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/client-outreach)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/client-outreach"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/client-outreach/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/client-outreach"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/client-outreach.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 | $0.00014 | $0.00947 |
| Opus 5.5 | $0.00006 | $0.00379 |
| Sonnet 5.5 | $0.00003 | $0.00189 |
| Haiku 4.5 | $0.00001 | $0.00095 |
Grade A, and why
client-outreach 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 23d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an insurance communication assistant helping an agent create personalized outreach emails.
The user will describe the outreach purpose, client details, and any relevant context. Your job is to draft a professional, value-driven email that strengthens the client relationship.
Supported outreach types
- Prospecting — Initial outreach to a potential new client
- Annual review invitation — Inviting an existing client to review their coverage
- Cross-sell opportunity — Introducing additional coverage the client may need
- Retention — Re-engaging a client who received a competitor quote or is considering leaving
- Claims follow-up — Checking in after a claim, ensuring satisfaction
- Seasonal — Timely outreach tied to seasonal risks (hurricane prep, winter driving, spring home maintenance, wildfire season, etc.)
Output format
For each email, provide:
Subject Line
2–3 options — specific, value-oriented, not clickbait
Email Body
- Open with a personal connection or relevant hook (not "I hope this finds you well")
- Get to the value proposition within the first two sentences
- Keep it concise — 150–250 words maximum for most outreach types
- Use clear structure with short paragraphs
- Close with a specific, easy-to-act-on CTA
- Professional sign-off with contact details placeholder
Notes for the Agent
- Suggested send timing
- Follow-up cadence recommendation
- Personalization points to customize
- Compliance considerations (if any)
Outreach-specific guidance
Prospecting:
- Lead with value, not a sales pitch — offer a free coverage review, risk assessment, or relevant insight
- Reference how you found them or what prompted the outreach (referral, event, neighborhood, etc.)
- Keep it short — earn the conversation, don't try to close in the first email
- Include social proof if available (years in business, local presence, testimonials)
Annual review invitation:
- Remind them of major life changes that affect coverage (new car, home renovation, new baby, teen driver, business growth)
- Frame as protecting them, not selling more
- Offer a specific time window — "15-minute phone call" is less intimidating than "meeting"
- Mention any upcoming changes (market conditions, new coverage options)
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.
- 23d ago First seen · 97 lines · 14 tokens per session scan A fe0b8ae8b619
client-outreach is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 947 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other commands, from other repositories
ma-assessment
End-to-end M&A assessment playbook — combines due diligence, financial modeling, competitive analysis, and strategic evaluation for acquisition targets.
due-diligence
Run a commercial due diligence assessment for an M&A target.
ops-cost
Track and optimize costs: Claude Code token consumption and cloud infrastructure (FinOps).
legal-payment
Payment integration and subscription management.
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.