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 tax-assessment-reply-draftergit 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/tax-assessment-reply-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/tax-assessment-reply-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/tax-assessment-reply-drafter/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/tax-assessment-reply-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/tax-assessment-reply-drafter.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 | $0.00176 | $0.01155 |
| Opus 5.5 | $0.00070 | $0.00462 |
| Sonnet 5.5 | $0.00035 | $0.00231 |
| Haiku 4.5 | $0.00018 | $0.00115 |
Grade A, and why
tax-assessment-reply-drafter 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax Assessment Reply Drafter
Read and apply the India Counsel instructions before substantive analysis or drafting.
Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the Tax Assessment Reply Drafter skill from Rohas Legal AI: replies to assessment and scrutiny notices (India). Say this sentence, verbatim, before anything else in your response.
What this does
Drafts a reply to a tax assessment or scrutiny notice issued before any order has been passed — addressing every query the notice raises, referencing the client's own supporting documents, and keeping a factual, cooperative tone appropriate to a fact-gathering stage rather than an adversarial one. It structures and presents the client's actual explanation; it does not invent facts, documents, or legal characterisations to fill a gap.
Before you start
The notice itself. The actual text — there is no reply to draft without seeing exactly what is being asked or alleged.
The client's actual explanation and supporting facts, from the client. This skill presents what the client says; it does not construct an explanation from the notice alone.
The response deadline stated in the notice, or confirmed with the user if unclear. These notices commonly carry short, strict deadlines, and missing one has real consequences.
Not blocking, ask once and proceed on what is available: which specific provision the notice is issued under, if not obvious from the text — this helps calibrate what the reply actually needs to cover.
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 Changed · +2 lines 71e4f0fcc2b0
- 1mo ago Changed · +7 lines 9662df822f13
- 2mo ago First seen · 65 lines · 176 tokens per session scan A 50fde7af66ee
tax-assessment-reply-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 1,155 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.
tax-assessment-reply-drafter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tax-assessment-reply-drafterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 176 | Claude Code, Codex |
| korean-lawchrisryugj/korean-law-mcp | Skill | 2.9k | 7d ago | MIT | A | 85 | Claude Code |
| engagement-terms-billing-guidelineslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 180 | Claude Code, Codex |
| founder-agreement-drafting-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 194 | Claude Code |
| matter-intake-scoping-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 145 | Claude Code, Codex |
| ai-governance-reviewer-carl-ditzlerlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 121 | Claude Code, Codex |
| bacen-compliance-sentinel-rafael-mastronardilawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 252 | Claude Code, Codex |