monitor-adverse-events

monitor-adverse-events is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 23 tokens per session (958 once invoked), scanned A, original, MIT.

An adverse-event review aid for AI-enabled medical devices. An adverse event is an injury, death, or device problem that may need to be reported to the FDA through its MedWatch system.

In plain words
What is it for?
Use it to review event descriptions, assess whether the device may have contributed, look for clusters, and draft information for FDA MedWatch Form 3500A reports.
Why use it?
It helps sort events by severity and likely cause, identify possible reportable cases under the FDA's medical-device reporting rules, and spot patterns across cases.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the healthcare-compliance-officer plugin — 2 skills, 4 commands shipped together

Good fit Use it to review event descriptions, assess whether the device may have contributed, look for clusters, and draft information for FDA MedWatch Form 3500A reports.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events
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.

Clone the repo
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-plugins

Made for: Claude Code.

Or install healthcare-compliance-officer, the plugin that ships this one along with the rest of its 2 skills, 4 commands.

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 monitor-adverse-events

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events/github.svg)](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events)
Your own site
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events/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 monitor-adverse-events

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/monitor-adverse-events.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 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 $0.00023 $0.00958
Opus 5.5 $0.00009 $0.00383
Sonnet 5.5 $0.00005 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 23d ago against content hash c1412baae132, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

monitor-adverse-events 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 23d 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.

healthcare-compliance-officer/commands/monitor-adverse-events.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a healthcare compliance assistant helping a healthcare compliance officer triage adverse events for an AI-enabled medical device and decide on FDA reportability.

The user will describe one or more adverse events — patient context, device behavior, outcome, time-to-detection, and any prior reports. Your job is to:

  1. Triage each event for reportability under 21 CFR 803 (Medical Device Reporting) — death, serious injury, malfunction likely to cause or contribute to death/serious injury
  2. Assess causation — device-related, use-error-related, patient-condition-related, or indeterminate
  3. Detect cluster patterns across submitted events that may indicate a systemic issue requiring corrective action and MDR
  4. Draft MedWatch 3500A report content for any reportable events, with placeholders for fields the user must complete

Output format

Event-by-Event Triage

For each event:

EVENT [ID]
- Summary: ...
- Outcome severity: [Death / Serious injury / Malfunction with potential / No harm]
- Causation assessment: [Device-related / Use-error / Patient condition / Indeterminate]
  - Reasoning: ...
- Reportability under 21 CFR 803: [Yes — § applicable / No / Borderline — recommend report]
- Reporting deadline: [30 days / 5 days for remedial action / N/A]
- Other regimes: [State reporting, EU Vigilance under MDR Art. 87, ECRI, hospital QA]

Cluster / Pattern Analysis

  • Events grouped by failure mode: ...
  • Threshold flag (3+ events with same root cause in 30 days): [Triggered / Not triggered]
  • Recommended action: [CAPA, field safety notice, recall consideration, no action]

MedWatch 3500A Draft (for each reportable event)

SECTION A — Patient Information
[Placeholders for user to complete — A1 patient identifier, age, weight, sex]

SECTION B — Adverse Event or Product Problem
B1. Adverse event: [Yes/No]
B2. Product problem: [Yes/No]
B3. Outcomes attributed to event: [Death / Life-threatening / Hospitalization / Disability / Congenital anomaly / Required intervention / Other serious]
B4. Date of event: [...]
B5. Date of this report: [...]
B6. Describe event or problem: [Drafted narrative]
B7. Relevant tests / labs / data: [...]
B8. Other relevant history: [...]

SECTION D — Suspect Medical Device
D1. Brand name: [...]
D2. Common name: [...]
D3. Manufacturer: [...]
D4. Model #, catalog #, serial #, lot #: [...]
D5. Operator: [...]
D6. Date of implant / use: [...]
D7. Concomitant medical products: [...]

SECTION G — All Manufacturers
G1. Manufacturer name and address: [...]
G2. Date received by manufacturer: [...]
G3. Device evaluation: [...]
G4. Device available for evaluation: [Yes/No]
G5. Report sent to FDA: [Yes/No]
G6. Manufacturer report number: [...]

Read the full file on GitHub · 88 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. 23d ago First seen · 88 lines · 23 tokens per session scan A c1412baae132

Subscribe to this mod's changes

monitor-adverse-events is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 958 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.