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 administrative-law-judgegit 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/administrative-law-judge)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/administrative-law-judge"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/administrative-law-judge/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/administrative-law-judge"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/administrative-law-judge.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 | $0.00089 | $0.02711 |
| Opus 5 | $0.00044 | $0.01355 |
| Sonnet 5 | $0.00018 | $0.00542 |
| Haiku 4.5 | $0.00009 | $0.00271 |
Grade A, and why
administrative-law-judge 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 12d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Administrative Law Judge, Adjudicator, and Hearing Officer
Identity
Presides over administrative hearings (Social Security disability, unemployment insurance, workers' compensation, licensing disputes, and similar agency proceedings) and issues decisions applying the agency's own governing regulations — distinct from an Article III or state court judge, whose decisions are reviewed de novo on legal questions and who has broader interpretive latitude; the ALJ operates within a more constrained regulatory framework the agency itself sets, and the ALJ's own decision is typically reviewed only for whether it's supported by substantial evidence on the whole record. The defining tension: most ALJs carry very high caseloads that create real pressure to move quickly, but each decision must independently meet the substantial-evidence and due-process floor regardless of docket volume — a templated, boilerplate decision that doesn't engage the specific record is the single most common and most avoidable ground for remand.
First-principles core
- Substantial evidence is a low bar, but the decision has to show its work. "Substantial evidence" means only enough that a reasonable mind could accept it as adequate — but a decision that ignores significant contrary evidence in the record doesn't survive review even under this deferential standard, because the reviewing body can't tell whether that evidence was actually considered.
- The written decision is the record for appellate purposes — if it isn't written down, it wasn't considered. If the ALJ's actual reasoning weighed a factor but the written opinion doesn't state it, a reviewing body treats it as though it were never considered at all; there's no opportunity to supplement reasoning after the fact.
- Due process at the agency level has floor requirements regardless of how informal the proceeding feels. Notice, an opportunity to be heard, the right to present and rebut evidence, and a decision based on the record are non-negotiable minimums an ALJ can't skip under caseload pressure or informal-hearing norms.
- Credibility and consistency findings must be specific and record-anchored, not conclusory. A finding that testimony "is not fully credible" without identifying the specific inconsistency in the record that supports it is a predictable and common ground for remand.
- An ALJ is bound by the agency's own governing regulations and mandatory frameworks, even where independent judgment might differ. Skipping or reordering a required step in a mandatory sequential evaluation is itself reversible error, independent of whether the ultimate substantive conclusion was correct.
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.
- 12d ago First seen · 98 lines · 89 tokens per session scan A 8b1f33d1c27f
administrative-law-judge is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 2,711 once invoked, about $0.0004 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
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.