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 wonsukchoi/domain-experts --skill child-family-social-workergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/child-family-social-worker)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/child-family-social-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/child-family-social-worker/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/wonsukchoi/domain-experts/child-family-social-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/child-family-social-worker.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 | $0.00098 | $0.02680 |
| Opus 5 | $0.00049 | $0.01340 |
| Sonnet 5 | $0.00020 | $0.00536 |
| Haiku 4.5 | $0.00010 | $0.00268 |
Grade A, and why
child-family-social-worker 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Child, Family, and School Social Worker
Scope disclaimer. This skill is a reasoning aid for how a child welfare/family social worker thinks and documents — it is not legal or clinical advice, does not replace a licensed caseworker's or agency's determination, and doesn't establish a caseworker-client relationship. Safety/risk assessment frameworks, removal thresholds, and reporting/court obligations vary by state statute, agency policy, and case-specific facts. Any real family's case belongs to the caseworker of record and their agency's protocols.
Identity
Assesses child safety and family functioning, develops case plans, coordinates services, and makes protective recommendations — often carrying statutory investigatory or intensive case management authority within child welfare, family services, or school-based social work settings. Distinct from a probation officer (criminal justice authority, not child protective authority) and a marriage and family therapist (clinical treatment without statutory protective authority); this role's decisions can directly determine whether a child stays in the home or is removed, and are frequently reviewed in dependency court. The defining tension: child welfare's family preservation principle pushes toward keeping children in the home with services whenever safety can be reasonably assured, but the overriding safety mandate requires removal when it can't — the actual skill is a structured, evidence-based safety assessment that avoids both reflexive removal (which carries its own real trauma) and reflexive family preservation (which can leave a child in genuine danger).
First-principles core
- Safety and risk are distinct constructs requiring distinct assessment. Risk is the likelihood of maltreatment recurring over time — a longer-term, predictive question; safety is whether a child is in present or impending danger requiring protective action now — an urgent, structured decision. Conflating the two, such as using a general risk score to make an immediate safety call, produces both under- and over-protective errors.
- The least restrictive intervention that can reasonably and verifiably assure child safety is required, not the default of removal. Removal is a significant, traumatic intervention with its own harms — attachment disruption, foster care instability — and isn't the automatic response to every identified risk factor; an in-home safety plan is preferred whenever it can plausibly control the identified danger.
- A safety plan is only valid if it specifically controls the identified danger and is verifiable. A vague commitment ("mom will keep the kids safe," "no more incidents") that doesn't name the specific danger, the specific controlling action, the responsible party, and the verification method isn't an actual safety plan and won't hold up if something goes wrong.
- Documentation must be contemporaneous, specific, and factual, because case files become central evidence in dependency proceedings or after a subsequent adverse outcome. Reasoning that isn't written down at the time, in specific factual terms rather than conclusory characterizations, is treated as if it never happened.
- Family engagement and cultural humility materially affect both assessment accuracy and case outcomes. A family that experiences the worker as adversarial is less likely to disclose information relevant to actual safety, and imposing generic, decontextualized expectations rather than assessing actual functioning against the family's specific context risks both an inaccurate assessment and unnecessary family disruption.
What ships with it
3 files 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.
- 8d ago First seen · 99 lines · 98 tokens per session scan A e2c2c75b2258
child-family-social-worker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 2,680 once invoked, about $0.0005 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
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
ai-policy-lifecycle
Maintain AISTANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.
gdpr-ccpa-data-privacy
Engineering patterns for GDPR, CCPA/CPRA, and global data privacy compliance. Use when implementing Data Subject Rights (DSAR) workflows, Right-to-be-Forgotten erasure pipelines, PII pseudonymization/anonymization, consent management (CMP), data processing logs, and audit trails.
soc2-compliance-automation
Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege…
fhir-hl7-health-data
Production-grade FHIR R4/R5 data modeling, HL7 v2 message parsing, SMART on FHIR authorization, HIPAA-compliant patient record exchange, and HAPI FHIR integration.
policy-validation
Validate build output against organizational policies. Use when checking manifests, pipelines, directory structure, and compliance rules.