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/babyblueviper1/invinoveritasWrote 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/babyblueviper1/invinoveritas/cursor-plugin)<a href="https://agentmods.dev/plugins/babyblueviper1/invinoveritas/cursor-plugin"><img src="https://agentmods.dev/badge/plugins/babyblueviper1/invinoveritas/cursor-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/babyblueviper1/invinoveritas/cursor-plugin"><img src="https://agentmods.dev/badge/plugins/babyblueviper1/invinoveritas/cursor-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
invinoveritas 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 2d 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": "invinoveritas",
"displayName": "invinoveritas",
"version": "1.0.0",
"description": "Independent, signed pre-action verdicts for agent tool calls and merges — a neutral second opinion before an irreversible action, with a recomputable proof after, via invinoveritas's official remote MCP server.",
"author": {
"name": "invinoveritas",
"email": "[email protected]"
},
"homepage": "https://api.babyblueviper.com",
"repository": "https://github.com/babyblueviper1/invinoveritas",
"license": "MIT",
"logo": "assets/logo.png",
"keywords": [
"verification",
"review",
"safety",
"guardrail",
"mcp",
"agent",
"merge",
"irreversible-actions"
],
"category": "developer-tools",
"tags": [
"review",
"verification",
"safety",
"mcp"
],
"variables": {
"type": "object",
"properties": {
"IVV_API_KEY": {
"type": "string",
"title": "invinoveritas API key",
"description": "Free, instant Bearer token — register with a single POST to https://api.babyblueviper.com/register (no payment required; paid tools bill per call once you fund the account)."
}
},
"required": [
"IVV_API_KEY"
]
},
"mcpServers": "./mcp.json",
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 71 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.
- 2d ago First seen · 47 lines scan A f931f9d1a296
invinoveritas is a plugin published in the GitHub repository babyblueviper1/invinoveritas (5 stars, last pushed today), 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 2026-09-06.
Other plugins, from other repositories
suede-code
Code quality subset: one-pass review plus an A-F ship verdict (suede-code), deep findings with TypeScript, React, Next.js, OWASP, and database checklists (suede-code-review), a grade-only verdict with instant-F triggers and grade caps (suede-code-grader), and CI branch protection that gates the merge (suede-ci-gate).
production-audit
Exhaustive production-readiness audit: diverse-angle discovery passes to convergence, evidence-grounded per-finding verification, claim-vs-code checks, one flat severity-tagged list with file:line evidence.
ensemble
Convene a council of LLMs that independently propose, peer-review, rebut, vote, and synthesize a group-confirmed consensus answer — exposed as the ensembledebate tool plus an /ensemble command.
flagrare
Development lifecycle skills: planning, quality gates, review, documentation, and design verification.
code-simplifier
Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality.
sentient-trader marketplace
Autonomous Kalshi BTC prediction market trader. Exposes a Markov chain momentum signal engine as MCP tools Claude Code can call directly — analyze markets, size positions with Kelly criterion, and place real Kalshi orders.