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 domestic-violence-safety-referral-checklistgit 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/domestic-violence-safety-referral-checklist)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/domestic-violence-safety-referral-checklist"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/domestic-violence-safety-referral-checklist/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/domestic-violence-safety-referral-checklist"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/domestic-violence-safety-referral-checklist.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 | $0.00040 | $0.01862 |
| Opus 5 | $0.00020 | $0.00931 |
| Sonnet 5 | $0.00008 | $0.00372 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
Domestic Violence Safety Referral Checklist 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domestic Violence Safety Referral Checklist
Purpose
Organize the facts and the referral and escalation considerations for a domestic violence or abuse-related concern in a family law matter — immediate safety concerns, existing protective orders, described incidents, available records, children involved, housing and financial access concerns, and upcoming court dates — so a qualified, licensed attorney and the appropriate support resources can be engaged. This skill organizes information and points to help; it does not create a safety plan, give emergency legal advice, or decide whether abuse occurred.
Use When
- A user raises a domestic violence, abuse, or safety concern within a family law matter.
- Facts and records around a safety concern must be organized and the right referrals identified for an attorney.
- A family law matter needs the safety dimension flagged and routed before other work proceeds.
Required Inputs
- The immediate safety concerns the user describes — or
not provided. - Any existing protective or restraining orders (type and date as stated, date marked
[deadline verification required]) — ornot provided. - The incidents the user chooses to describe, and any police reports, medical records, messages, or photos provided, with source references — or
not provided. - Whether children are involved, and any housing or financial access concerns — or
not provided. - Upcoming court dates the user supplies, echoed verbatim and marked
[deadline verification required]— ornot provided. - The parties, their roles, and the jurisdiction — or
not provided, jurisdiction flagged[verify jurisdiction].
The user is never required to describe more than they wish. Record only what the user volunteers; never press for traumatic detail.
Do Not Use When
- The request is to create a safety plan or to advise on how to stay safe — this skill does not do that; direct the user to a qualified local domestic violence resource.
- The request is to advise on gathering evidence, recording, or confronting the other party.
- The request is to determine whether abuse occurred, to assess credibility, or to prepare a protective order.
- The request is for legal advice or for protective-order procedures, eligibility, or standards.
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 · 112 lines · 40 tokens per session scan A 595ed938e4be
Domestic Violence Safety Referral Checklist is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,862 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 2026-09-03.
Other skills, from other repositories
cross-check-legal-advice
Use AI for legal issue-spotting, plain-language clause explanations, and questions to verify with licensed counsel.
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.
hse-indonesia
Expert HSE (Health, Safety & Environment) skill untuk konteks regulasi Indonesia. Gunakan skill ini kapanpun user menyebut: K3, HSE, SMK3, P2K3, Ahli K3, CSMS, ISO 45001, keselamatan kerja, audit K3, HIRARC/IBPR, JSA, permit to work, APD, B3, limbah B3, MSDS/SDS, laporan kecelakaan kerja, BPJS Ketenagakerjaan…
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…