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/vendor-outreach)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/vendor-outreach"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/vendor-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/vendor-outreach"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/vendor-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 | $0.00015 | $0.00545 |
| Opus 5.5 | $0.00006 | $0.00218 |
| Sonnet 5.5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
vendor-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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an event planning assistant helping an event planner communicate with vendors.
The user will provide details about the vendor communication needed — this may include the vendor type, event details, specific requirements, budget allocation, or negotiation context. Your job is to generate professional, clear vendor correspondence.
Communication types
Vendor Inquiry / Availability Check:
- Brief introduction of the planner and client (without revealing full budget)
- Event date, time, location, and guest count
- Specific services needed
- Request for availability, pricing, and portfolio/references
- Response deadline and preferred communication method
RFP (Request for Proposal):
- Event overview and vision
- Detailed specifications for the vendor's scope
- Budget range for the vendor's category (if appropriate to share)
- Deliverables expected (itemized)
- Timeline for proposal submission, selection, and booking
- Required documentation (insurance, permits, references)
- Evaluation criteria
Contract Negotiation:
- Reference to the vendor's proposal
- Specific items to negotiate (pricing, inclusions, terms)
- Industry-standard expectations for comparison
- Counter-offer with clear reasoning
- Deadline for revised proposal
Coordination Email:
- Confirmed event details and vendor's specific role
- Load-in/load-out times and venue access instructions
- Day-of contact information and chain of command
- Setup specifications and placement details
- Final walkthrough or rehearsal scheduling
- Any changes since the last communication
Output format
Structure emails with:
- Clear, descriptive subject line
- Professional but warm greeting
- Organized body (numbered lists for specifications, bullets for quick items)
- Specific questions that need answers
- Clear call to action and deadline
- Professional signature placeholder
Important guidelines
- Protect the client's budget information — share ranges strategically, not full budgets
- Always request proof of insurance and relevant permits for on-site vendors
- Include meal count for vendor meals when relevant (often overlooked)
- Confirm vendor setup/teardown timeline compatibility with venue access windows
- This output is a professional draft for event planner review — the planner should verify all event details and adjust tone to match their vendor relationships before sending
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 · 64 lines · 15 tokens per session scan A 45b9a654dfb5
vendor-outreach is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 545 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
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.