trust-and-safety

v0.1.2

Trust & Safety team — agents for content-moderation and abuse-detection work. The trust-safety-policy-lead designs the policy taxonomy + enforcement ladder, the human-review operations layer (queue prioritization, reviewer wellness, escalation, appeals/due-process), and the measurement frame (prevalence, enforcement precision/recall, time-to-action SLA, appeal-overturn rate). The abuse-detection-engineer builds the detection stack: signals, rules-vs-ML classifiers, reviewer queues, thresholds tied to precision/recall. skills, a knowledge bank (a Mermaid enforcement decision tree + a T&S metrics catalogue with formulas), templates, best-practice rules, and an advisory hook. Seams: classifier-eval validity → applied-statistics; PII → data-governance-privacy; account-takeover → security-engineering; LLM-classifier build → claude-app-engineering. Enforcement is proportional; appeals are due process; measure prevalence, not just volume. Requires ravenclaude-core@>=0.7.0.

Claude Code3 Skills

By Matt CorbettLicense: MIT7 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 3 skill or MCP entries
Source updated: Sep 15, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install trust-and-safety for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install trust-and-safety@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/mcorbett51090/RavenClaude

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/trust-and-safety/.

Plugin files

plugins/trust-and-safety/

├── .claude-plugin/plugin.json
├── skills/build-abuse-detection-pipeline/SKILL.md
├── skills/design-moderation-policy/SKILL.md
└── skills/measure-enforcement-quality/SKILL.md

Included Skills3

build-abuse-detection-pipelineskills/build-abuse-detection-pipeline/SKILL.md

Design an abuse/fraud/spam detection pipeline — inventory signals, decide rules vs. ML (or hybrid), wire signal → score → threshold → action/reviewer-queue, and set the operating point from a precision/recall tradeoff. Reach for this when the user asks to catch an abuse type, choose signals, or route to a reviewer queue. Used by abuse-detection-engineer (primary).

design-moderation-policyskills/design-moderation-policy/SKILL.md

Design a content-moderation policy from scratch — a policy taxonomy (categories + severity tiers), a proportional enforcement ladder (warn / limit / remove / ban), and a real appeal path — by traversing the enforcement decision tree. Reach for this when the user asks to design or review a moderation policy, or to map a violation to an action. Used by trust-safety-policy-lead (primary).

measure-enforcement-qualityskills/measure-enforcement-quality/SKILL.md

Build the Trust & Safety measurement frame — prevalence (not just volume), enforcement precision/recall, time-to-action SLA, and appeal-overturn rate — with the formulas and the applied-statistics seam for eval validity. Reach for this when the user asks what to measure, whether moderation is working, or how to read a high overturn rate. Used by trust-safety-policy-lead + abuse-detection-engineer.

Plugin manifests1

plugins/trust-and-safety/.claude-plugin/plugin.json

{
  "name": "trust-and-safety",
  "version": "0.1.2",
  "description": "Trust & Safety team — agents for content-moderation and abuse-detection work. The trust-safety-policy-lead designs the policy taxonomy + enforcement ladder, the human-review operations layer (queue prioritization, reviewer wellness, escalation, appeals/due-process), and the measurement frame (prevalence, enforcement precision/recall, time-to-action SLA, appeal-overturn rate). The abuse-detection-engineer builds the detection stack: signals, rules-vs-ML classifiers, reviewer queues, thresholds tied to precision/recall. skills, a knowledge bank (a Mermaid enforcement decision tree + a T&S metrics catalogue with formulas), templates, best-practice rules, and an advisory hook. Seams: classifier-eval validity → applied-statistics; PII → data-governance-privacy; account-takeover → security-engineering; LLM-classifier build → claude-app-engineering. Enforcement is proportional; appeals are due process; measure prevalence, not just volume. Requires ravenclaude-core@>=0.7.0.",
  "author": {
    "name": "Matt Corbett"
  },
  "homepage": "https://github.com/mcorbett51090/RavenClaude",
  "license": "MIT",
  "keywords": [
    "trust-and-safety",
    "content-moderation",
    "abuse-detection",
    "spam-detection",
    "enforcement-ladder",
    "reviewer-operations",
    "appeals-due-process",
    "prevalence",
    "precision-recall",
    "policy-taxonomy",
    "classifier-thresholds",
    "sla"
  ],
  "requires": {
    "plugins": [
      "ravenclaude-core@>=0.7.0"
    ]
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[trust-and-safety on Agent Plugins Marketplace](https://pluginsmp.com/plugins/trust-and-safety)