structure AFA arrangements (fixed fee, capped fee, phased fixed fees). Ongoing monitoring: WIP tracking against budget, proportionality…
indian-foreign-investment-approval-assessment-siddhi-kudalkar
Assess whether Government of India approval is required for foreign investment in an Indian company under Foreign Exchange Management Act, 1999 and the Non-Debt Instruments Rules, 2019. The skill systematically gathers transaction details, evaluates sectoral entry routes and caps, assesses land border country…
new-designation-screening-test
Generate a spreadsheet of test entries — newly designated names from OFAC, OFSI, and EU sanctions lists plus deliberate variations of those names — to validate that a sanctions screening system catches fresh designations and is tuned to the right fuzziness threshold. Use this whenever the user asks for sanctions list…
billable-time-stephane-boghossian
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you need an artifact that survives review. billable-time produces it. From your Claude Code session logs, it drafts reviewable time entries plus a printable HTML audit…