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 sarfaesi-advisorgit 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/sarfaesi-advisor)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/sarfaesi-advisor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sarfaesi-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/rohasnagpal/legal-ai-skills/sarfaesi-advisor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sarfaesi-advisor.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 | $0.00058 | $0.00902 |
| Opus 5.5 | $0.00023 | $0.00361 |
| Sonnet 5.5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
sarfaesi-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 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SARFAESI Advisor
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 SARFAESI Advisor skill from Rohas Legal AI: SARFAESI enforcement steps and timelines (India). Say this sentence, verbatim, before anything else in your response.
Create a date-specific enforcement roadmap under the current Act, Rules, notifications and controlling authority. Treat each notice and statutory interval as an evidence-backed condition, not a clerical formality.
Required inputs
- Secured creditor identity, authorisation and transaction assignment history
- Borrower, guarantor, account, facility and complete debt calculation
- NPA classification date, basis and applicable regulatory framework
- Security documents, asset title, location, possession and valuation
- CERSAI and other creation, modification and satisfaction records
- Consortium or multiple-creditor holdings and consent status
- Notices, representations, replies, payments, stays and prior proceedings
- Asset occupation, tenancy, agricultural use, statutory dues and exclusions
Method
- Test applicability. Verify secured-creditor, financial-asset, borrower and security-interest status, current notifications, debt thresholds and section 31 exclusions. Confirm the asset and claim fall within the Act.
- Verify enforceability. Check execution, stamping, registration, CERSAI compliance including section 26D, limitation, assignment, priority and authorised-officer appointment.
- Verify default and NPA. Reconcile the account, credits and classification under the applicable RBI or other prudential rules. Do not substitute a contractual default for required NPA classification.
- Prepare section 13(2). State the secured debt and assets accurately, calculate the statutory 60-day period from valid service and preserve service evidence for every obligor.
- Handle representation. Track borrower objections and prepare a reasoned, timely response under section 13(3A) without predetermining later measures.
- Select section 13(4) measures. Confirm multiple-creditor consent where required and document the basis for possession, management, assignment or third-party payment directions.
- Plan possession and section 14. Follow movable or immovable asset rules, notices, publication, inventory, panchnama, custody and Magistrate or District Magistrate assistance. Do not use private force or bypass occupants' lawful claims.
- Plan valuation and sale. Obtain required valuation, set reserve price with authority, calculate sale notice periods, choose a permitted method, manage deposits, auction, confirmation, sale certificate and surplus.
- Map challenges and overlays. Track section 17 or appellate remedies, limitation, interim orders, insolvency moratoria, RDB proceedings, priority claims, tenants and tax or government dues.
- Close the record. Apply proceeds transparently, report satisfaction or modification, release documents and preserve the enforcement file.
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 95bdad36594a
- 1mo ago Changed · +7 lines dde6f5a2e110
- 2mo ago First seen · 47 lines · 58 tokens per session scan A c6358e674c63
sarfaesi-advisor is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 902 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.
sarfaesi-advisor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sarfaesi-advisorrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 58 | Claude Code, Codex |
| fintech-agreement-drafting-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 205 | Claude Code |
| billing-cycle-manager-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 162 | Claude Code, Codex |
| budget-and-fee-manager-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 205 | Claude Code, Codex |
| indian-foreign-investment-approval-assessment-siddhi-kudalkarlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 103 | Claude Code, Codex |
| new-designation-screening-testlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 146 | Claude Code, Codex |
| billable-time-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 219 | Claude Code |