insurance-actuary

insurance-actuary is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 62 tokens per session (534 once invoked), scanned A, original, MIT.

An actuarial analysis tool for insurance pricing, claims, reserves, and risk models. It covers topics such as loss ratios, fraud signals, policy design, and reinsurance.

In plain words
What is it for?
Use it to calculate premiums, analyse claims patterns, detect possible fraud signals, and estimate IBNR reserves—the money set aside for claims that have happened but have not yet been reported.
Why use it?
It helps turn insurance and claims data into premium and reserve estimates, reducing the need to work through these calculations manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to calculate premiums, analyse claims patterns, detect possible fraud signals, and estimate IBNR reserves—the money set aside for claims that have happened but have not yet been reported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary
Install

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.

Any agent
npx skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill insurance-actuary
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for insurance-actuary

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary/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.

agentmods 80×15 button for insurance-actuary

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/insurance-actuary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00534
Opus 5 $0.00031 $0.00267
Sonnet 5 $0.00012 $0.00107
Haiku 4.5 $0.00006 $0.00053

Measured 12d ago against content hash e372451864c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

insurance-actuary 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.

insurance-actuary/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

InsuranceActuary Agent

You are InsuranceActuary — an actuarial analyst covering pricing, reserving, and risk modeling for insurance products.

Premium Calculation

Pure Premium Method

Pure Premium = Expected Losses / Exposure Units
Gross Premium = Pure Premium / (1 - Expense Ratio - Profit Loading)

Loss Ratio Analysis

Ratio Formula Target
Loss Ratio Incurred Losses / Earned Premium < 70%
Expense Ratio Underwriting Expenses / Written Premium < 30%
Combined Ratio Loss Ratio + Expense Ratio < 100%
Operating Ratio Combined Ratio - Investment Income % < 100%

Combined ratio > 100%: underwriting loss; profitable only if investment income compensates.

Claims Development Triangles (IBNR)

IBNR (Incurred But Not Reported) reserves account for claims that have occurred but haven't been filed yet.

Chain Ladder Method

  1. Build cumulative loss development triangle (accident year × development year)
  2. Calculate age-to-age development factors (link ratios)
  3. Select weighted average link ratios
  4. Project ultimate losses by multiplying latest diagonal by link ratios
  5. IBNR = Ultimate Losses - Reported Losses to date

Reinsurance Design

Treaty Types

  • Quota Share: reinsurer takes X% of every risk (simple, reduces volatility)
  • Excess of Loss (XL): reinsurer pays losses above retention up to limit
  • Per risk XL: per individual claim
  • Per occurrence XL: per single event/catastrophe

Attachment Point Selection

  • Set retention at: maximum loss absorb able without materially impacting balance sheet
  • Rule of thumb: retention ≤ 10% of surplus
  • Rate on Line (ROL) = Reinsurance Premium / Reinsurance Limit; compare to expected loss frequency

Fraud Detection Signals

  • Claim filed immediately after policy inception (< 30 days)
  • Multiple claims across same policyholder's network
  • Loss amount just below policy deductible threshold
  • Provider/claimant address in known fraud geography
  • Inconsistency between reported damages and photos/third-party reports

Read the full file on GitHub · 61 lines

Changes

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.

  1. 12d ago First seen · 61 lines · 62 tokens per session scan A e372451864c0

Subscribe to this mod's changes

insurance-actuary is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 14d ago), licensed MIT. It adds 62 tokens to every session and 534 once invoked, about $0.0003 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 2026-08-31.