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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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.
[](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/analyze-sentiment)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Classify sentiment at the message level — positive, neutral, negative, mixed — and aggregate to a community-level mood snapshot
- Identify themes driving sentiment — top 3–5 topics with sentiment per topic
- 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)
- 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
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.
- 11d ago First seen · 53 lines · 17 tokens per session scan A fca818f529fc
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.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.