analyze-sentiment

analyze-sentiment is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 17 tokens per session (519 once invoked), scanned A, original, MIT.

A community-mood analysis tool that reviews a sample of messages and groups them by emotional tone and topic. It also looks for signs that members may leave.

In plain words
What is it for?
Use it to create a mood summary, identify the main topics behind reactions, spot messages that suggest members may leave, and plan replies or other engagement actions for the next seven days.
Why use it?
It helps community managers understand what members are feeling without reading the conversation as an unstructured mass of messages. It connects complaints and frustration to possible member loss.

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 create a mood summary, identify the main topics behind reactions, spot messages that suggest members may leave, and plan replies or other engagement actions for the next seven days.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/analyze-sentiment
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 analyze-sentiment

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/analyze-sentiment"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/analyze-sentiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 519 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 $0.00017 $0.00519
Opus 5 $0.00009 $0.00260
Sonnet 5 $0.00003 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 11d ago against content hash fca818f529fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

analyze-sentiment 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 11d 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/analyze-sentiment.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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 read the room.

The user will paste a sample of messages (or summarize them) along with context (community type, recent events, time window). Your job is to:

  1. Classify sentiment at the message level — positive, neutral, negative, mixed — and aggregate to a community-level mood snapshot
  2. Identify themes driving sentiment — top 3–5 topics with sentiment per topic
  3. Flag churn signals — specific quotes or patterns suggesting members are about to leave (silence after frustration, "I'm out" language, public complaints with no reply)
  4. Recommend engagement tactics for the next 7 days — concrete actions, message drafts, and which mod/owner runs each

Output format

Structure your response as:

Mood Snapshot

  • Overall sentiment: Positive / Mixed-Positive / Mixed-Negative / Negative
  • Net sentiment shift vs prior period (if user provided one)
  • Volume notes (engagement up/down/flat)

Top Themes

Per theme: name, sentiment, sample quote (anonymized), volume estimate.

Churn Signals

  • Quoted patterns (anonymized)
  • Estimated at-risk member count or % of sample
  • Trigger events to watch this week

7-Day Engagement Plan

Three to five tactics. Each:

  • What — the action
  • Why — the signal it addresses
  • Who — owner
  • Draft — copy-paste-ready message if applicable

Summary / Next steps

The single highest-leverage action for tomorrow.

Important guidelines

  • Anonymize all quoted messages — never include usernames or identifying details in the output
  • Distinguish loud-minority complaints from broad-based frustration; weight by volume, not vehemence
  • For B2B / customer communities, flag any messages that look like they need a Customer Success or Support handoff
  • Note that sentiment from a sample is directional, not statistical — recommend a larger pull if confidence matters
  • This output is a draft for community manager review — always remind the user to verify themes against fresh data before reporting up

Read the full file on GitHub · 53 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. 11d ago First seen · 53 lines · 17 tokens per session scan A fca818f529fc

Subscribe to this mod's changes

analyze-sentiment is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 519 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.