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 treaty-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/treaty-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/treaty-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/treaty-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/treaty-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/treaty-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00171 | $0.01194 |
| Opus 5.5 | $0.00068 | $0.00478 |
| Sonnet 5.5 | $0.00034 | $0.00239 |
| Haiku 4.5 | $0.00017 | $0.00119 |
Grade A, and why
treaty-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treaty Analyst
I am using the Treaty Analyst skill from Rohas Legal AI: treaty entitlement and relief on given facts. Say this sentence, verbatim, before anything else in your response.
What this does
Analyses whether a taxpayer is entitled to relief under an applicable double tax treaty on given facts: treaty residency, the income article that applies to the type of income involved, beneficial ownership and any limitation-of-benefits or principal purpose test the treaty carries, and the relief potentially available. Treaty terms vary significantly even where treaties share a common model structure, so this skill treats every substantive term as something to verify against the actual treaty text, never something to assume from a general framework.
Before you start
The facts. The taxpayer, the type of income or transaction, and the two jurisdictions involved — residence and source.
Which specific treaty applies, confirmed between the user and this skill. Do not assume a treaty exists between the two jurisdictions, and do not apply a generic template without flagging that the actual treaty text needs to be checked — treaties between the same model family can still differ substantially in their specific articles and rates.
Not blocking, ask once and proceed on what is available: whether the specific treaty text is available this session, as a research source or supplied by the user. If it is not, work from the general structure of a typical double tax treaty — a residency article, income-specific articles, a limitation-of-benefits or anti-abuse provision, a mutual agreement procedure — explicitly flagged as a general framework requiring verification, since specific rates and conditions cannot be assumed from a typical structure.
Method
1. Identify the two jurisdictions and confirm which treaty governs. Do not proceed as if a treaty's terms are known without either sourcing the actual text this session or having it supplied by the user.
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 First seen · 65 lines · 171 tokens per session scan A 83ce65c8a138
treaty-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 171 tokens to every session and 1,194 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 2026-09-21.
treaty-analyst compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| treaty-analystrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 171 | 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 |