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 zgbrenner/agentcounsel --skill protected-leave-reviewgit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/protected-leave-review)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/protected-leave-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/protected-leave-review/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/zgbrenner/agentcounsel/protected-leave-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/protected-leave-review.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 | $0.00047 | $0.03852 |
| Opus 5 | $0.00023 | $0.01926 |
| Sonnet 5 | $0.00009 | $0.00770 |
| Haiku 4.5 | $0.00005 | $0.00385 |
Grade A, and why
Protected Leave Review 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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protected Leave Review
Purpose
Produce a structured, attorney-ready review of an employee's protected-leave situation. The skill organizes the known facts, identifies which leave frameworks may be implicated, surfaces the procedural obligations and entitlement questions that must be researched and confirmed through verified legal authority, identifies how multiple frameworks interact, and — critically — flags adverse-action exposure where a termination, demotion, denial of reinstatement, or discipline is contemplated.
This skill provides decision support and workflow discipline. It does not compute entitlements, calculate deadlines, state rules from background knowledge, or conclude whether any action is lawful. Every entitlement, threshold, and deadline is flagged for verified research. This is draft legal work product for attorney review — not legal advice.
Use When
- An employer, HR professional, or attorney needs to organize the facts of an employee's leave and identify which protected-leave frameworks may apply.
- A leave situation involves multiple frameworks that may run concurrently or interact (for example, medical leave and disability-accommodation leave arising from the same condition).
- A question arises about what procedural obligations — notices, certifications, designation steps — have been met or remain outstanding.
- An adverse action (termination, demotion, denial of reinstatement, or discipline) affecting an employee who is on, has recently taken, or has requested protected leave is being contemplated, and the employer needs to understand the exposure before proceeding.
- A user asks: "Can we terminate this employee who is on leave?", "What do we owe someone returning from military leave?", "What happens if their leave runs out and they can't come back?", or similar questions about an employee's leave situation.
Required Inputs
- The leave situation: the type or types of leave at issue (e.g., medical, family, military or service-member, disability-related, or a combination). If unclear, describe the underlying reason for the absence.
- The employee's work schedule and arrangement: full-time, part-time, or variable hours; whether leave is continuous or intermittent; and, if intermittent, how it has been taken or is anticipated to be taken.
- Key dates: the leave start date; the expected or actual return date; any dates on which notices, certifications, or designation decisions were or were not communicated. Flag all dates as
[deadline verification required]— do not use them to compute deadlines. - Procedural status: whether an eligibility notice has been issued; whether a designation notice has been issued; whether medical or other certification has been requested, received, or found insufficient; whether a cure opportunity has been provided.
- Jurisdiction(s): the jurisdiction(s) in which the employee works. If unknown or in dispute, flag as
[CONFIRM: governing jurisdiction]. - Adverse action contemplated: whether any termination, demotion, denial of reinstatement, or disciplinary action is under consideration. If yes, describe it and its proposed timing.
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.
- 11d ago First seen · 164 lines · 47 tokens per session scan A e7f25f8e2094
Protected Leave Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,852 once invoked, about $0.0002 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
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
contract-review
A contract-review workflow for agreements governed by Chinese law, United States law, or both. It examines clauses one by one and produces a list of legal-risk questions, with an optional marked-up Word document.
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.