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 privilege-log-buildergit 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/privilege-log-builder)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/privilege-log-builder"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/privilege-log-builder/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/privilege-log-builder"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/privilege-log-builder.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 | $0.00067 | $0.00708 |
| Opus 5 | $0.00034 | $0.00354 |
| Sonnet 5 | $0.00013 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
privilege-log-builder 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privilege Log Builder
I am using the Privilege Log Builder skill from Rohas Legal AI: supportable privilege entries, family reconciliation, waiver flags and challenges. Say this sentence, verbatim, before anything else in your response.
Create a factually supportable log that permits evaluation of each asserted basis without revealing the protected communication or work product itself.
Intake
Obtain the governing jurisdiction and forum, procedural rules and orders, parties and client structure, relevant legal advisers and roles, applicable privilege or protection categories, document population, review decisions, family relationships, production and redaction data, confidentiality arrangements, clawback terms, challenge procedure, deadlines, and any categorical-log agreement.
Treat the governing law and required log fields as blocking for a final log. A draft may proceed with conspicuous placeholders and verification flags.
Method
- Identify every potentially applicable protection and its required elements. Distinguish legal-advice privilege, litigation or work-product protection, without-prejudice material, joint or common-interest arrangements, regulatory protections, and confidentiality; do not collapse them into "privileged."
- Verify the actors, their capacities, client relationship, purpose, recipients, confidentiality, legal context, and document date from evidence rather than names, domains, titles, or copied lawyers alone.
- Assign stable document IDs and preserve family, thread, duplicate, near- duplicate, attachment, version, redaction, and production relationships.
- Draft neutral descriptions that explain the general subject and protected purpose without revealing advice, strategy, mental impressions, or substance.
- Record the precise asserted basis, supporting facts, withholding or redaction status, confidentiality basis, and reviewer or counsel approval. Separate mixed- purpose material and non-privileged attachments where required.
- Test waiver, broad distribution, third-party presence, forwarding, dominant or primary purpose, client identity, advice capacity, in-house counsel role, litigation anticipation, crime-fraud or equivalent exceptions, and governing- law uncertainty. Flag; do not decide unsupported facts.
- Apply categorical, metadata-minimal, or exception treatments only where an order, agreement, or applicable rule supports them.
- Reconcile the log to withheld documents, redacted productions, slip sheets, numbering, families, and production totals. Identify orphans and inconsistent decisions.
- Prepare challenge responses by linking each disputed entry to its evidence and legal elements, while preserving protected content.
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 · 69 lines · 67 tokens per session scan A 4b23ad2e0226
privilege-log-builder is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 708 once invoked, about $0.0003 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…