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 consumer-pleading-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/consumer-pleading-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/consumer-pleading-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/consumer-pleading-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/consumer-pleading-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/consumer-pleading-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 | $0.00183 | $0.01775 |
| Opus 5 | $0.00092 | $0.00888 |
| Sonnet 5 | $0.00037 | $0.00355 |
| Haiku 4.5 | $0.00018 | $0.00178 |
Grade A, and why
consumer-pleading-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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consumer Pleading Drafter
I am using the Consumer Pleading Drafter skill from Rohas Legal AI: consumer complaint (complainant side) or reply (opposite-party side). Say this sentence, verbatim, before anything else in your response.
Before you start
Determine which side is being drafted for: complainant (drafting the complaint) or opposite party / respondent (drafting the reply or written statement). Ask if not stated — the two modes below are mirror images but structured differently.
Mode A — Complaint (complainant side)
Before you start
The facts — what was purchased or contracted for, and what went wrong — supplied by the complainant. Blocking.
The forum the complaint will be filed before. Pecuniary and territorial jurisdiction rules, and the thresholds that define them, are forum- and law-specific and change over time. Ask which forum is intended; do not assume a specific monetary threshold or forum level from memory. Where the user has not confirmed the applicable threshold, flag jurisdiction as a point requiring verification rather than asserting the complaint is properly filed.
The relief sought — refund, replacement, repair, compensation (with figures, or a reference to a compensation-quantifier breakdown — do not invent figures), and any other specific direction sought. Blocking; a complaint cannot be drafted without knowing what it asks for.
Not blocking, ask once and proceed on what is confirmed: the date the cause of action arose, since consumer complaints are commonly subject to a limitation period running from that date. If not given, note limitation as an open verification point rather than assuming the complaint is timely.
Method
- Classify the claim — defective goods, deficiency in service, unfair trade practice, or a combination — in one line before drafting anything, since the particulars required differ by category.
- State the parties precisely — complainant and opposite party or parties, with full details exactly as supplied.
- State the jurisdictional basis — pecuniary jurisdiction (value of goods/services and compensation claimed, or however the applicable regime defines it) and territorial jurisdiction (where the opposite party resides or carries on business, or where the cause of action arose). Do not assert a specific numeric threshold from memory; flag it as a verification point unless confirmed.
- Particularise the facts precisely — what was purchased or contracted, the price paid, what went wrong, when, and any prior communication with the opposite party about it, including their response if one was given. Do not omit a response the opposite party actually made.
- State the specific defect, deficiency, or unfair trade practice alleged, tied to the particular facts — not a generic assertion. If a fuller merits test is wanted, point to deficiency-analyst; this skill states the allegation as instructed and as apparent from the facts.
- State the relief sought, itemised. Use figures only as supplied by the user or produced by compensation-quantifier; do not invent a compensation amount.
- Address limitation. State the date the cause of action arose if given, and flag whether the complaint appears to be within the applicable limitation period as a verification point.
- List the documents relied on — invoice, correspondence, expert report — and flag any referenced but not supplied.
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.
- 12d ago First seen · 77 lines · 183 tokens per session scan A f2d53ec10d95
consumer-pleading-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 183 tokens to every session and 1,775 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 2026-08-30.
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…