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/ffroliva/gflow-cliWrote 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/plugins/ffroliva/gflow-cli/gflow)<a href="https://agentmods.dev/plugins/ffroliva/gflow-cli/gflow"><img src="https://agentmods.dev/badge/plugins/ffroliva/gflow-cli/gflow/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/plugins/ffroliva/gflow-cli/gflow"><img src="https://agentmods.dev/badge/plugins/ffroliva/gflow-cli/gflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gflow 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 yesterday.
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.
What it actually says
{
"name": "gflow",
"displayName": "gflow-cli",
"version": "0.85.0",
"description": "Drive Google Flow from your agent: Veo text-to-video, image-to-video and clip extension, Imagen images, reusable Characters and scene composition.",
"author": {
"name": "Flavio Oliva",
"url": "https://github.com/ffroliva"
},
"homepage": "https://ffroliva.github.io/gflow-cli/",
"repository": "https://github.com/ffroliva/gflow-cli",
"license": "MIT",
"keywords": [
"google-flow",
"veo",
"imagen",
"video-generation",
"mcp"
],
"defaultEnabled": false,
"userConfig": {
"acknowledgeBilling": {
"type": "boolean",
"title": "I understand this plugin can spend my Google account's Veo credits",
"description": "gflow's MCP server drives a real Chrome session signed in to your own Google account. Video generation bills against that account's Flow credit allowance. Images and composition are free; only Veo video spends. Enabling this plugin starts the MCP server automatically.",
"required": true,
"default": false
}
}
}
What it installs
The manifest is a name and a version. 2 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 281 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 8f70e6e13715
- 3d ago Changed b13b1d1bc59c
- 4d ago Changed bbd3d9e6b7bd
- 7d ago Changed 545d017c2c3e
- 8d ago Changed 2e51fd1f61c2
- 13d ago Changed ee988b2b7a1d
- 14d ago Changed 8a6ca0f12669
- 15d ago Changed 6b1f3694a0e1
- 16d ago Changed c36bb290be5d
- 23d ago First seen · 31 lines scan A 9e47282967e7
gflow is a plugin published in the GitHub repository ffroliva/gflow-cli (297 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
hatch3r
Tool-agnostic agentic coding setup: 30 agents, 55 skills, 74 rules, 33 commands, 7 hooks, MCP servers, and a CLI-tool surface generated for 3 AI coding tools from a single canonical source. Counts derived from governance/inventory.json.
syncpoint-ai-skill
Skills for SyncPoint — AI agent coordination protocol. Setup multi-agent projects, claim resources, manage sync gates, hand off work, review checkpoints, and guard files.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.