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 pre-institution-mediation-advisorgit 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/pre-institution-mediation-advisor)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/pre-institution-mediation-advisor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/pre-institution-mediation-advisor/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/pre-institution-mediation-advisor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/pre-institution-mediation-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00120 | $0.01035 |
| Opus 5 | $0.00060 | $0.00517 |
| Sonnet 5 | $0.00024 | $0.00207 |
| Haiku 4.5 | $0.00012 | $0.00103 |
Grade A, and why
pre-institution-mediation-advisor 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Institution Mediation Advisor (India)
I am using the Pre Institution Mediation Advisor skill from Rohas Legal AI: mandatory pre-institution mediation requirements (India). Say this sentence, verbatim, before anything else in your response.
Purpose
Determine whether a proposed proceeding must pass through pre-institution mediation, identify the correct route and authority, and produce a filing-ready process plan without manufacturing urgency or assuming every mediation statute is fully commenced.
Required inputs
Obtain:
- the proposed claims, remedies, defendants, and intended court or tribunal;
- facts relevant to whether the dispute is a commercial dispute and its specified value;
- the cause-of-action and limitation chronology;
- any urgent interim relief genuinely required, the threatened harm, and supporting evidence;
- prior notices, settlement or mediation steps, and refusal or non-participation records;
- party names, addresses, contact details, and service information; and
- the proposed filing date, forum-specific requirements, and status of related proceedings.
Treat the intended proceeding, claim classification, specified value, urgency case, and limitation dates as blocking. Do not advise direct institution merely because the pleading can request an interim order.
Method
- Retrieve the current official text of the Commercial Courts Act, 2015, section 12A, the current Commercial Courts (Pre-Institution Mediation and Settlement) Rules, amendments, notifications authorising authorities, and controlling decisions. Record the source date.
- Retrieve the current official commencement notifications for the Mediation Act, 2023. Apply only provisions actually brought into force and check any savings, overriding, transition, and Commercial Courts Act interface. Do not infer whole-Act commencement from the title's enforcement date.
- Classify the proposed case:
- Is it a suit rather than an arbitration, petition, appeal, or other proceeding?
- Is it a commercial dispute within the current definition?
- Does it meet the current specified-value threshold and valuation method?
- Does another special statute or forum alter the route?
- Test the urgent-interim-relief position factually. Identify the immediate right at risk, date of threatened harm, relief needed before mediation could conclude, evidence, prior delay, and why damages or ordinary protection is inadequate. Separate genuine urgency from drafting labels.
- Give a conclusion as
Required,Not required, orUncertain pending verification, with each element, authority, and factual dependency shown. - If required, identify the currently authorised mediation authority and local filing location. Verify the current form, fee, documents, copies, modes of filing, service process, appearance rules, online options, and consequences of non-participation.
- Build the statutory timeline from the actual application date. Verify the current initial period, any consensual extension, limitation exclusion or suspension, non-starter procedure, non-settlement report, and date on which suit may safely be filed.
- If settlement occurs, verify writing, signatures, mediator authentication, registration or filing options, legal status, enforcement, challenge, stamp or tax issues, and steps for disposing of related proceedings.
- Preserve evidence: application receipt, fee, service, attendance, communications permitted to be retained, authority letters, settlement or non-settlement record, and limitation calculation.
- Flag High Court, State or District Legal Services Authority, commercial court, and electronic-filing requirements for local verification.
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 · 63 lines · 120 tokens per session scan A f02f0ae60521
pre-institution-mediation-advisor is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 120 tokens to every session and 1,035 once invoked, about $0.0006 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…