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 whistleblower-report-analystgit 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/whistleblower-report-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/whistleblower-report-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/whistleblower-report-analyst/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/whistleblower-report-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/whistleblower-report-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.00604 |
| Opus 5.5 | $0.00020 | $0.00242 |
| Sonnet 5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
whistleblower-report-analyst 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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whistleblower Report Analyst
I am using the Whistleblower Report Analyst skill from Rohas Legal AI: protected intake, risk triage and proportionate investigation planning. Say this sentence, verbatim, before anything else in your response.
Assess whether and how to investigate; do not decide truth from intake alone. Treat specificity separately from the reporter's identity, motive, style, or status.
Intake
Preserve the original report, channel, date, metadata, attachments, access log, anonymity or confidentiality preference, allegations, people, entities, periods, evidence locations, immediate risk, deadlines, prior reports, and conflicts.
Triage method
- Acknowledge receipt where possible without promising absolute confidentiality, a particular outcome, or protection beyond the organisation's authority.
- Address imminent harm, evidence loss, retaliation, reporting deadlines, financial dissipation, and safeguarding first.
- Screen investigators, management, legal, HR, audit, compliance, and the reporting line for conflicts; establish independence where needed.
- Break the report into allegation, actor, conduct, date, location, source, affected rule or control, and potential evidence.
- Assess specificity, consistency, corroborability, seriousness, recurrence, exposure, and alternatives neutrally. Anonymous or motivated reporting is not inherently unreliable.
- Rank allegations by urgency, impact, evidence fragility, legal duty, and risk of alerting subjects.
- Preserve relevant systems, devices, messages, files, logs, sites, and custodians without unnecessary disclosure.
- Design scope, reviewers, data requests, interview order, milestones, decision rights, escalation criteria, and the finding standard.
- Establish confidential communication, anti-retaliation monitoring, support, access restrictions, and a route for new concerns.
- Coordinate HR, privacy, privilege, employment, regulatory, disclosure, and law-enforcement issues with independent specialists.
- Plan closure, feedback where lawful, remediation, accountability, trend analysis, and monitoring without revealing protected information.
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.
- 5d ago First seen · 60 lines · 49 tokens per session scan A 2053dc7ad489
whistleblower-report-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (149 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 604 once invoked, about $0.0002 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 2026-09-21.
Other skills, from other repositories
lawyer-expert
Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.
law-to-markdown
A skill that converts legal provisions and regulatory documents from plain text, PDF, or Word format into Markdown. Markdown is a plain-text format commonly used for structured documents.
federal-court-rules
Use when an agent needs to look up, quote, summarize, cite, or reason from bundled federal court rules, including the Federal Rules of Civil Procedure, Federal Rules of Appellate Procedure, Federal Rules of Evidence, supplemental rules, selected federal district local rules, and selected ECF rules. Provides local…
ma-laws
Use when an agent needs to look up, quote, search, summarize, cite, or reason from the Massachusetts Constitution, Massachusetts General Laws, or Massachusetts Rules of Civil Procedure.
assistant-juridique-fr
Assistant juridique expert en droit français. Recherches, consultations, rédaction d'actes, contre-argumentaires, analyses de contrats et de pièces, veille, vérification et harmonisation de références. Produit des documents Word (computer use) ou des réponses conversationnelles structurées. MCP : OpenLegi, Themia…
invoice-review-compliance
Invoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for in-house legal ops teams managing outside counsel. Review invoices against billing guidelines; flag block billing, prohibited fees, rate violations, staffing violations, late submission. Produce…