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/commands/vibiz-ai/vibiz-claude-plugin/ad)<a href="https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/ad"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/ad/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/vibiz-ai/vibiz-claude-plugin/ad"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/ad.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 | $0.00594 |
| Opus 5.5 | $0.00006 | $0.00238 |
| Sonnet 5.5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
ad 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 2mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vibiz:ad
Generate a polished ad creative for the project in this repo. Pulls context from the README + recent commits to write the prompt automatically — or you can override it.
Steps
- Pick the format.
- If
$1isvideo→ usevibiz_generate_ad_video. - If
$1isimage(or omitted) → usevibiz_generate_image. - If
$1is something else, treat it as the prompt override and default to image.
- If
- Pick the vibiz via the project-match skill: detect this project's brand URL and match against
list_vibizbywebsiteUrl. Exactly one match → use it. Multiple → ask. Zero → suggest/vibiz:onboard(do NOT silently fall back). - Build the prompt. Unless the user passed an override (
$2or$1when not image/video), generate one from:- First paragraph of
README.md(skip badges + headers) - The last 3 commit subjects (
git log -3 --format='%s') - Project name from
package.jsonnameor the directory name Write a 1-2 sentence visual prompt focused on the user benefit ("a busy founder shipping …" beats "a screenshot of feature X").
- First paragraph of
- Confirm with the user before generating: show the prompt + format + vibiz, ask "looks good?" — wait for yes.
- Call the tool. With
target: { vibiz: "<slug>" },useBrand: true, default platforminstagram_portraitfor image /9:16for video. - Surface the result.
- For image: poll
statusUrl(returned in the response) every ~3s untilstatus: 'completed', then showviewUrl+ the rendered image URL. - For video: same — but warn the user upfront video can take 60-180s.
- For image: poll
- Offer follow-ups:
- "Want me to draft a social post to go with this? → /vibiz:post"
- "Want to launch this as a paid Meta ad? → /vibiz:campaign" (TODO command)
Sidecase handling
- Empty README + no commits → ask the user to type a one-line prompt themselves.
- Tool returns
connectUrl(no Late profile) for downstream social/ad steps → surface the link and stop. - Don't auto-launch paid spend. Generation is free; launching costs money.
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.
- 2mo ago First seen · 36 lines · 0 tokens per session scan A 505d2a70a404
ad is a command published in the GitHub repository Vibiz-ai/vibiz-claude-plugin (7 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 594 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 2026-08-31.
ad compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adVibiz-ai/vibiz-claude-plugin | Command | 7 | 6mo ago | MIT | A | 14 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |