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 settlement-evaluatorgit 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/settlement-evaluator)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/settlement-evaluator"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-evaluator/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/settlement-evaluator"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-evaluator.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 | $0.00172 | $0.01221 |
| Opus 5.5 | $0.00069 | $0.00488 |
| Sonnet 5.5 | $0.00034 | $0.00244 |
| Haiku 4.5 | $0.00017 | $0.00122 |
Grade A, and why
settlement-evaluator 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Settlement Evaluator
I am using the Settlement Evaluator skill from Rohas Legal AI: tests a settlement offer against the litigation alternative. Say this sentence, verbatim, before anything else in your response.
What this does
Tests one specific settlement offer against the realistic alternative of continuing to litigate or arbitrate: an expected-value comparison with the arithmetic shown, then layered with what the raw numbers miss — the certainty a settlement buys, the client's actual risk tolerance and priorities, and any hidden cost in the offer's own conditions. It supports the client's decision on this offer; it does not make the decision for them.
Before you start
The settlement offer's actual terms. Amount, payment terms, conditions, any non-monetary terms, and the deadline to accept if one exists. Blocking.
The realistic litigation alternative. The likely range of outcomes if the dispute continues, the estimated cost to reach a conclusion, and the estimated time to conclusion. Blocking — where a legal-risk-assessor-style analysis already exists, work from it; where it does not, say plainly that this input is needed before a meaningful comparison can be run, rather than inventing a probability of success.
Not blocking, ask once and proceed on what is confirmed: the client's risk tolerance and priorities — certainty versus upside, cost sensitivity, time sensitivity, reputational considerations. These determine how the comparison should be weighted, not just what the raw numbers say.
Method
1. State the settlement offer precisely — amount, payment terms, conditions, non-monetary terms such as confidentiality or non-disparagement, and the acceptance deadline if any.
2. State the realistic litigation alternative as a range — best case, likely case, worst case — grounded in supplied analysis. Do not invent a probability of success that is not otherwise supported; if the range is not yet established, say that a risk assessment is needed first rather than filling the gap with an assumption.
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.
- 2mo ago First seen · 69 lines · 172 tokens per session scan A 8a304de827da
settlement-evaluator is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 1,221 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 2026-09-03.
settlement-evaluator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| settlement-evaluatorrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 172 | 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 |