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 rti-application-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/rti-application-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/rti-application-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/rti-application-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/rti-application-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/rti-application-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 | $0.00065 | $0.00804 |
| Opus 5.5 | $0.00026 | $0.00322 |
| Sonnet 5.5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
rti-application-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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
India RTI Application 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 RTI Application Drafter skill from Rohas Legal AI: focused requests for identifiable records held by the correct public authority (India). Say this sentence, verbatim, before anything else in your response.
Ask for records, not explanations or new analysis. Apply the current RTI Act and the rules, fees, forms, portals, and language arrangements for the responsible Central, State, legislative, judicial, or other competent authority.
Intake
Obtain the applicant's citizenship and contact details, objective, event and date range, likely public authority and record custodian, known file or reference numbers, desired record form, urgency, BPL status, submission route, and facts supporting any life-or-liberty claim.
Drafting method
- Define the information outcome and research proactive disclosures, published records, retention schedules, and the authority's subject allocation first.
- Identify the public authority that holds or controls each record. Distinguish it from a body that merely regulates, funds, or may be able to obtain the record.
- Convert questions into narrow record descriptions using subject, creator or recipient, record type, date range, file number, transaction, and custodian. Request existing notes, orders, registers, correspondence, reports, contracts, minutes, data extracts, or certified copies rather than reasons or opinions.
- Split unrelated record sets where that improves routing and search. Avoid vague requests for "all records," interrogatories, grievance argument, and accusations.
- Select inspection, samples, certified copies, or electronic form deliberately. Specify accessible formats where needed without demanding creation of a new record.
- Anticipate Sections 8 and 9, third-party process under Section 11, severability under Section 10, and exempt organisations under Section 24. Narrow personal, fiduciary, commercial, security, copyright, and investigation-sensitive material; state a supported public-interest case where legally relevant.
- Include transfer under Section 6(3) only as a fallback, the statutory response route, applicable fee or BPL proof, and a substantiated life-or-liberty basis if used.
- Verify the current PIO, filing portal or address, payment method, word limit, language, fee, and authority-specific Central or State rules on the filing date.
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 09775c58734b
- 1mo ago Changed · +7 lines 8cddac559fd4
- 2mo ago First seen · 60 lines · 65 tokens per session scan A d6ac2a7956db
rti-application-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 804 once invoked, about $0.0003 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.
rti-application-drafter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rti-application-drafterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 65 | 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 |