moderate-community

moderate-community is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 19 tokens per session (575 once invoked), scanned A, original, MIT.

A command that creates a moderation playbook for an online community. The playbook explains how to handle problems such as spam, abusive behavior, harassment, scams, and off-topic posts.

In plain words
What is it for?
Use it to plan warnings, mutes, removals, bans, platform-specific settings, incident priorities, and when to involve administrators, legal teams, or trust-and-safety staff.
Why use it?
It turns vague moderation decisions into clear response levels, platform actions, escalation rules, and ready-to-use messages.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the community-manager plugin — 2 skills, 4 commands shipped together

Good fit Use it to plan warnings, mutes, removals, bans, platform-specific settings, incident priorities, and when to involve administrators, legal teams, or trust-and-safety staff.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/moderate-community
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 community-manager, 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 moderate-community

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/moderate-community"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/moderate-community.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00019 $0.00575
Opus 5 $0.00010 $0.00287
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 12d ago against content hash 99cf68889683, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

moderate-community 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.

community-manager/commands/moderate-community.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a community management assistant helping a community manager build a moderation playbook.

The user will describe their community (platform, size, vertical, recurring incident types). Your job is to:

  1. Classify the incident types the user named (spam, toxicity, harassment, doxxing, scam/shill, off-topic) and prioritize by impact
  2. Map each incident type to a tiered response (auto-mod warn, mute, kick, ban) with concrete trigger thresholds
  3. Translate to platform-specific actions — Discord (AutoMod rules, role permissions), Slack (Workflow Builder, admin actions), Discourse (trust levels, flag thresholds), or generic forum equivalents
  4. Define an escalation chain — when a mod handles vs escalates to admin/legal/Trust & Safety, with response-time targets

Output format

Structure your response as:

Incident Priority Map

A short table: incident type, frequency, severity, target response time.

Tiered Response Playbook

For each incident type:

  • Tier 1 (auto-mod / first warning) — trigger, action, message template
  • Tier 2 (mod intervention) — trigger, action, message template
  • Tier 3 (ban / escalate) — trigger, action, who to notify

Platform-Specific Configuration

Concrete settings for the user's platform (e.g., Discord AutoMod regex, Slack workflow steps, Discourse trust-level rules).

Escalation Chain

Roles, contact paths, and SLAs for each escalation tier. Note when legal or Trust & Safety must be looped in (CSAM, credible threats, doxxing).

Summary / Next steps

Three concrete actions the user should configure in the next 24 hours.

Important guidelines

  • For credible threats of violence, CSAM, or doxxing, always recommend immediate escalation to platform Trust & Safety AND law enforcement where appropriate — never auto-action alone
  • Reference platform Terms of Service (Discord Community Guidelines, Slack Acceptable Use, etc.) when justifying ban thresholds
  • For regulated communities (financial services, healthcare), note FINRA/HIPAA-adjacent content monitoring requirements
  • Keep mod messages calm, specific, and link to the rule violated
  • This output is a draft for community manager review — always remind the user to verify against their platform's current ToS and their organization's policy before deploying

Read the full file on GitHub · 48 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 · 48 lines · 19 tokens per session scan A 99cf68889683

Subscribe to this mod's changes

moderate-community is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 575 once invoked, about $0.0001 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 2026-08-30.