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 samarailly51-pixel/claimpilot-harness --skill bodily-injury-claims-processinggit clone --depth 1 https://github.com/samarailly51-pixel/claimpilot-harnessWrote 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/samarailly51-pixel/claimpilot-harness/bodily-injury-claims-processing)<a href="https://agentmods.dev/skills/samarailly51-pixel/claimpilot-harness/bodily-injury-claims-processing"><img src="https://agentmods.dev/badge/skills/samarailly51-pixel/claimpilot-harness/bodily-injury-claims-processing/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/samarailly51-pixel/claimpilot-harness/bodily-injury-claims-processing"><img src="https://agentmods.dev/badge/skills/samarailly51-pixel/claimpilot-harness/bodily-injury-claims-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 22 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.00478 |
| Opus 5 | $0.00038 | $0.00239 |
| Sonnet 5 | $0.00015 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
Grade A, and why
bodily-injury-claims-processing 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bodily Injury Claims Processing
Use a safety-first workflow. Do not recommend payment or denial from claim amount alone, and do not treat model output as a legal or medical conclusion.
Review workflow
- Establish parties, policy, loss date, jurisdiction, coverage status, and reported accident facts.
- Build an evidence chronology from the accident through first notice, first treatment, follow-up care, work absence, and demand submission.
- Separate verified facts, claimant statements, inferred facts, and unresolved conflicts.
- Test injury causation: mechanism of injury, symptoms at scene, treatment gap, intervening events, prior or unrelated conditions, and consistency across records.
- Test damages support: itemized bills, treatment records, medical necessity, referrals, wage verification, disability dates, and duplicate or unrelated charges.
- Classify the next action as
approve,investigate, ordeny. Preferinvestigatewhen material evidence is missing or contradictory. - Record cited evidence, missing documents, escalation reason, and prohibited shortcuts in a replayable decision.
Guardrails
- Never auto-approve solely because a claim is below a monetary threshold.
- Never infer causation from diagnosis or billing alone.
- Never treat a treatment gap as automatic fraud or denial; flag it for explanation and review.
- Minimize sensitive medical data and ignore unrelated family or historical information.
- Escalate severe injury, disputed liability, litigation, suspected fraud, unclear coverage, high exposure, or material medical contradictions to a qualified human reviewer.
- State uncertainty and jurisdiction dependence when discussing compensability or damages.
Output contract
Return a structured review containing:
- recommended action and confidence
- material findings
- missing documents
- cited evidence IDs
- chronology conflicts
- escalation reason
- privacy or safety flags
Read references/review-checklist.md when performing a full file review or creating an evaluation case.
What ships with it
2 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 · 42 lines · 76 tokens per session scan A 4b8cf534c52a
bodily-injury-claims-processing is a skill published in the GitHub repository samarailly51-pixel/claimpilot-harness (117 stars, last pushed 19d ago), licensed MIT. It adds 76 tokens to every session and 478 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
clinical-trial-protocol-skill
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
prior-auth-review-skill
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…
insurance-expert
Expert-level insurance systems, underwriting, claims processing, actuarial analysis, risk assessment, and insurtech solutions. Use when the user mentions underwriting, claims, actuarial, risk, or insurtech, or when the task involves Insurance Systems, Insurance Types, Standards and Regulations, or Claims Processing.
Insurance Cold-Start Interview
Use when an insurance practice group is adopting AgentCounsel and needs to configure its practice profile by answering a structured interview covering jurisdictions, client context, escalation thresholds, output preferences, source documents, standard positions, review requirements, and prohibited assumptions.
Bad Faith Risk Triage
Use when issue-spotting potential claim-handling and bad-faith risk themes from claim file materials into a source-cited risk-theme list for attorney review.
Certificate of Insurance Review
Use when reviewing certificates of insurance and related endorsements against contract insurance requirements into a source-cited comparison table for attorney review.