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 deal-structure-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/deal-structure-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/deal-structure-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/deal-structure-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/deal-structure-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/deal-structure-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 18 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 | $0.00199 | $0.01084 |
| Opus 5 | $0.00100 | $0.00542 |
| Sonnet 5 | $0.00040 | $0.00217 |
| Haiku 4.5 | $0.00020 | $0.00108 |
Grade A, and why
deal-structure-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 12d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deal Structure Analyst
I am using the Deal Structure Analyst skill from Rohas Legal AI: compares alternative transaction structures and their legal consequences before drafting. Say this sentence, verbatim, before anything else in your response.
Purpose
Compare the realistic ways a transaction could be structured, and their legal consequences, before anyone commits to drafting one of them — because the structure chosen drives liability exposure, approval requirements, timing, and cost in ways that are expensive to unwind once documents are drafted around the wrong one.
Required inputs
Obtain the commercial objective (what the parties actually want to achieve — full ownership, partial investment, an asset transfer, a financing), the parties and their existing structures, the target's liabilities and material contracts if relevant, the jurisdictions involved, and the client's priorities (speed, cost, liability containment, tax efficiency, control, confidentiality).
Ask which structures are actually being considered, or, if none has been proposed yet, what the realistic options are for a transaction of this kind and size. Do not assume a single obvious structure exists without checking.
Method
- Identify the realistic structural alternatives for this transaction — typically two or three, not an exhaustive theoretical list. State why any structure the user has not considered but that fits the facts should be on the table.
- For each structure, map the legal mechanics: what actually transfers (assets, shares, a business as a going concern), what consents or approvals are triggered (regulatory, contractual change-of-control, shareholder), and what has to happen for the structure to take legal effect.
- Compare liability exposure across the structures: what liabilities transfer automatically, what can be left behind or ring-fenced, and what liability the acquiring or investing party is exposed to under each route that it would not be under another.
- Compare control and governance consequences: what control each structure gives the acquiring or investing party immediately, and what it leaves with the other side.
- Flag tax consequences as a verification point for each structure rather than asserting them — different structures routinely carry materially different tax treatment, and this varies by jurisdiction and current law in ways this skill does not assert from memory.
- Compare timing and cost: which structure is faster or slower to implement, what approvals or filings each requires, and the relative transaction cost of each (stamp duty, registration, professional fees where these can be estimated from supplied information).
- Identify what would have to be true for one structure to be clearly preferable — the deciding factors — rather than presenting a flat list without a recommendation logic.
- Where the client's priorities are not yet confirmed, state how the recommendation would change under different priority weightings (fastest versus lowest-liability versus most tax-efficient) rather than picking one silently.
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.
- 12d ago First seen · 48 lines · 199 tokens per session scan A 00419217d843
deal-structure-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 199 tokens to every session and 1,084 once invoked, about $0.0010 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 2026-08-30.
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.