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 transfer-pricing-documentergit 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/transfer-pricing-documenter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/transfer-pricing-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/transfer-pricing-documenter/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/transfer-pricing-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/transfer-pricing-documenter.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 | $0.00156 | $0.01140 |
| Opus 5.5 | $0.00062 | $0.00456 |
| Sonnet 5.5 | $0.00031 | $0.00228 |
| Haiku 4.5 | $0.00016 | $0.00114 |
Grade A, and why
transfer-pricing-documenter 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transfer Pricing Documenter
I am using the Transfer Pricing Documenter skill from Rohas Legal AI: transfer pricing documentation and benchmarking record. Say this sentence, verbatim, before anything else in your response.
What this does
Documents an intercompany transaction for transfer pricing purposes: a functional analysis of what each party does, owns, and risks; a transfer pricing method selected and reasoned from that analysis; and a benchmarking record testing the actual result against comparables. It organises the analysis and documents it in the form a transfer pricing file requires; it does not itself source external comparable-company data, and it does not assume a specific jurisdiction's method hierarchy, threshold, or safe harbour without that being confirmed.
Before you start
The intercompany transaction facts. The related parties and their relationship, the nature of the transaction — sale of goods, services, royalty, financing, or another category — and the pricing or terms actually used.
The governing transfer pricing framework and jurisdiction. Ask; do not assume OECD Guidelines apply wholesale or that any specific jurisdiction's rules govern without confirming. Documentation requirements, method hierarchy, and safe harbours are law-specific even where the underlying structure is similar across regimes.
Not blocking, ask once and proceed on what is supplied: whether comparable or benchmarking data is already available, or needs to be sourced separately. This skill documents and organises the analysis; it works from comparables the user supplies or that are sourced this session, not from invented benchmarks.
Method
1. Confirm the related-party relationship and why it triggers transfer pricing rules — the ownership or control basis for treating the parties as related. State it precisely as given; do not assume a specific ownership percentage threshold applies without flagging that the threshold is jurisdiction-specific.
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 · 71 lines · 156 tokens per session scan A d28724c545fb
transfer-pricing-documenter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 156 tokens to every session and 1,140 once invoked, about $0.0006 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.
transfer-pricing-documenter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| transfer-pricing-documenterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 156 | 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 |