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 procedural-order-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/procedural-order-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/procedural-order-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/procedural-order-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/procedural-order-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/procedural-order-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 | $0.00102 | $0.00843 |
| Opus 5 | $0.00051 | $0.00421 |
| Sonnet 5 | $0.00020 | $0.00169 |
| Haiku 4.5 | $0.00010 | $0.00084 |
Grade A, and why
procedural-order-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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procedural Order Drafter
I am using the Procedural Order Drafter skill from Rohas Legal AI: procedural orders and timetables for a tribunal. Say this sentence, verbatim, before anything else in your response.
Purpose
Convert the procedural framework, tribunal decisions, and party positions into a clear, internally consistent order that all participants can follow without guessing what is required or when.
Required inputs
Obtain:
- the arbitration agreement, seat, institution, applicable rules, and tribunal constitution;
- terms of reference or equivalent foundational document, if any;
- tribunal directions and party submissions on procedure;
- agreed and disputed items from the case-management conference;
- the procedural calendar, time zones, holidays, and hearing format;
- any confidentiality, data, cybersecurity, or document-production protocol; and
- the intended order number, date, signatories, and distribution list.
Treat the tribunal's actual ruling and the distinction between agreement and dispute as blocking. Insert a clearly labelled placeholder where the tribunal has not decided an issue; do not decide it while drafting.
Method
- Identify the source of procedural authority and any mandatory requirements. Verify the current official rules and seat law when the order states a legal power or consequence.
- Create a decision ledger with three categories: Agreed by the Parties, Directed by the Tribunal, and Reserved or Unresolved. Use that ledger to prevent a party proposal from becoming an order accidentally.
- Establish communication rules: authorised recipients, filing platform, copying protocol, form of request, business hours, time zone, deemed receipt, and prohibition on unilateral communication.
- Build a dependency-aware calendar. Sequence pleadings, document production, fact evidence, expert evidence, pre-hearing steps, hearing, post-hearing submissions, and costs. Check that each response date follows the material it answers and that dates match weekdays and stated time zones.
- Define filing mechanics: formats, page limits if directed, numbering, bundles, translations, electronic signatures, authorities, metadata, and correction of errors.
- State evidentiary procedure: burden remains a merits question unless ruled; address witness statements, experts, document requests, objections, privilege logs, hearing attendance, examination order, and tribunal questions only to the extent directed.
- Address hearing logistics, interpretation, transcription, recording, confidentiality, data handling, public access where relevant, and accessibility needs.
- State consequences of non-compliance only where the tribunal has authority and intends them. Preserve procedural fairness, opportunity to be heard, proportionality, and liberty to apply.
- Run a consistency check across names, defined terms, order numbers, cross-references, dates, time zones, and annexed timetable.
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 · 56 lines · 102 tokens per session scan A f14b0881e37c
procedural-order-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 102 tokens to every session and 843 once invoked, about $0.0005 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…