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-appeal-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-appeal-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/rti-appeal-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/rti-appeal-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-appeal-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/rti-appeal-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 | $0.00075 | $0.00726 |
| Opus 5 | $0.00037 | $0.00363 |
| Sonnet 5 | $0.00015 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
rti-appeal-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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
India RTI Appeal Drafter
I am using the RTI Appeal Drafter skill from Rohas Legal AI: remedy selection, limitation, grounds and relief for RTI appeals and complaints (India). Say this sentence, verbatim, before anything else in your response.
Choose the remedy before drafting. Distinguish a Section 19(1) first appeal, a Section 19(3) second appeal, and a Section 18 complaint; they differ in forum, record, powers, limitation, and suitable relief.
Intake
Obtain the application, proof and date of filing, fee, transfer notices, PIO reply and enclosures, dispatch and receipt dates, First Appellate Authority appeal and order if any, later disclosures, the information still missing, prejudice, delay explanation, public-interest facts, and the applicable Central or State authority.
Analysis and drafting method
- Build a procedural chronology and calculate the statutory response and appeal dates under the current Act and applicable rules. Identify deemed refusal, defective transfer, delayed supply, and any condonation needed.
- Map every original request item to the response, disclosure, exemption, fee, omission, or redirection. Do not enlarge the application through the appeal.
- Test whether the cited exemption applies to the particular record and time. Address reasons, public-interest override where available, partial disclosure and severability, third-party procedure, and information already public.
- Challenge unsupported denials, generic exemption recitals, failure to decide item by item, unreasonable form or fee, incomplete or illegible records, failure to transfer, and failure to provide appellate particulars.
- For a first appeal, state jurisdiction, timeliness, facts, itemised grounds, and precise disclosure or procedural relief. Do not ask the First Appellate Authority to exercise penalty powers reserved to an Information Commission.
- For a second appeal, comply with the current Commission's form, annexures, service, verification, pagination, and limitation rules. Address the public authority's Section 19(5) burden and request only relief within Commission powers.
- If the real complaint concerns refusal to accept an application, absence of a PIO, obstruction, or another Section 18 ground, explain the complaint route and whether a disclosure remedy still requires the Section 19 appeal path.
- Verify current PIO, First Appellate Authority, Central or State Information Commission jurisdiction, portal, address, fee, rules, practice directions, and filing status as of the drafting 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.
- 9d ago First seen · 62 lines · 75 tokens per session scan A 1b1cd40f615d
rti-appeal-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 726 once invoked, about $0.0004 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…