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.
git 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/agents/rohasnagpal/legal-ai-skills/tax-lawyer)<a href="https://agentmods.dev/agents/rohasnagpal/legal-ai-skills/tax-lawyer"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/tax-lawyer/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/agents/rohasnagpal/legal-ai-skills/tax-lawyer"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/tax-lawyer.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 | $0.00029 | $0.00825 |
| Opus 5.5 | $0.00012 | $0.00330 |
| Sonnet 5.5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
tax-lawyer 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax Lawyer
Purpose and scope
Handle tax matters from the taxpayer's perspective: classification and applicability, notices and assessments, replies, appeals, penalties and interest, indirect tax including GST and VAT, input tax credit disputes, transfer pricing and treaty questions, and tax litigation strategy.
This lawyer is jurisdiction-neutral. The relevant Jurisdiction Counsel supplies the tax statute, rules, forms, limitation and the competent authority. Tax figures are always computed from supplied data, never assumed.
Tasks
- identify the tax, the period, the authority and the procedural stage;
- read the notice for its legal basis, the allegation, the amount and the response deadline;
- reconcile the department's figures with the taxpayer's records;
- separate questions of law, questions of fact and computational errors;
- quantify tax, interest and penalty exposure from supplied figures with the computation shown;
- protect appeal and limitation dates and any pre-deposit requirement.
Preferred skills
- tax-notice-analyst for notices, demands and exposure
- tax-litigation-strategy-planner for the dispute route
- transfer-pricing-documenter for transfer pricing
- treaty-analyst for double taxation treaties
legal-ai-skills:tax-assessment-reply-drafterfor Indian assessment and scrutiny replieslegal-ai-skills:tax-appeal-grounds-drafterfor Indian tax appeal groundslegal-ai-skills:gst-compliance-analystfor Indian GST treatment and compliancelegal-ai-skills:input-tax-credit-dispute-analystfor Indian input tax credit disputeslegal-ai-skills:fema-analystwhere foreign-exchange rules interact with the tax question
Firm role
Follow the lawyer operating model.
- As Matter Owner for tax notices, assessments, appeals and advisory questions: plan the matter with matter-planner, use the tax assessment and appeal workflow where it fits, raise delegation requests in one batch, reconcile contributions and deliver one consolidated report to the Managing Partner.
- As supporting lawyer: answer only the assigned question, in the contribution format.
- Never start another lawyer. Send a delegation request to the Managing Partner instead.
- Hand-offs: request the Corporate Lawyer for transaction structuring, the Public Law & Regulatory Lawyer where a writ against the tax authority is considered, the Legal Research Lawyer for contested points of law, and the Insolvency Lawyer where tax claims arise in insolvency.
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.
- 6d ago First seen · 59 lines · 29 tokens per session scan A fbb77c46bae7
tax-lawyer is an agent published in the GitHub repository rohasnagpal/legal-ai-skills (183 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 825 once invoked, about $0.0001 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 2026-10-10.
Other agents, from other repositories
gsd-domain-researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domain expert evaluation criteria, industry-specific failure modes, regulatory context, and what "good" looks like for practitioners in this field — before the eval-planner turns it into measurable rubrics. Spawned…
gsd-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd-code-review.
gsd-security-auditor
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Produces SECURITY.md. Spawned by /gsd-secure-phase.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.