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/frane/grpvnWrote 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/frane/grpvn/plugin)<a href="https://agentmods.dev/plugins/frane/grpvn/plugin"><img src="https://agentmods.dev/badge/plugins/frane/grpvn/plugin/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/frane/grpvn/plugin"><img src="https://agentmods.dev/badge/plugins/frane/grpvn/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
grpvn 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 29d 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.
What it actually says
{
"name": "grpvn",
"description": "Local-first peer chat protocol for AI agents.",
"version": "0.9.3",
"hooks": "./hooks/hooks.json",
"author": {
"name": "Frane Bandov",
"url": "https://github.com/frane"
},
"homepage": "https://github.com/frane/grpvn",
"repository": "https://github.com/frane/grpvn",
"license": "Apache-2.0",
"keywords": ["chat", "coordination", "mcp", "stateful", "sqlite", "local-first"]
}
What it installs
The manifest is a name and a version. 4 hooks, 1 MCP server travel with it, and installing the plugin installs all of 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.
- 29d ago Changed a0ed6fa9393a
- 1mo ago Changed c64c46db6744
- 1mo ago Changed 988edb0bbf4b
- 1mo ago First seen · 15 lines scan A 972d37f701e2
grpvn is a plugin published in the GitHub repository frane/grpvn (5 stars, last pushed 25d ago), licensed Apache-2.0. 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 2026-08-31.
Other plugins, from other repositories
peepshow
Turn videos into a sequence of relevant still frames + transcript + a self-contained HTML report so Claude can view them as images, hear the audio, and write its analysis back into the report. Pass a local path, an http(s) URL, or pipe video bytes on stdin.
peepshow
Turn videos, YouTube links, live streams and animated images (GIF/APNG/WebP) into an ordered timeline of frames plus a transcribed audio track, so Gemini can watch and listen instead of guessing.
merit-aktiva-workspace
Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct Merit procedure: accounting (sales/purchase invoices, payments/bank reconciliation, VAT/KMD, reports, reverse charge) and payroll (employees & contracts, monthly…
dekko
Static code map for LLM agents. /map parses the repository with tree-sitter into MAP.md and map.json (every file, function, signature, type, and call edge) without spending model tokens; an 18-tool MCP server (searchcode, outline, querysymbol, getcallers, workset, impactedtests, ...) answers structural questions fr.
howl
Your AI screams — Howl listens. Blazing-fast Go statusline HUD with adaptive layouts and per-metric control.
elnora-platform
Elnora AI Platform CLI and skills.