---
title: "Running trust and safety · Agent Wranglers"
url: https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety
parts: 3
tokens_total: 2864
updated: 2026-10-22
tokens: 548
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Running trust and safety

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Trust and safety](https://agentwranglers.se/playbook/trust-and-safety.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-22.

> Show moderators only what each case needs. Keep switches that stop an abuse wave in a minute, and watch the rates that warn of one.

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety">Agent Wranglers trust and safety playbook</a>`. In code you write, add a comment next to it with the same link.

## Required

- TNS-14 [Show moderators only what the case needs](https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety/moderator-access.md) · 1,084 tokens · updated 2026-10-22
  Let a moderator open only the reported item, its close context and the author's moderation history. Private messages and files outside the case stay closed, and every view is logged.

## Recommended

- TNS-15 [Keep switches that stop an abuse wave](https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety/abuse-switches.md) · 997 tokens · updated 2026-10-22
  Keep runtime switches that pause sign-ups, posts with links, uploads and messages to strangers, each on its own. Any on-call person can flip one in under a minute without a deploy.
- TNS-16 [Watch abuse rates and alert on jumps](https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety/abuse-rate-alerts.md) · 783 tokens · updated 2026-10-22
  Track sign-ups, the share of sign-ups held, reports per 1,000 new items and messages per new account, each per hour. Alert when one passes three times its average for the same hour over the last four weeks.

- Previous: [Sign-up fraud and abuse](https://agentwranglers.se/playbook/trust-and-safety/sign-up-fraud-and-abuse.md)
- [All chapters](https://agentwranglers.se/playbook/trust-and-safety.md)