coroner

coroner is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 72 tokens per session (2,677 once invoked), scanned A, original, MIT.

A medicolegal death-investigation guide for deciding whether a death falls under official investigation and how to assess its cause and manner. It covers scene findings, autopsy and toxicology decisions, and postmortem timing, while noting that local law and forensic specialists control the final decision.

In plain words
What is it for?
It is for assessing reportable deaths, deciding whether further examination is needed, estimating time since death, and preparing conclusions for death certificates or legal proceedings.
Why use it?
It helps separate medical conclusions from legal classifications and reduces mistakes when evidence is incomplete, time-sensitive, or governed by local rules.

Skill for Claude CodeCodex

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

Good fit It is for assessing reportable deaths, deciding whether further examination is needed, estimating time since death, and preparing conclusions for death certificates or legal proceedings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wonsukchoi/domain-experts/coroner
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 wonsukchoi/domain-experts --skill coroner
Clone the repo
git clone --depth 1 https://github.com/wonsukchoi/domain-experts

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 coroner

README.md
[![agentmods](https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coroner/github.svg)](https://agentmods.dev/skills/wonsukchoi/domain-experts/coroner)
Your own site
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/coroner"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coroner/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 coroner

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/coroner"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coroner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,677 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 $0.00072 $0.02677
Opus 5 $0.00036 $0.01339
Sonnet 5 $0.00014 $0.00535
Haiku 4.5 $0.00007 $0.00268

Measured 9d ago against content hash 7d5ba6745fe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coroner 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 9d 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.

roles/coroner/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coroner

Scope disclaimer. This skill is a reasoning aid for medicolegal death investigation, not a substitute for forensic pathology training, jurisdiction-specific statute, or a licensed forensic pathologist's autopsy findings. Coroner vs. medical examiner authority, reportable-death criteria, inquest procedure, and death-certificate signing authority vary by state and even by county — confirm the controlling statute before acting. Nothing here overrides a jurisdiction's specific legal requirements.

Identity

The official (elected or appointed, physician or non-physician depending on jurisdiction) who determines whether a death falls under medicolegal jurisdiction, investigates its circumstances, and signs off on cause and manner of death — sometimes personally, sometimes by referring for autopsy to a forensic pathologist. Accountable to two audiences with different needs: the family that wants an answer now, and the legal system (criminal, civil, insurance) that needs a determination that holds up under cross-examination years later. The defining tension: scene findings are perishable and time-pressured, but the conclusions drawn from them get relied on long after the scene is gone — so the investigation has to be done once, correctly, because there is no second visit to the body as it was found.

First-principles core

  1. Cause of death and manner of death are two different legal questions, and conflating them is a real, recurring error. Cause is the specific physiological mechanism (e.g., "gunshot wound to chest"); manner is the legal category it falls into (natural, accident, suicide, homicide, or undetermined). The same cause of death — a gunshot wound — can be any of four different manners depending entirely on the circumstances, and the manner determination is what actually drives legal and insurance consequences.
  2. Not every death is under coroner/medical examiner jurisdiction — reportability is a statutory checklist, not a judgment call about how the death "feels." Sudden or unexpected death, death without an attending physician, death in custody, violent or suspicious death, and death within a defined window of a medical procedure are typical statutory triggers; a death that doesn't meet the jurisdiction's specific criteria goes to the attending physician for certification, not to the coroner.
  3. Postmortem interval estimates are ranges with real uncertainty, not point-in-time facts — treating a single method's output as precise overstates what the evidence supports. Body cooling (algor mortis), rigor mortis progression, and livor mortis (lividity) fixation each give a rough window on their own and are far more reliable used together, cross-checked for internal consistency, than any one taken alone.
  4. Chain of custody starts at the scene, not at the morgue — evidence handled before a formal chain-of-custody log exists is evidence a defense attorney will challenge later. Photographs, scene sketches, and collected specimens need documented handling from the moment of discovery, because the legal question of "who touched what, when" gets asked in court, not just in the lab.
  5. "Undetermined" is a legitimate, defensible manner-of-death finding, not a failure to reach a conclusion. Pressure to give families or investigators a definitive answer doesn't change what the evidence actually supports — certifying a manner beyond what the evidence justifies creates a record that can be wrong in a way that matters later (insurance payout, criminal charge, civil suit).

Read the full file on GitHub · 103 lines

Files

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.

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. 9d ago First seen · 103 lines · 72 tokens per session scan A 7d5ba6745fe5

Subscribe to this mod's changes

coroner is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 2,677 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 2026-09-03.

Related

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.

docxology/template · 30 tokens

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.

paruff/uFawkesAI · 54 tokens

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.

hamzabellouch/agent-skills · 70 tokens

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…

hamzabellouch/agent-skills · 66 tokens

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.

hamzabellouch/agent-skills · 47 tokens

policy-validation

Validate build output against organizational policies. Use when checking manifests, pipelines, directory structure, and compliance rules.

paruff/uFawkesAI · 24 tokens