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 | $0.01045 |
| Opus 5 | $0.00088 | $0.00522 |
| Sonnet 5 | $0.00035 | $0.00209 |
| Haiku 4.5 | $0.00018 | $0.00104 |
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 9d 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.
Tax Assessment Reply Drafter
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.
Method
1. Read the whole notice once before drafting anything. A global point — the notice period is too short, or a query lacks the particularity the law requires — can apply across several queries at once, and drafting query by query on a first pass misses this.
2. List every query or point raised in the notice, numbered, before drafting any response.
3. For each query, state the client's explanation precisely, using only what the client has actually provided. Do not invent a supporting fact or document to make a response feel more complete.
4. Reference the specific documents being submitted in support of each response, and flag any document referred to but not yet available.
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.
- 9d 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 (88 stars, last pushed 10d ago), licensed MIT. It adds 176 tokens to every session and 1,045 once invoked, about $0.0009 per session on Opus 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.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…