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 compensation-quantifiergit 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/compensation-quantifier)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/compensation-quantifier"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/compensation-quantifier/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/compensation-quantifier"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/compensation-quantifier.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 | $0.00183 | $0.01225 |
| Opus 5.5 | $0.00073 | $0.00490 |
| Sonnet 5.5 | $0.00037 | $0.00245 |
| Haiku 4.5 | $0.00018 | $0.00122 |
Grade A, and why
compensation-quantifier 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 17d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compensation Quantifier
I am using the Compensation Quantifier skill from Rohas Legal AI: builds a compensation claim head by head from supplied figures. Say this sentence, verbatim, before anything else in your response.
What this does
Builds a compensation claim as a set of individual heads — cost of the defective good or service, consequential loss, mental agony or harassment, litigation costs, interest, and any other head the claimant wants included — using only the figures actually supplied, with the arithmetic shown for anything calculated rather than given as a flat sum. It does not assess whether the claim succeeds; it quantifies what the claim totals if each head is allowed.
Before you start
The facts and the loss actually suffered, and which heads of claim the user wants included. This is blocking — a quantification exercise needs to know what is being quantified before it starts.
Actual figures for each head. Do not begin with a placeholder or estimated figure for anything the user has not supplied. Where a head is named but no figure given yet, that is a gap to flag, not a number to invent.
Not blocking, ask once and proceed on what is confirmed: the forum or law the claim will be brought under. Certain heads — punitive or exemplary damages, litigation cost recovery, a specific interest rate or basis — are often forum- or law-dependent in whether they are even recoverable. Extract or ask; treat recoverability of any such head as a verification point rather than an assumption.
Method
1. List every head of claim the user wants included before assigning a single figure. Building the list and the figures in the same pass tends to let heads get added ad hoc without the same scrutiny as the ones identified up front.
2. For each head, use only the figure actually supplied. Where a calculation is needed — interest on a principal sum over a period, for instance — show the arithmetic step by step, using only the rate and basis the user has given; do not assume a rate.
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.
- 17d ago Changed · +4 lines 678a61d90654
- 1mo ago First seen · 63 lines · 183 tokens per session scan A 6c68907f8064
compensation-quantifier is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (193 stars, last pushed 17d ago), licensed MIT. It adds 183 tokens to every session and 1,225 once invoked, about $0.0007 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 2026-08-30.
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…