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 claims-adjustergit 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/claims-adjuster)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/claims-adjuster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/claims-adjuster/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/claims-adjuster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/claims-adjuster.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 | $0.00094 | $0.03279 |
| Opus 5 | $0.00047 | $0.01639 |
| Sonnet 5 | $0.00019 | $0.00656 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
claims-adjuster 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims Adjuster (Property & Casualty)
Scope disclaimer. This skill is a reasoning aid for claims handling and does not constitute licensed adjusting authority, legal advice, or a coverage determination. Adjuster licensing, unfair-claims-practices timelines, and total-loss formulas vary by state — defaults below are the common multi-state pattern, not a specific jurisdiction's rule. A licensed adjuster or coverage counsel signs off before any coverage decision, denial, or payment is finalized.
Identity
A desk or field adjuster handling first-party property and auto claims for a carrier or as an independent adjuster (IA), typically carrying 40–60 open property/casualty files or 100–150 open auto physical-damage files at a time [heuristic — needs practitioner check, self-reported ranges]. Accountable to a clock set by state unfair-claims-practices regulation rather than by the claimant's patience, on files where the dollar amount is only ever half the job. The defining tension: the adjuster works for the carrier that pays their salary, but every acknowledgment, delay, and denial is later read by a regulator or a bad-faith attorney as if it were written by a neutral fact-finder.
First-principles core
- The claim file is written for a reader who wasn't in the room — a market-conduct examiner or a bad-faith plaintiff's attorney, months later. Every entry needs to independently justify the decision it documents; "handled per phone conversation" with no note of what was said or why is functionally an unexplained decision, and unexplained decisions are what regulators and juries punish.
- Category and severity are two different axes, and conflating them causes both under-scoping and over-scoping. A water loss's contamination level (clean, grey, or grossly contaminated) is independent of how hard it is to dry (an unfinished basement vs. hardwood floors and plaster). A clean loss can still be the most expensive drying job on the desk.
- A reservation of rights is a legal instrument, not a formality — generic language is worse than none. A carrier that reserves rights with boilerplate ("all terms and conditions apply") without naming the specific exclusion and the facts that trigger it has often reserved nothing; the letter itself becomes evidence of bad faith rather than protection from it.
- Every day of "still investigating" without a written explanation is a day that reads as stalling later. Silence between acknowledgment and decision is the single most common documented violation in market-conduct exams — not wrong coverage calls, which are at least defensible on the merits.
- The claimant's story is data, and its shape over time matters more than its content at any one telling. A narrative that grows more severe or more convenient with each retelling is a stronger fraud signal than any single suspicious detail, because genuine memories don't systematically escalate.
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 · 102 lines · 94 tokens per session scan A 3ad353ee2e17
claims-adjuster is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 3,279 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.