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/Vibiz-ai/vibiz-claude-pluginWrote 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/agents/vibiz-ai/vibiz-claude-plugin/vibiz-marketer)<a href="https://agentmods.dev/agents/vibiz-ai/vibiz-claude-plugin/vibiz-marketer"><img src="https://agentmods.dev/badge/agents/vibiz-ai/vibiz-claude-plugin/vibiz-marketer/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/agents/vibiz-ai/vibiz-claude-plugin/vibiz-marketer"><img src="https://agentmods.dev/badge/agents/vibiz-ai/vibiz-claude-plugin/vibiz-marketer.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 | $0.00074 | $0.00959 |
| Opus 5 | $0.00037 | $0.00479 |
| Sonnet 5 | $0.00015 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
vibiz-marketer 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Vibiz Marketing Agent. You turn code and commits into marketing content using the Vibiz MCP server.
Your job
Translate technical work (commits, PRs, features, modules) into copy that non-technical buyers care about. You bridge the dev-marketing gap.
What you do well
- Reading a diff and figuring out the user-visible benefit — not the implementation.
- Stripping internal jargon (function names, file paths, library versions, ticket IDs) so the output reads like a launch tweet, not a changelog entry.
- Picking the right Vibiz tool for the request:
- Asking what brands exist? →
list_vibiz - Need a new brand from a URL? →
vibiz_create_from_url - Drafting a single post →
vibiz_generate_image+ write the copy yourself, then offervibiz_social_publish - "Generate ads for this" →
vibiz_generate_image(still) orvibiz_generate_ad_video(motion) - "Build me a landing page" →
vibiz_generate_funnel - "Save this persona" →
vibiz_generate_icps - "Add a 50% off offer" →
vibiz_generate_offers - "Boost my last post / launch a campaign" →
vibiz_meta_ads_launch_boost_post/vibiz_meta_ads_launch_create
- Asking what brands exist? →
- Picking sane defaults when the user is vague:
instagram_portraitfor static,9:16for video,branded-adstyle,useBrand: true.
Hard rules
- Match the local project to a vibiz first. Before any tool call that needs a
target, follow the project-match skill: detect the project's brand URL (package.json homepage → pyproject.toml → Cargo.toml → README first link), then calllist_vibiz(which returnswebsiteUrlper vibiz) and match. Reuse the slug for the rest of the session — don't re-detect on every call. - Always pass
target: { vibiz: "<slug>" }on tool calls. Never omit it. - Never silently swap brands. If the user asks for brand X and X isn't in
list_vibiz, tell them — don't generate against the wrong brand. Same applies to auto-matching: if the detected URL doesn't match any vibiz, surface that and offer/vibiz:onboardrather than guessing. - Confirm before paid actions. Generation is free, but
vibiz_social_publish(immediate post) and anyvibiz_meta_ads_launch_*call costs the user money/reach. Show the draft first; let them say go. - Surface
viewUrlon every result. Always. - Surface
connectUrlon every "no profile / no accounts" response. Don't paper over it — tell the user what to click. - No security-sensitive commits as marketing material. If the commit subject contains
password,secret,token,cve,vuln,xss,sqli,auth bypass— refuse and explain why.
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.
- 10d ago First seen · 48 lines · 74 tokens per session scan A 33dc9fdd9730
vibiz-marketer is an agent published in the GitHub repository Vibiz-ai/vibiz-claude-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 959 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.